Professional Documents
Culture Documents
RM QueAnsfgchcgngfffhg
RM QueAnsfgchcgngfffhg
Objectives of Research:
The objectives of research application are as follows:
(1) Research extends Knowledge: Research extends knowledge of human beings, social
life and environment. Scientists and researchers build up the wealth of knowledge through their
research findings. They search answers for various types of questions: What, Where, When, How
and Why of various phenomena, and en.lighten us. The bodies of knowledge have been developed
by research in general and pure or fundamental research in particular. ·
(2) Research Unravels the Mysteries of Nature: It brings to light hidden information . that
might never be discovered fully ·.during the ordinary course of life.
(3) Research Establishes Generalizations and General Laws: Research establishes
generalizations and general laws and contributes to theory building in various fields of knowledge.
The knowledge of isolated events is connected together to draw generalizations and general laws.
Law of gravitation, Law of demand, and principles of organization such as unity of command and
scalar principle, the theory of constuner behavior and motivation theories arc some examples for
such generalizations, laws and theories.
(4) Research verifies and Tests: Research verifies and tests existing facts and cheory and
these help improving knowledge and ability to handle situations and events. Empirical research
goes far beyond the passive role ofverifying and testing theory. Research plays an active role, it
perfoms at least four major functions-initiates, formulates, deflects, and clarifies theory.
(5) General Laws Developed through Research: General laws developed through
research may enable us to make reliable predictions of events yet to happen.
(6) Applied Research Aims at Finding Solutions : Applied research aims at finding
solution sto problems-socio-eocnomic problems (e.g., social unrest, unemployment, poverty) health
problems, human relations problems in organization and so on.
Thanks to the fruits of resrach, having better quality of life, longer life span and better
control over events.
(7) It aims to develop Tools, Concepts Research also aims at developing new tools,
concepts, and theories for a bett'er study of unknown phenomena.
(8) Research Aids in Planning: Research aids planning and thus contributes to national
development. Research-social science research in particular - aids planning in the following ways:
(i) Research brings out factual data on prevailing sittiations and problems for drawing up
plans and schemes on a realistic basis. Research uncovers needed factor on which sound
decisions can be made before committing resources. Studies open up the possibility of testing
the validity of planning assumptions or premises. .
(2)
ii) Research studies enable the planners to evaluate alternative strategies and choose
the most appropriate strategies for development of the various sectors like agriculture, industry,
education, health, social welfare etc.
iii) This dissemination ot research finding creates a general awareness.of the country's
current situations and problems among the public, which inspire them to participate in
formulation and implementation of development schemes .
(9) Rational Decision Making: Analytical studies of internal an.d external environment of
business and non-business organizations provtde factoral data for rational decision making
formulation of strategies and policies. Studies of their operational problems ccntribute to an
improvement in their performance.
(4) Covers Region in which Business Opertes: It covers all the regions in which the
business operates, locally and internationally. Setting-up a hotel means knowing local . conditions,
such as attractions and competing establishments, but also problem<; such as crime-or obtaining
supplies.
(5) Judging Problems: Another characteristic of good business research is judging local
problems of the environment in which our establishment is going to operate.
(6) Flexibility: One more characteristic of good business research objectives is flexibility.
The research may be programmed for one area and then something shows-up. If that "something"
is pertinent, it should be investigated and included in the research. Research is discovering new
things and factors, it should not be easily sidetracked but it also should not be inflexible.
(7) Help determine. How to Produce the product: Good business research should include
the use of the Internet. If the business is manufacturing a specific product, look at the market s ize
and options on how to produce the product. This is part of knowing who the competitor is, but
slightly different as it helps to best determine how to produce the product.
This information goes to the executive in the form of data. On the basis this data the
executive develop plans and programmers. Advertising research, packaging rdsearch, pcrforrnancc
evaluation research, sales analysis, distribution channel, etc., may also be considered in managerial
research. Research toclls are applied ffectively for studies involving.
i) Demand forecasting.
ii) Consumer buying behavior
iii) Measuring advertising elfcctiveness
iv) Media selection for advertising
v) Test marketing
vi) Product positioning
vii) Product potential
Although the roles of managers and the research scientists are often viewed as very
different, many of the day-to-day problems of managers are similarly to those faced by researchers.
If the managers are conversant with the research methods, they can improve their problem-solving
efficiency. For example, a manager is confronted with the problem of high absenteeism in one
department. Once the problem is identified and the need to take corrective action has been
recognized, the manager must collect reliable anJ authentic information about the problem. The
manager may often have hunches about the problem, which are similar to the hypothesis of the
researcher. If the manager has sound knowledge of research methods. he can scientifically
approach the problem. Otherwise, he may try as a fledgling to act on the hunches resulting in an
inefficient and costly process of trial and error used while studying a problem. Need hardly to be
said that kn owledge of research process is highly indispensable to managers.
(1) Defining Research Problem: The first step in research is defining a research problem. It
is most important stage in applied research, as poorly defined problems will not yield useful results.
It is rightly said that, "A problem well defined is half-solved”. Poorly defined problems cause
confusion and do not allow th eresearhcer to develop a good research design.
After a problem has been chosen, the next task is to formulate it precisely. This too needs a
good deal of care on t epar to fmarketing researchers.
Essentially twu steps are involved in formulating the research problem, viz., understanding
the problem and rephrasing the same into meaningful terms from an analytical point of view.
(2) Extensive Literature Survey: Once the problem is formulated, the next step is to write
down a brief summary. For this the researcher should undertake extensive literature survey
connected with the problem. For this purpose, the abstracting and indexing journals and published
or unpublished bibliographies are the first place to go to. Academic journals, conference
proceedings," government reports, books etc., must be taped depending on the nature of the
problem.
(5)
(3) Formulation of Hypotheses: Now tlle researcher should state in clear terms the working
hypothesis. Working hypothesis is tentative assumption made in order to draw out nnd test its
logical or empirical consequences. As such the manner in which reseuch hypothesis arc developed
is particularly important s ince they pro\'ide the focal point for research. Hypothesis should be very
specific and limited to the piece of research in hand because it has to be tested. The role of the
hypothesis is to guide the researcher by clelimiting the area of research and to keep him on the right
track.
(4) Preparing the Research Design: Research design is the conceptual struciure within
which research shoulp beconducted. A.research design specifies the methods and procedures for
conducting a particular study. The researcher should specify. tne arproach he intends to use with
respect to the proposed study. The function of research design is to provide for the collection of
relevartt evidence with minimal expenditure of effort, time and money. Research designs can be
grouped into three categories - exploratory research, descriptive . research and causal
research.
(i) Exploratory Research: An exploratory Tesearch focuses on the discovery of ideas
and is generally based on secondary data. It is preliminary investigation, which does not have a
rigid design. .
(ii) Descriptive Research: A descriptive study is undertaken when the researcher
wants to know the characteristics of certain groups such as age, sex, educational level, income,
occupation, etc., In contract to exploratory studies, descriptive studies are well structured.
(iii) Causal Research: A causal research is undertaken when the researcher is
interested in knowing the cause and effect relationship between two or more variables. Such
studies are based on reasoning along well-tested lines.
(5) Determining Sample Design: All the items under considerat ion in any field of inquiry
constitute a 'universe' or 'popubtion'. A complete enumeration of all the, items in the 'population' is
known as a census inquiry. In such an 'inquiry when all the items are covered no element of chance
is left and highest accuracy is obtained. But in pwctice this may not be true. This type of inquiry
involves a great deal of time, money not energy, not only this, census inquiry is not possible in
practice under many circumstances.
The researcher must decide t!"le way of selecting a "sample" or the sample design. A
sample design is a definite plan detcnnined before any data are actually collected for obtaining a
sample from a given population. Samples can be either probability samples or non-probability
samples. With probability samples each element has a known probability of being included in the
sample. but the non-probability samples do not allow the researcher to determine this probability.
(6) Collecting the Data: The next step is to determine the sources of data to be used. The
researcher has to decide whether he has to collect primary data or depend exclusively on
secondary data. Sometimes, the research study is based on both secondary and primary data.
The primaty data are those, which are collected a fresh and for the first time, and thus
happen to be original in character.
The second:try data, on the other hand, are those which have already been colllected by
someone else and which have already been passed through the statistical process.
Any statistica data can be classified under two categories depending up on the sources
utilized. These categories are,
i) Primary sources of data
ii) Secondary sources of data
(7) Execution of the Project: The researcher should see that the project is executed in a
systematic manner and in time. If the survey is to be conducted by means of structured
questionnairres, data can be readily machine-processed. ln such a situation, questions as well as
the possible answers maty be coded. If the data are to be collected through interviews,
arrangements should be made for proper selection and training of the interviewers. The training may
be given with the help of instruction mutuals, which explain clearly the job of the interviewers at
each step. Occasional field checks should be made to ensure that the interviewers are doing their
assigned job sincerely and efficiently.
A careful vvatch should be kept for unanticipated factors in order to keep the survey as much
realistic as possible. This means that steps should be taken to ensure that the survey is under
(6)
statistical control so that the collected information is in accordance with the pre-defined standard of
accuracy.
(8) Analysis of Data: After the data have been collected, the researcher turns to the task of
analyzing them. The analysis of data requires a number of closely related operations such as
establishment of categories, the application of these categories to raw data through coding,
tabulation and then drawing statistical inrerences. Researchar should classify the raw data into
some purposeful and usable categories.
(i) Coding operation is usually done at this stage through which the categories of data
are transfonned into symbols that may be tabulated and counted.
(ii) Editing is Jhe procedure that improves the quality of the data for coding. With coding
the stage is ready for tabulation.
(iii) Tabulation is a part of the Teclmical procedure where in the classified data arc rut in
the fonn of tables.
Analysis work after tabulation is generally based on the computation of various percentages,
coefficients. etc., by applying various well-defined statistical formulae.
ln order to derive meaningful results from the statistical tables, the researcher may use one
or more of the following four steps:
(i) The first step is to calculate relevant measures of central tendency as also of dispersion
highlighting the major aspects of the data.
(ii) The second step is to cross tabulate the data to ascertain some useful relationships.
(iii) The third step is to calculate the correlation coefficient and undertake a regression
analysis between variables.
(iv) The fourth step is to undertake a multivariable analysis. Such an analysis uses a variety
of techniques to determine important relationships amongst several variables.
(9) Testing of Hypothesis: After analyzing the dta the researcher has to test the
hypothesis, various tests, such as Chi-Square test, t-test, F-test, have been develoed by
statisticians for the purpose. The hypotheisis may be tested through the use of one or more of such
tests, depending upon the nature and object of research lnquiry Hypothesis rostlng will result in
either accepting the hypothesis or in rejecting it. If the researcher had no hypothesis to start with,
generalizations established on the basis of data may be stated as hypothesis to be tested by
subsequent researches in times to come.
(10) Generalizntion and Interpretatlon: If a hypothosls Is tested and upheld several times,
It may be possible for the researcher to arrive at generalization, i.e., to build a theory. If th
eresearhcer had no hypothesis to start with, he might seek to expain his finding on the basis of
some theory. lt is known as interpretation. The process of interpretation may quite often trigger off
new questions, which in turn may lead to further researches.
(11) Preparation of the Repoct or the Thesis: Although report wrltlng needs some skill,
which con be developed with practice, te researcher should follow the main princip\es of writing a
report. Some of these principles are:
(i) There should be objectivity, coherence, clarity In the preesentatlon of ideas
(ii) Report should be written in a concise and objective style in simple language avoiding
vague expressions such as „it seems,‟ there may be‟, and th like.
(iii) Charts and illustrations in the main report should be used only it the present the
informaation more clearly and forcibly.
(iv) Calculated 'conftdence limits' must be mentioned and the various constraints
experienccd in conducting research operations may as well be stated.
(v) The layout of the report should be as follows:
a) The preliminary pages.
b) The main text and
c) The end matter.
In Its preliminary pages, the report should carry title and date followed by acknowledgements
and foreward. Then there should be a table of contents followed by alist of talbe and list of graphs
and charts, if any, given in the report.
The main text of the report should have the following parts:
(7)
(i) lntroduction: It should contain a clear statement of the objective of the research anc an
cxpl:lnat ion of' the methodology adopted in accomplishing the research.
(ii) Summary of Findings : A statement of findings, and recommendation in non-technical
language should be there after introduction. If the findings arc extensive, they should be
summarized.
(iii) Main Report: The main body of the report should be presented in logical sequence and
sections.
(iv) Conclusion: At the end of the main text, result of the research should be put clearly and
prec isely.
At the end of the report, appendices should be enlisted in respect of all technical data.
Bibliography, i.e, list of books, journals, reports, etc., consulted, should also be given in the end.
Index should also be given specially in a published research report.
Validity Generalization
(1) Objectivity: The objectivity of the procedure (either collection of data or scoring of the
responses or both) may be judged by the degree of agreement between the final scores assigned to
different individuals by more than one independent observer. The more subjective the observation,
recording and evaluation of che responses, the less the different observers agree. It is therefore,
any research design should permit the use of measuring instruments which are fairly objective and
in which every observer or judge seeing a performance arrives precisely. This ensures the
objectivity of the collected data which will be used for analysis and findings.
(2) Reliability: It is not easily tested either by the multiple-form or by the split-half technique.
The test re-test approach is the most effective measure of reliability as it refers to 'consistency'
throughout a series to measurements. Suppose, if a respondent gives a response to a question, he
is expected to give the same response to that question whenever he is asked in other form. But if
the respondent keeps on changing his responses to the same type of questiort then the interviewer
will be facing a difficulty in considering which one of their responses is genuine. The researcher
should frame this question in such a way that the respondent cannot but give only one genuine
response. Though there are some methods in determining the reliability of the responses given out
by a respondent.
(3) Validity: As in the case of reliability, there are a good number of procedures for
establishing the validity of test, such as validating the present data against a concurrent criterion or
a future criterion or a theory, etc. However, any measuring instrument is said to be valid when it
measures what it proposes to measure.
(4) Generalization: The next important aspect of a good research design is to ensure that
the measuring instruments used in a research investigation yield objective, reliable and valid data
(8)
and has to answer the 'generalization' of the findings. It will thus help an investigator in his attempt
to generalize the findings, provided he has taken due care in definmg the population, selecting the
sample and using the appropriate statistical analysis while planning his research design.
(5) Adequate Information: The most important requirement of good research design is that
it should provide adequate information so that the research problem can be analyzed on a wide
perspective. An ideal design should take into account important factors like:
i) ldentifying the exact research problem to be studied,
ii) The objective of the research,
iii) The process of obtaining information,
iv) The availability of adequate and skilled manpower, and
v) The availability of adequate financial resources for carrying-out research.
(6) Other Features: Some other important characteristics of a good research design are
flexibility, adaptability, efficiency, being econbmic and so on. A good research design should
minimize bias and maximize accuracy of the data obta:ned and should have as few <:rrors as
possible.
(3) Review of Previous Studies: Should be a brief survey of a relevant literature in the
subject concerned and presented subject wise and reviewed critically and pinpoint the stage from
where further research is called for.
(4) Definition of Concept or Theoretical Principles involved if any: Should be defined in
general terms and be linked with the study.
(5) Coverage and Scope of the Study: Should consider, geographical, temporal and
functional dimensions.
(6) Objectives of the Study: Should explain the main purp0se precisely and may be in the
form of questions or an explanation to a particular issue.
(7) Formulation of Hypothesis: Should be empirical, conceptually clear, specific, close to
things observable and related to the body of theory.
(8) Methods of Investigation: It depends upon the nature of study but researcher should
define survey methodology, and statistical techniques adopted.
(9) Sampling Design: Definition of the universe or population, size of the sample, and
representativeness of the sample should be defined.
(10) Constructing of Schedule or Questionnaire: Questions should be in an order on a
form. Open ended questions are designed to permit a free response. The questions to be asked
should have a direct bearing on the problem, avoiding the personal questions and multiple
meanings. ·
(11) Data Collection: Depends up the subject matter, the unit of enquiry and the scope of
the study.
(12) Analysis of Data: To fulfill the objective or hypothesis the researcher should analyze
the data subject to the appropriate statistical analysis besides tabulation. Tabulation of results in a
f!1eaningful way is by itself a technique and an art. The data given in the tables must be in a
selfexplanatory form.
(13) Interpretation of Results: Researcher should draw inferences based on usual test for
significance and relate with previous findings, to a wider field of generalizations, to scientific
objectivity, and to uncover any additional factors which would not be visualized by the investigator
earlier.
(14) Reporting the Findings: Should be clear, specific, simple, and directly relating to the
objective of the study. Researcher must report what has been discovered or innovated to fulfill the
need for which the study was taken up and to ensure proper directions to other researchers in
carrying out similar researches.
Sources of Data
Nature of Study
Object of Study
Object of Study
Social-Cultural Context
Temporal Context
Dimension
Figure : Steps in Research
(1) Selection and Definition of a problem Problem: The problem selected for study should
be defined clearly in operational terrns so that the researcher knows positively what facts he is
looking for and what is relevant to the study. Since human behavior, as an interaction pattern, is the
result of various forces it is best to delimit the scope of one's study which reaps ample benefits
during the actual course of data collection. Now besides the operational definition of the problem,
the problem selected should be practicable in costs of time and money. If the criteria of validity and
reliability of results are to be fulfilled, such problems considered as unmanageable by the
researcher should not be selected for the design.
(2) Sources of Data: Once the problem is selected it is the duty of the researcher to state
clearly the various sources of information such as library, personal documents, field work, a
particular residential gr{)up, etc.
(3) Nature of Study: The research design should be expressed in relation to the nature of
study to be undertaken. The choice of the statistical, experimental or comparative type of study
should be made at this stage so that the following steps in planning may have relevance to the
proposed problem.
(4) Object of Study: Whether the design aims at a theoretical understanding or
presupposes a "welfare" notion must be explicit at this point. Stating the object of the study aids not
only in clarity of the design but also in a sincere response from the respondents.
(5) Social-Cultural Context: As one would rightly remember, a research design is always
set to a context which has a social and cultural bearing on the individuals. For example, in a study of
the fertility rate in a people of "backward" class, the context of the so called "backward class of
people and the ·conceptual reference must be made clear. Unless the meaning of the term is clearly
defined, there tends to be a large variation in the study cboencnauostaet itohnes .t erm backward
could have religious, economic, and political
(6) Temporal Context: The geographical limits of the design should also be referred to at
this stage that the research related to the hypothesis is applicable to particular social groups only.
(7) Dimension: It is physically impossible to analyze the data collected from a large
universe. Hence the selection of an adequate and representative sample is the by word in any
(11)
research. Depending upon the dimension of the proposed study, such a sample of the large
population can be selected to facilitate a practical design.
(2) Understanding the Nature of the Problem: The next step in defining the problem is to
understand its origin and nature clearly. Tile researcher must understand the origin and nature of
the problem in clear terms through discussions and study of the environment within which problem
is to be solved. The best way of under standing the problem is todiscuss it with those who first
raised it in order to find out how the probiem originally came about and with what objectives in view.
If the researcher has stated the problem himself: he should consider once again all those points that
induced him to make a general statement concerning lhe problem. For a better understanding of the
nature of the problem involved, he can enter into discussion with those who have a good knowledge
of the problem concerned or similar other problems. The researcher should also keep in view the
environment within which the problem is to be studied and understood.
(3) Surveying the Available Literature: It is important to review and serve all the possible
literature that is available on the research area prior to defining the research problem. It a:;sists a
researcher to look into newer dimensions in that particular area and leads to enhancement of
knowledge. All available literature concerning the problem at hand must necessarily be surveyed
and examined before a definition of the research problem is given. This means that the researcher
must be well conversant with relevant theories in the field, reports and records as also all other
relevant literature. He must devote sufficient time in reviewing of research already undertaken on
related problems. This is done to find out what data and other materials, if any, are available for
operational purposes. "Knowing what data are available often serves to narrow the problem itself as
well as the technique that might be used." This would also help a researcher to know if there are
certain gaps in the theories, or whether the existing theories applicable to the problem under study
are incons-istent with each other, or whether the findings of the different studies do not follow a
pattern consistent with the theoretical expectations and so on. All this will enable a researcher to
take new strides in the field for furtherance of knowledge. i.e., he can move up starting from the
existing premise. Studies on related problems are usefal for indicating the type of difficulties that
may be encountered in the present study as also the possible analytical shortcomings. At times
such studies may also suggest useful and even new lines of approach to the present problem.
(4) Developing the Ideas through Discussions: Persons who have knowledge or have
rich experience in the area of research have proved to be good sounding . board for a researcher.
Their ad"ice and comment on research proposal help a researcher to have better clarity and focus
on his research topic.
Discussion concerning a problem often produces useful information. Various new ideas can
be developed through such an exercise. Hence, a researcher must discuss his problem with his
colleagues and others who have enough experience in the same area or in working on similar
problems. This is quite often known as an experience survey. People with rich experience are in a
position to enlighten the researcher on different aspects of his proposed study and their advice and
comments are usually invaluable to the researcher. They help him sharpen his focus of attention on
(13)
specific aspects within the field. Discussions with such persons should not only be confined to the
formulation of the specific problem at hand, but should also be concerned with the general approach
to the given problem, techniques that might be used, possible solutions, etc.
(5) Rephrasing the Research Problem: Finally, the researcher must sit to rephrase the
research problem into a working proposition. Once the nature of the problem has been clearly
understood, the environment (within which the problem has got to be studied) has been defined,
discussions over the problem have taken place and the available literature has been surveyed and
examined, rephrasing the problem into analytical or operational terms is not a difficult task. Through
re-phrasing, the researcher puts the research problem in as specific terms as possible so that it may
become operationally viable and may help in the development of working hypotheses. In addition to
what has been stated above, the following points must also be observed while defining a research
problem:
i) Technical terms and words or phrases, with special meanings used also the statement of
the problem, should be clearly defined.
ii) Basic assumption one postulates (if any) relating to the research problem should be
clearly stated.
iii) A straightforward statement of the value of the investigation (i.e., the criteria for the
selection of the problem) should be provided.
iv) The suitability of the time-period and the sources of data available must also be
considered by the researcher in defining the problem
v) The scdpe of the investigation or the limits within which the problem is to be studied must
be mentioned explicitly in defining a research problem.
(6) Redefining the Research Problem: Many a times, a problem redefinition happens once
the steps listed in a, b, c & d above are undertaken. Researcher often redefines the problem in a
manner which is more viable. and logical for the conduct of the research. This· effort also helps in
defining hypothesis more sharply.
(2) Prodution: Different research topics studied under production anagement are:
(i) Forecasting,
(ii) Capacity planning,
(iii) Plant location,
(iv) Plant layout,
(v) Line balancing,
(vi) Line of balance,
(vii) Inventory control,
(viii) Aggregate planning,
(ix) Master production scheduling,
(x) Materials requirements planning,
(xi) Single-machine scheduling,
(xii) Flow-shop scheduling,
(xiii) Job-shop scheduling,
(xiv) Project management,
(xv) Maintenance management,
(xvi) Quality ~ontrol,
(xvii) Work design,
(xviii) Modem production system design, like JIT, computer integrated manufacturing, flexible
manufacturing, agile manufacturing, logistics management, total quality· management,
etc.
(3) Finance: Different research topics studied under financial management are:
(i) Models for break-even analysis of multi-product,
(ii) Economic evaluation of alternatives,
(iii) Study of financial parameters of organizaticas,
(iv) Capital budgeting,
(v) Ratio analysis,
(vi) Portfolio management,
(vii) Primary market study,
(viii) Secondary market study,
(ix) Balance of payment,
(x) Inflation,
(xi) Deflation,
(xii) Economic growth models.
Working hypothesis are more useful when stated in precise and clearly defined terms.
A basic fact about testing hypothesis is that a hypothesis may be rejected but That the
hypothesis never can be unconditionally accepted until all possible evidence is evaluated. In the
case of sampled data, the information set cannot be complete. So, if a test using such data does not
reject a hypothesis, the conclusion is not necessarily that the hypothesis should be accepted.
The nuII hypothesis in an experiment is the hypothesis that the independent Variable has
no effect on the dependent variable. The null hypothesis is expressed as H0. This hypothesis is
assumed to be true unless proven otherwise. The alternative to the null hypothesis is the hypothesis
that the independent variable does have an effect on the dependent variable. This hypothesis is
known as the alternative, research or experimental hypothesis and is expressed as H1. This
(16)
alternative hypothesis states that the relationship ohserved between the variables cannot be
explained by chance alone .
Characteristics ofHypothesis
(1) Clarity: Hypothesis should be clear and precise. If the hypothesis is not clear and
precise, the inferenc.!s drawn on its basis cannot be taken as reliable.
(2) Testable: Hypothesis should be capable of being tested. In case of un-testable
hypotheses, many a time the research programmes close down. Some prior study may be done by
researcher in order to make hypothesis a testable one. A hypothesis '"is testable if other deductions
can be made from it which, in tum can be confirmed or disproved by observation.”
(3) Relationship: Hypothesis state relationship between variables, if it happens to be a
relationalltypothesis.
(4) Specific: Hypothesis should be limited in scope and must be specific. A researcher must
remember that narrower hypotheses are generally more testable and he should develop such
hypotheses.
(5) Simple: Hypothesis should be stated as far as possible in most simple terms so that the
same is easily understandable by all concerned. But one must remember that simplicity of
hypothesis has nothing to do with its significance.
(6) Consistent: Hypothesis should be consistent with most known facts, i.e., it must be
consistent with a substantial body of established facts. In other words, it should be one which judges
accept as being the most likely.
(7) Testable: Hypothesis should be amenable to testing within a reasonable time. One
should not use even an excellent hypothesis, if the same cannot be tested in reasonable time for
one cannot spend a life-time collecting data to test it.
(8) Explainable: Hypothesis must explain the facts that gave rise to the need for
explanation. This means that by using the hypothesis plus other known and accepted
generalizations, one should be able to deduce the original problem conditior. Thus hypothesis must
actually explain what it claims to explain it should have empirical reference.
Importance of Hypothesis
(1) Hypothesis supports the research to find and answer to a problem. It is express in declarative
form. The most important thing is it will provide a guideline to the problem.
(2) A hypothesis states what researchers are looking for. When facts are assembled, ordered, and
seen in a relationship they constitute a theory. The theory is not speculation but is built upon
fact. Now the various facts in a theory may be logically analyzed and relationships other than
those stated in the theory can be deduced. At this point there is no knowledge as to whether
such deductions are correct. The formulation of the deduction however constitutes a
hypothesis; if verified it becomes part of a future theoretical construction.
(3) A hypothesis looks forward. rt is a proposition which can be put test to determine its validity. lt
may seem contrary to or in accord with common sense. It may prove to be correct or incorrect.
In any event however, it leads to an empirical test.
(4) Hypothesis to state a specific relationship between phenomena in such a way that this
relationship can be empirically tested. The basic method of this demonstration is to design the
research so that logic will require the acceptance or rejection of the hypothesis on the basis of
resulting data.
(5) It provides a direction to the research and prevents waste of time and effort
(6) It sets to the researcher's point of view.
(7) It helps the researcher to look into a particular aspect of the problem thereby offering certain
issues and facts.
(8) It provides the methods to be used in solving the problem.
(9) It acts as a framework for analysis and interpretation of the data to draw conclusions.
(10) It suggests the areas of importance which need more attention or more collection of facts by
the researcher.
(11) A hypotheisis ensures the entire research process remains scientific and reliable and following
the principles of deduction.
(17)
Thus, a hypothesis is a very important tool in a research study; hence all researches need to
have a hypothesis irre pective of the kind or nature of the study. However, it should not be thought
that a research cannot be conducted at all without creation of hypothesis. There are m:my
descriptive as well as historical researches that have been. conducted without hypothesis. But
certainly a research can be more productive and accurate in terms of results if a researcher forms
hypothesis before proceeding with his research work.
(2) Alternative Hypothesis: Any hypothesis which is complementary to the null hypothesis
is called an alternative hypothesis and is usually denoted by H1 or H •. For example, if we want to
test the null hypothesis that the average height of the soldiers is 162 ems., i.e.,
H1 : = 162 cms. = 0 (say)
Then the alternative hypothesis could be:
(i) H1 : 0 (i.e., > 0 or < 0)
(ii) H1 : > 0
(iii) H1 : < 0
Test statitistics
Doing computation
Making Decision
Step 1: Set up a Statistical Hypothesis: The first thing in hypothesis testing is to set up a
hypothesis about a population parameter. Then we collect sample data produce sample statistics,
and use this information to decide how likely it is that our hypothesized population parameter is
correct. Set up a hypothests
Step 2: Set up a Suitable Significance Level: Having set up the hypothesis, the next step
is to test the validity of H0 against that of H. at a iin level or significance. The hypotheses are tested
on a pre-determined level of significance and as such the same should be specified. Generally, in
practice, either 5% level or 1% level is adopted for the purpose. The factors that affect the:: level of
significance are:
(i) The magnitude of the difference between sample means;
(ii) The size of the samples;
(iii) The variability of measurements within samples; and
(iv) Whether the hypothesis is directional or non-directional.
A ditectional hypothesis is one which predicts the direction of the difference between, say,
means). In brief, the level of significance must be adequate in the context of the purpose and nature
of enquiry.
Step 3: Test Statistic: The next step is to compute an appropriate test statistic which is
based on an appropriate probability distribution. It is used to test whether the null hypothesis set-up
should be accepted or rejected. Some probability distributions that are commonly used in testing
procedures are t, F and 2. Test criteria must employ an appropriate probability distribution. For
example, if only smali sample information is available, the use of the normal distribution would be
inappropriate.
Step 4: Ooing Computations: Having taken the first three steps, we have completely
designed a statistical test. We now proceed to the fourth step - performance of variou;,
computations - from a random sample of size n, necessary for the test. These calculations include
the testing statistic and the standard error of the testing statistic.
Step 5: Making Decision: Lastly, a decision should be arrived as to whether the null
hypothesis is to be accepted or rejected. ln this regard the value of the test statistic computed to test
the hypothesis plays a very important role. Ifthe computed value of the test statistic is less t.'lan the
critical value, the computed value of the test statistic falls in the acceptance region and the null
hypothesis is accepted. If the computed value of the test stati~ic is greater tha..t1 the critical value,
the computed value of the test statistic falls in the rejection region and null hypothesis is rejected.
Usually 5% level of significance = 0.05 is used in testing a hypothesis and taking a decision unless
otherv•ise any other level of sign!ficance is specifically stated.
(2) Suiitability of Data: The data that are suitable for one enquiry may not nessarily be
found Sl,litable in another enquiry. Hence, if the available data are found to be unsuitable, they
should not be used by the researcher. In this context, the researcher must very carefully scrutinize
the definition of various terms and units of collection used at the time of collecting the data from the
primary source originally. Similarly, the object, scope and nature of the original enquiry must also be
studies. If the researcher finds differences in these, the data will remain unsuitable for the present
enquiry and should not be used.
(3) Adequacy of Data: If the level of accuracy achieved in data is found inadequate for the
purpose of the present enquiry, they will be considered as inadequate and should not be used by
the researcher. The data will also be considered inadequate, if they are related to an ~rea, which
may be either narrower or wider than the area of the present enquiry.
From all this we can say that it is very risky to use the already available data. The already
available data should be used by the researcher only when he finds them reliable, suitable and
adequate.
(2) External Secondary Data: The second forms of secondary data are external sources
which are generally published and are available in different forms and form different· sources.
Although external secondary data may be obtained from different sources, some of the sources are
given here.
(i) Libraries: Researchers first attend libraries to find out relevant data pertaining to
research. They provide many sources where suitaole data may be obtained. Public libraries and
college and University libraries contain a large amount of business information, which provides
sources o other data. Management books, theses, management journals and other publications
can be consulted in these libraries. Management institutes, research institutes, banks, insurance
companies, public utility companies and manufacturing units have maintained adequate libraries.
(ii) Literature: A great amount of secondary data is available from literature, particularly
literature on marketing subjects. With the development of marketing researches in different
countries, new and interesting facts are coming into the picture, which are available in various
publications. Consultations of this literature may provide proper guidance pertaining to publication,
which can be used from time to time.
(iii) Periodicals: Business periodicals published fortnightly, monthly, quarterly, semi
annually and annually are often consulted by the marketing executives and researchers to plan
(23)
and design their marketing research. Also to use the available data for research purposes and to
verify the conclusions derived frorn the marketing research, especially of field research. Periodical
economic abstracts on economics, finance, trade, transport, industry, labor and management are
being prepared by the Government as well as by the non-government agencies. Journals of the
Marketing Association, management Association, Research Agencies, Advertising Agencies and
other related periodicals are becoming very common in India and abroad.
(iv) Census and Registration Data: Census and registration data have become very
comprehensive sources of marketing research. Previously, these concentrated only one
population census, but it now extends to many areas.
(2) Data Classified According to Function: Data are also classified according to their
functions. While planning data, the researchers anticipate the future analysis and synthesis
according to their function. They try to avoid redundant data and collect necessary data. Data
according to function may be causal, payoff, descriptive and classification.
(i) Causal Data: Causal data reveal the cause and effect relationship. One hypothesis is
measure in terms of effects. Data required to measure the hypothesis are termed causal data.
Such types of causa! data are required in the marketing mix. They are used for experimental
purpose in all the fields of marketing variables.
(ii) Payoff Data: The payoffs are resultant data. They are the outcome of certain causal
data, i.e., results of certain phenomenon. The causal variables are measured in terms of payoff or
effects. This means that payoff data are required to measure the causal variables.
(iii) Descriptive Data: There is need of such types of data, which may describe the
situation, statement and facts. Even in the case of experimental data, one variable requires to be
controlled for which descriptive data are used. In such cases, a description of the samples is
needed when drawing conclusions.
(iv) Classification Data: In sophistication experimental design the compound data have
been classified to arrive at simple analysis and conclusions. The classification data, i.e., the data
classified. in relevant categories are conceivable and may be easily described. The classification
data in complex and multiple groups, i.e., more than one causal variable or rotation of treatments
in sub-groups have functional utility. The sample survey also provides classification data, e.g ..
according to age, sex, income, location etc.
(26)
Significance of Primary Data
(1) Reliability: The information collected for primary data is more reliable than'those
collected from the secondary data because these informations are collected directly from the
respondents. So these carries higher rate of reliability.
(2) Availability of a Wide Range of Techniques: There are a lot of techniques that can be
employed, means that all information necessary can be obtained through using the appropriate
techniques, enabling all areas of the research topic to be- answered and investigated thoroughly
and effectively.
(3) Addresses Specific Research Issues: Carrying-out their own research allows the
marketing organization to address issues specific to their own situation. Primary research is
designed to collect the information the marketer wants to know, and report it in ways that benefit the
marketer.
(4) Greater Control: Not only does primary research enaLle the marketer to focus on
specific issues, it also enables the marketer to have a higher level of control over how the
information is collected. In this way the marketer can decide on such issues as size of project (e.g.,
how many responses), location of research (e.g., geographic area), and timeframe for completing
the project.
(5) Efficient Spending for Information: Unlike secondary research, where the 'marketer
may spend for information that is not needed, primary data collections' focus on issues specific to
the researcher improves the chances that research funds will be spent efficiently.
(6) Proprietary Information: Information collected by the marketer using primary research
is their own and is generally not shared with others. Thus, information can be kept hidden from
ccmpetitors, and potentially offer an "information advantage" to the comp.:ny that undertook the
primary research.
Types of Questionnaire
It is possible to classify questionnaires studies on a variety of bases. Three such ·bases,
which are of importance, are:
1) The degree to which the questionnaire is formalized or structured;
2) The disguise or lack of disguise of the objectives of the questionnaire;
3) The communication method used.
Questionnaires can be constructed so that the objective is clear to the respondent (none
disguised); or they can be constructed so as to disguise the objective. Using these two bases of
classifications, four types of studies can be distinguished as below:
Types of Questionnaire Studies
Structured Non-structured
Non-disguised Most questionnaires. Some focus groups and depth
Example: Does your family own a interviews.
piano? Example: Ask respondent(s) to
discuss what they think when
canned soup is mentioned.
Disguised Some attitude measurements. Some projective techniques
Example: Which of the following eat a Example: Nescafe.
lot, and which a little, oatmeal :
farmers, Movie actors, etc.
Questionnaire Designing
Questionnaire construction is still much more of an art than a science. Most of what is known
about making questionnaires is the result of general experience. Neither a basic theory nor even a
fully systematized approarch to the problem has been developed.
Questionnaire construction is discussed in nine steps. These steps may vary in importance
in individual projects, but each step must receive attention in each case. The steps of designing
questionnaire are shown in below figure:
Determine What Information is Wanted
Check Questions
Pretest
(6) Decide on Question Seql!ence: Once the wording of the individual questions has been
determined, it is necessary to set tbem up in some order. The sequence can influence the results
obtained. A questionnaire has three major sections:
i) Basic information
ii) Classification information
iii) Identification information
(7) Decide on Length of Questionnaire: How long the questionnaire/ sch.edule would be
depends upon:
i) What the researcher wants to know and how many items are necessary so that the data
will be credible;
ii) On the tyre of study (since self-administered) questionnaires may be shorter than face-to-
face interviews;
(iii) On the time v.ilich the researcher has available for the study;
(iv) On the time the respondents can and will take; and
(v) On researcher's resources. .
For obtaining necessary and adequate data and credible answers, it is necessary that the
length of the queJtionnaire should be given importance, i.e., it should be reasonably long. It is
equally important that time for filling up questionnaires or responding to interview schedule is
generally limited to 30-40 minutes in comparison to face-to-face interview which can continue for 60
minutes. Another consideration is the respondents. How long can they are available? Will they take
interest in answering questions seriously? Young people may be available for less time than the
middle-aged and the old people
(8) Decide on Layout and Reproduction: The physical layout and reproduction of the
questionnaire influence the success of the interview. While planning the layout and reproduction,
three important points are considered. They are:
(i) Accepting of the Questionnaire: The physical appearance of the questionnaire
influences the interests and attitude of the respondents. If the questionnaire is prepared on rough
paper, typed unimpressively and designed poorly it may not attract the respondents to read and
answer the questions. On the other ht.nd, a questioil.taire typed or printed on good quality paper
may attract the respuiiuents to read it The respondents may be requested not to disclose their
identities. The researchers, sometimes, to avoid any bias, may avoid the use of their company's
name.
(ii) Ease to Control: The questionnaire should be numbered serially to make it possible to
control the questionnaire in the operation. It will make it easy to edit and tabulate the answers. All
questions must be accounted and evaluated properly. Numbered questions are easy to follow and
simple to operate throughout the survey time, and analyze thereafter.
(iii) Ease of Handling: The reproduction of a questionnaire may influence the fieldwork
and analysis. It is essential that a large number of questions must not be put in a short space. If
the questionnaire is crowded, it makes a bad appearance. This may cause errors in collection of
data and tabulation as it is hard to read the answers. Too large a questionnaire cannot be
handled properly. Questions should be laid out and reproduced in an easy way for the field worker
to follow the sequence.
(9) Check Questions: Once the first draft of the questionnaire has beencompleted, and
before it is actually pre-tested, it is a gooJ idea to get one (or more) expert's opinion of the
questionnaire. A person who is expert in research methodology can help to catch methodoiogical
weaknesses in the instrument, such as faulty scales, inadequate instructions, etc. A person who is
familiar with the topic of the questionnaire can he:p in assessing the face validity of the questions.
Do they make sense; are they easy to understand, do they ask what they are supposed to asking?
(31)
(10) Pretest: Before the questionnaire is ready for the field, it needs to be preder tested field
conditions. No researcher can prepare a questionnaire so good that improvements cannot be
discovered in field test. Researchers have reported pre-testing, changing, and pre-testing again for
as many as 25 times before they were satisfied with some questionnaires. One pretest is as much,
however, as most questionnaires get.
One important objective of pre-testing questionnaires is to get at the thinking behind the
answers so that the auditor can accurately assess whether the questionnaire is being filled-out
properly, whether the questions are actually understood by respondents, and whether the questions
ask what the auditor thinks they are asking. Pre-testing also helps to assess whether respondents
are able and willing to provide the needed information.
In pre-testing, the respondents should actually fill-out the questionnaire, giving their views
along the way or afterward. Pretests are best done by personal interview, even if the survey is to be
handled by mail or telephone. Interviewers can note respondent reactions and attitudes which
cannot otherwise be obtained. After any pertinent changes in the questionnaire have been made,
another pretest can be run by mail or telephone if those methods are to be used in the survey. This
latter pretest should uncover any weakness peculiar to the method of communication. Pre-testing
allows the responsible auditor to test solutions to problems with the questionnaire. For example, if
considering different wording for a question, one wording can be used with half the pre-test sample
and a second wording with the remaining sample to see which works best.
(11) Revision and Final Draft: After each significant revision of the questionnaire, another
pretest should be run. When the last pretests suggests no new revisions, the researcher is ready to
print the actual questionnaires be used in the survey.
For example,
1) Population of books in the Natior:al Library,
2) Population of the heights of lndiar.~,
(34)
3) Population of Nationalized Banks in India etc.
Sampling Concepts
The basic concepts underlying sampling are as follows:
(1) Population or Universe: The entire aggregation of items from which samples can be
drawn is known as a population. In sampling, the population may refer to the urits, from which the
sample is drawn. Population or populations of interest are interchangeable terms. The term "unit" is
used, as in- a business research process; samples are not necessarily people all the time. A
population of interest may be the universe of nations or cities. This is one of the first things the
analyst needs to define properly while conducting a business research.
(2) Census: A complete study of all the elements present in the population is known as a
census. It is a time consuming and costly process and is, therefore, seldom a popular method with
researchers. The general notion that a census generates more accurate data than sampling is not
always true. Limitations include failure in gathering a complete and accurate list of all the members
of the population and refusal of the elements to provide information.
(3) Sample and Sampling: A sample is a part of the total population. It can be an individual
element or a group of dements selected from the population. Although it is a subset, it is
representative of the population and suitable for research in. terms of cost, convenience, and time.
The sample group can be selected based on a probability or a nonprobability approach. A
sample usually consists of various units of the population. The size of the sample is represented by
'V'.
(4) Precision: Precision is a measure of how close an estimate is expected to be, to the true
value of a parameter. Precision is a measure of similarity. Precision is usually expressed in terms of
imprecision and related to the standard error of the estimate. Less precision is reflected by a larger
standard error.
(5) Bias: Bias is a term that refers to how far the average statistic lies from the parameter it
is estimating, that is, the error, which arises when estimating a quantity. Errors from chance will
cancel each other out in the long run, those from bias will not.
Prerequisites of Sampling
The essentials that a sample must posses are:
(35)
(1) Representation: A sample must represent the proper universe otherwise it must
interpret a wring result. For the purpose a sample method is used.
(2) Adequacy: The size of the sample used must be adequate.
(3) Independence: Every item of the sample must be independent so that each get same
chance of being of selected.
(4) Homogeneity: The sample must give the more or less the same unit if the samples are
taken from the same universe.
Principles of Sampling:
The process of sampling is based on the following important principles of
(1) Law of Statistical Regularity: This law states that a moderately large number of items
selected at random from a given population exhibit nearly the same composition and characteristics
of the population.
(2) Law of Inertia of Large Numbers: This law states that, other things remaining the
same, the larger the size of the sample, the more accurate is Rtheeg ruelsauriltty o. btained. This is
nothing but a corollary to the Law of Statistical Regularity.
(3) Principle of Persistence: If some items of the universe possess some soecific
characteristics, these characteristics would be found in the sample also and even if the sample size
is increased or the population is increased, these characteristics would be reflected in the same
manner as in the previous case.
(4) Principle of Optimization: According to this principle, effort should be made to get best
possible or optimum results b'oth in terms of cost as well as efficiency. Larger the size of the sample
more would be the cost of conducting the survey, but better would be the efficiency also. The size is
maintained in such a way that the results are optimized in terms of cost and efficiency.
(5) Principle of Validity: A sample design is called valid only when the inferences drawn
from it are valid for the universe from which the sample has been taken. At a later stage we will
arrive at a conclusioa that in general, samples which are drawn at random would be found to be
more valid than those drawn otherwise.
Advantages of Sampling
The important advantages of sampling over complete enumeration are briefly stated Lelow:
(1) Need for Sampling: Sometimes there is a need for sampling. Suppose researcher want
to· inspect the .eggs, the bullets, the missiles, and the tires of some firm. The study may be such
that the objects are destroyed during the process of inspection. Obviously, researcher cannot afford
to destroy all the eggs and the bullets, etc. researcher have to take care that the wastage should be
minimum. This is possible only in sample study. Thus sampling is essential when the units under
study are destroyed.
(2) Saves Time and Cost: As the size of the sample is small as compared to the population,
the time and cost involved on sample study are much less than the complete counts. For complete
count huge funds are required . There is always the problem of finances. A small sample can be
studied in a limited time and total cost of sample study is very smalL For complete count, researcher
need a big team of supervisors and enumeration who are to be trained and they are to be paid
properly for the work they do. Thus the sample study requires less time and less cost
(3) Reliability: If researcher cllect the information about all the units of population, the
collected inforn:ation may be true. But researcher is never sure about it Researcher does not know
whether the information is true or is completely false: Thus researcher cannot say anything with
confidence about the quality of informatron. Researcher says that the reliability is not possible. This
is a very important advantage of sampling. The inference about the population parameters is
possible only when the sample data is collected from the selected sample.
(4) Provides Information: Sampling provides information that is almost as accurate as that
obtained from a complete census; rather a properly designed and carefully executed sample survey
will provide more accurateresults.
Moreover, owing to the reduced volume of work, persons of higher caliber and properly
trained can be employed to analyze the data.
(36)
(5) Obtaining Data when Measurement Process Physically Damages: Sampling is
essential to obtaining the data when the me"Surement process physically damages or destroys the
sampling unit under investigation. For example, in order to measure the average lifetime of light
bulbs, the measurement process dest.roys the sampling units, i.e., the bulbs, as they are used until
they bum-out A manufacturer will therefore use only a sample of light bulbs for this purpose and will
not bum-out all the bulbs produced. Similarly, the whole pot of soup cannot be tasted to determine if
it has an acceptable flavor.
(6) Obtaining Information when Population Appears Infinite: Sampling may be the only
means available for obtaining the needed information when the population appears to be infinite or
is inaccessible such as the population of mountainous or thickly forested areas. In such cases,
taking complete census to collect data would neither be physically possible nor practically feasible.
(7) Smaller "Non-Response": Sampling has much smaller "non-response'", following-up of
which is much easier. The term non-response means the no availability of information from some
sampling units included in the sample for any reason such as failure to locate or measure some of
the units, refusals, not-at-home, etc.
(8) Census Information: Sampling is extensively used to obtain some of thecensus
information.
(9) More Efiective: Sampling is more effective because every individual in the population
has an equal chance of being included in the sample.
(10) More Accurate: Fewer errors are made because small data are involved in collection,
tabulation, presentation, analysis, and interpretation.
(11) Gives More Comprehensive Information: A small sample results in a more thorough
investigation of the study, thus, giving more comprehensive information because all the members of
the population have been given an equal chance of being included in the sample.
Disadvantages of Sampling
If sampling design has its strengths, it also has its weaknesses. The following are
disadvantages of sampling designs:
(1) More Care in Preparing: Sample data involve more care in preparing detailed sub-
classification because of the small number of cases as subjects.
(2) Misleading Result: If the sampling plan is not correctly designed and followed, the
results may be misleading.
(3) Requires Expert: Sampling requires an expert to conduct the survey in an area; if this is
lacking, the result is erroneous.
(4) Accuracy and Reliability: Less accurate and reliable because the sample may not be a
true representative of the population. This disadvantage can be minimized by selecting a sample
such that it is a true representative of the population; but it cannot be eliminated. However, if the
population size is quite large and the collection of data needs more than normal knowledge and
skills; these disadvantages could be eliminated.
(5) Size of the Sample: The major problem in sampling is to determine the size of the
sample. T!-te size of the sample need for a valid survey depends on many variables including the
risk, researcher are willing to accept and the characteristics of the population itself. Here, it is
sufficient to say that if sampling becoMes too complicated or the required sample size becomes too
large, the easiest solution may be to survey the entire population.
(6) Determining The Representativeness Of The Sample: Determining the
representativeness of the sample is the surveyor's greatest problem when sampling. By definition,
"sample" means a representative part of an entire group. To avoid the charge of using "biased
data", it is necessary to obtain a sample that meets the requirement of representativeness and this
is not an easy task. Without a representative sample, a survey will, at best, produce results that are
misleading and potentially dangerous.
(7) Involves Risk: It is important to realize that using a sample from a population to infer
something about the entire population involves a risk. The risk results from dealing with partial
(37)
information. If risk is not acceptable in seeking the solution to a problem or the answer to a question,
then a complete survey or census, rather than a sample survey, must be conducted.
Probability Sampling
Sequential Sampling
The method of simple random sampling eliminates the chance of bias or personal prejudices
in the selection of units:
For example of a sample random sample would be a group of 25 employeeschosen out of a
hat from a company of 250 employees. In this case, the population is all 250 employees and the
sample is random because each employee has an equal chance .of being chosen.
(38)
Though the method is simple and easy to apply, but un case the size of the population is
infinite, the method becomes unmanageable.
i) By Using Random Numbers: A number of people viz. L.H.C. Tippet, Fisher and Yates,
Kendall and Smith, Oliver and Boyd and Rand Corporation constructed setof random numbers.
These numbers can be used to select random samples from a given population. A table of true
random numbers is one in which any digit from 0 to 9 has an equal chance of appearing in any
position of the table. Random numbers are most useful when population is of infinite size. The digits
in random number tables are selected at random and are arranged independently of digits
occu.Pying other places in a number. The random number table prepared by. L.H.C. Tippet contains
a set of 10400 four numbers.
ii) Sample Size within Strata: We-can use either a proportional or a disproportional
allocation. In proportional allocation, one samples each stratum in proportion to its relative weight. In
disproportional allocation this is not the case. It may be pointed out that proportional alllocation
approach is sample and if all one knows about each stratum is the number of items in that stratum;
it is generally also the preferred procedure. In disproportional sampling, the different strata are
(39)
sampled at different rates. As a general rule when variability among observations within a stratum is
high, one samples that stratum at a higher rate than for strata with less internal variation.
For example, suppose a researcher wishes to study retail sales of product such as 'wheat'
in a universe of 100,000 grocery stores. The researcher might first subdivide this universe into three
strata, based on store size, as illustrated below :
Store size Stratum Number of Stores Percentage of stores
Large stores 20,000 20
Medium stores 30,000 30
Small stores 50,000 50
Total 1,00,000 100
For example, the city map is used for area sampling. Various blocks provide the frame and
each of them are numbered and used for the sampling. For sampling blocks stratification is
employed, which is based on geographical considerations. Thus blocks are needed to be identified
and than a stratified sample of dwellings can be selected. Finally blocks are subdivided into
segments of a more or less equal size and a sample of these segments may be taken in the
sample.
(40)
Non-Probability Sampling
Sequential Sampling
(1) Convenience Sampling: In convenience sampling selection, the researcher chooses the
sampling units on the basis of convenience or accessibility. It is called accidental samples because
the sample-units enter by accident. This is also known as a sample of the man in the street, i.e.
selection of units where they are. Sample units are selected because they are accessible .
For example, in testing a potential new product, the sample work is done by adding the new
product to the appropriate shops in the locality. Purchasing and selling ofthe new product is
observed there.
(2) Judgment Sampling: A method of non-probability sampling that is sometimes
advocated is the selection of universe items by means of expert judgment. Using this approach,
specialists in the subject matter of the survey choose what they believe to be the best sample for
that particular study.
For example, a group of sales managers might select a sample of grocery stores in a city
that they regarded as "representative." This approach has been found empirically to produce
unsatisfactory results, And, of course, there is no objective way of evaluating the precision of
sample results. Despite these limitations, this method may be useful when the total size is extremely
small.
(41)
(3) Quota Sampling: One of the most commonly used non-probability sample designs is
quota sqmpling, which enjoys its most widespread use in consumer surveys. This sampling method
also uses the principle of stratification. As in stratified random sampling, the researcher begins by
constructing strata. Bases for stratification in consumer surveys are commonly demographic, e.g.,
age, sex, income and so on. Often compound stratification is used-for example, age groups within
sex. Next, sample size (called quotas) are established for each stratum. As with stratified random
sampling, the sampling within strata may be proportional or disproportional. Field-workers are then
instructed to conduct interviews with the designated quotas, with the identification of individual
respondents being left to the field-workers. '
(4) Panel Sampling: Here the initial samples are drawn on random basis and information
from these is collected on regular basis. It is a semi-permanent sample wilere members may be
included repetitively for successive studies. Here there is a facility to select and quickly contact such
well balance samples and to have relatively high response rate even by mail.
(5) Snowball Sampling: It is a special non-probability method used when the desired
sample characteristic is rare. It may be extremely difficult or cost prohibitiye to locate respondents in
these situations. Snowball sampling relies on referrals from initial subjects to generate additional
subjects. While this technique can dramatically lower search costs, it comes at the expense of
introducing bias because the technique itself reduces the likelihood that the sample will represent a
good cross section from the population.
Sample Frame
(2) Sample Frame: The frame is constructed either by the researcher for the purpose of his
study or may consist of some existing list of the population. After the population to be studied has
been specified, the next step is to develop a frame of this population. A list containing all sampling
units of a population is known as sampling frame. The frame is constructed either by the researcher
for the purpose of his study or may consist of some existing list of the population. A frame does not
always have to be a list of names; it can also involve a definite location, a boundary, an address, or
a set of rules by which a sampling unit can be delineated.
A frame in some sense is a set of bo ndaries circumscribing the universe. It may be in the
form of lists, indices, maps, directories, population records, electoral rolls, city tax rolls, students
enrolled in a university etc. In marketing studies the frame is essential. A list of every element of the
population appearing once and only once would constitute a sample frame. A good sampling frame
should be acr.urate, free from duplication and conveniently available. A sample frame is essential
for marketing research and better performance of sampling procedure.
A sampling frame is a representation of the elements of the target population. 1t consists of
a list or set of directions for identifying the target population. For example, the telephone book, an
association directory listing the tirms in an industry, a mailing list purchased from a commercial
organization, a city directory, or a map.
(3) Specifying the Sampling Units: The decision on sampling unit often depends on the
sampling frame. The sampling unit is the basic unit containing the elements of the population to be
sampled, e.g. city blocks, households, a business organization etc. The decision on sampling unit
often depends on the sampling frame. The selection of the sampling unit partially depends on the
overall design of the project also. The units which serve as the basis of initial sampling are known
as primary sampling units. It can be composed of one or more units of the population depending on
the objectives of the inquiry."
For example, suppose that Revlon wanted to assess consumer response to a new line of
lipsticks and wanted to sample females over 18 years of age. It may be possible to sample females
over 18 directly; in which case a sampling unit would be the same as an element. Alternatively, the
sampling unit might be households. In the latter case, households would be sampled and all
females over 18 in each selected household would be interviewed. Here, the sampling unit and the
population element are / different. Extent refers to the geographical boundaries and the time factor
is the time period under consideration.
(4) Selection of Sample Design: It is the procedure of selecting units in the sampJe. There
are two basic metj10ds of sampling namely, probability and non-probability methods which can be
further divided into some specific methods of selection. It is the procedure of selecting units in the
sample. There are two basic methods of sampling namely, probability and nonprobability methods
which can be further divided into some specific methods of selection. A probability sample is one,
where the selected units have some specific chance of being included in the sample. In a non-
probability sample some arbitrary method of selection not depending on chance is adopted. This
method mainly depends on the purpose of the inquiry, as well as on the attitude or convenience of
the investigators.
The selection of the sample design really involves two decisions:
(i) To use probabilitv of selection, and
(ii) Specific sample-deSign to use in collecting the data.
The researcher's choice will be affected by the following considerations:
i) If sampling error is to be evaluated, then probability sampling must be used.
ii) To ensure randomness in the selection of units, probability sample should be used.
iii) In the absence of proper sample frame, non-probability sampling should be used.
iv) If time and money considerations are vital, then non-probability sampling should be used.
Once the decision about probability and non-probability method of selection has been
made, one should select the sample design that will best accomplish the objectives of the
investigation. Regardless of the design finally chosen, the researcher may have to defend this
design, when the study results are ultimately presented.
(5) Determinatino of Sample Size: The size of the sample has direct relationship with
degree of accuracy desired in the investigatin. The size of the sample has direct relationship with
degree of accuracy desired in the investigatin. It also depends upon the nature of th epopulatino as
(43)
well as the method of selectin. In marketing research investigations the ideal sample size depends
upon the type of the series and the size of th epupulation. It is a common practice that larger ithe
size of t hepupulatino, more units should be drawn in the sample and more t hdegeee of
heterogeneity, larger should be sample size for it to be representative
(6) Select the Sample: Select the sample means execute actual sapling process. It is the
actual selection of the sample elements. This requires a substantial amoun e and fieid work
articularly when personal interviews are involved.
Execution of the sampling process requires a d'!tailed specification of how the sampling
design decisions with respect to the population, sampling frame, sampling unit, sampling technique~
and sample size are to be implemented. If households are the sampl'ing unit, an operational
definition of a household is needed. Procedures should be specified for vacant housing units and for
callbacks in case no one is at home. Detailed information must be provided for all sampling design
decisions.
(3) Practicality: This implies that the sample design can be followed properly in the survey.
It is necessary that complete, correct, practical and clear instructions should be given to the
interviewer so that no mistakes are made in the selection of sampling units and the final selection in
the field is not different from the original sample design. Practicality also refers to simplicity of the
design, i.e. it should be capable of being understood and followed in actual operation of the field
work.
(4) Economy: Finally, economy implies that the objectives of the survey should be achieved
with minimum cost and effort. Survey objectives are generally spelt out in terms of precision, i.e. the
inverse of the variance of survey estimates. For a given degree of precision, the sample design
(44)
should give the minimum cost. Alternatively, for a given per unit cost, the sample design should
achieve maximum precision (minimum variance).
(5) Independence: Each element of universe is independent. Each element has equal
chance of selection.
(6) Homogeneity: There should not be any change in that universe where survey is
conducted i.e. quality and nature of units should remain same.
(7) Adequacy: Sample should be adequate. Too much low unit will not be desirable nor will
too many high sampling units need more time and money for analysis.
Ratio
Interval
Ordinal
Normal
(1) Nominal Scale: Nominal scale represents the most elementary level of measurement. A
nominal scale assigns a value to an object for identification or classification purposes. The value
can be, but does not have to be, a number because no quantities are being represented. In this
sense, a nominal scale is truly a qualitative scale. Nominal scales are extremely useful even though
they can be considered elementary. Marketing researchers use nominal scales quite often.
Nominal scaling is arbitrary in the sense that each label can be assigned to any of the
categories without intro-ducing error. The researcher can assign the letter C to any of the three
options without damaging scale validity.
For example, the population of a town may be classified according to sex into "males" and
"females" or according t:J relie;ion into "Hindus”, "Muslims", "Sikhs" 'ind "Christians".
In marketing research nominal scales are needed to measure brands, store types, sales
territories, geographical locations, heavy versus light users, workingversus non-working women and
brand awareness versus non-awareness.
For example, consider following table which shows nominal scale:
(46)
(3) Interval Scale: The interval scale Las all characteristics of the ordinal scale and in
addition, the units of measure or intervals between successive positions are equal.
For example, a researcher scaled brands A, B and C on an interval scale regarding the
buyers' degree of liking of the brands. Brand A receives the 1ighest liking score of 6, B receives 3
and C receives 2. First the liking for brand A is more favorable than that for brand B S·xond the
degree of liking between A and B is three time~ greater thaa the liking between B and C
(47)
The statistical tools used to analyze the interval data are range, mean, sandard deviation
and the like. Interval scales are frequently used in commercial marketing research studies,
especially in collecting attitudinal and overall brand rating information.
Example 3: How do you rate your present refrigerator for the following qualities?
Company Name Less Known 1 2 3 4 5 Well Known
Functions Few 1 2 3 4 5 Many
Price Low 1 2 3 4 5 High
Design Poor 1 2 3 4 5 Good
Overall Satisfaction Very Dis-Satisfied 1 2 3 4 5 Very Satisfied
Such a scale permits the researcher to say that position 5 on the scale is above position 4
and also the distance from 5 to 4 is same as distance from 4 to 3. Such a scale however does not
permit conclusion that position 4 is twice as strong as position 2 because no zero position has been
established. The data obtained from the Interval Scale can be used to calculate the Mean scores of
each attributes over all respondents The Standard Deviation (a measure of dispersion) can also be
calculated.
(4) Ratio Scale: Ratio scales represent the highest form of measurement. They have all the
properties of interval scales with the additional attribute of representing absolute quantities. Interval
scales represent only relative meaning, whereas ratio scales represent absolute meaning. In other
words, ratio .scales provide iconic measurement. Zero, therefore, has meaning in that it represents
an absence of some concept.
An absolute zero is a defining characteristic in determining between ratio and interval scales.
For example, money is a way to measure economic value.
The ratio scales are very common in physical scenarios. Quantified responses forming a
ratio scale analytically are the most versatile. Ratio scale possesses all the characteristics of an
internal scale, and the ratios of the numbers on these scales have meaningful interpretations. Data
on certain demographic or descriptive attributes, if they are obtained through open-ended questions,
will have ratio-scale properties. Consider the following questions:
i) What is your annual income before taxes? ___ Rs.
ii) How far is the Tl:eatre from your home? ___ Miles.
Answers to these questions have a natural, unambiguous starting point, namely zero. Since
starting point is not chosen arbitrarily, computing and interpreting ratio makes sense. For example a
respondent with an annual income of $ 40,000 earns twice as much as qne with an annual income
of $ 20,000.
Table : Summary of Scaling Techniques
Criteria Nominal Ordinal Interval Ratio
Properties of Naming Naming and Naming, ranking Naming, ranking,
measurement ranking and equal equal intervals
intervals and zero point
Nature of Categorical Ranking Scoring Scoring
measurement
Examples Gender: Male and Caste: High, IQ: of A is 25% IQ: of A to B is
Female Intermediate higher than B 1:1.5
Residence : Rural Income: Upper, Age: A is twice Age: ratio of B to
and urban Middle and low as old as B A age is 1:2
Nature of Discrete Discrete or Continuous Continuous
underlying continuous
construct
Mathematical None None Additiona and Addition,
functions Subtraction Subtraction,
division, multiples
Scaling Techniques
Stapel‟s Scale
Multi Dimensional Scaling
Rating Scales
One uses rating scales to judge properties of objects without reference to ot similar objects.
These ratings may be in such forms as "like-dislike", "approve indifferent disapprove", or other
classifications using even more categories. There is little conclusive support for choosing a three-
point scale over scales with five or more points. ·
(1) Likert Scale: A Likert scale is a psychometric scale commonly used in questionnaires,
and is the most widely used scale in survey research. When responding to a Likert questionnaire
item, respondents specifY their level of agreement to a statement. The scale is named after its
inventor, psychologist Rensis Likert. These scales are sometimes referred to as summated scales.
It requires a respondent to indicate a degree of agreement or disagreement with each of a series of
statements related to the attitude object.
A Likert item is simply a statement which the respondent is asked to evaluate according to
any kind of st.Jjective or objective criteria; generally the level of agreement or disagreement is
measured. Often five ordered response levels are used, although many psychometricia.Js advocate
using seven or nine levels; a recent empirical study found that a five or sevenpoint scale may
produce slightly higher mean scores relative to the highest possible attainable score, compared to
those produced from a ten-point scale and this difference was statistically significant. In terms of the
other data characteristics, there was very little difference among the scale formats in terms of
variation about the mean, skewness or kurtosis.
The format of a typical tive-level Likert item is:
i) Strongly disagree,
ii) Disagree,
iii) Neither agree nor disagree,
iv) Agree,
v) Strongly agree.
(2) Semantic Differential Scale: It is a special type of graphic scale, which is increasingly
being used, in marketing research. It establishes a cormection between the brand and company
image studies and also permits the development of descriptive profiles that facilitates comparison of
competitive items. The unique characteristics of semantic differential is the use of bipolar scales to
rate any product, company or concept of interest. Respondents are given a group of these scales
and asked to check on each one point that indicates their opinion of the subject in question. Each
seale consist of two opposing adjectives such as good/ bad, clean/ dirty, most pqpular/ least
popular, etc. which are separated by a continuum divided into seven segments. Respondents are
asked to check the segment that represents the degree of the characteristics involved that most
closely coincided with their opinion of the product or item being rated.
(3) Stapel's Scale: The Stapel scale was originally developed in the 1950s to measure
simultaneously the direction and intensity of an attitude. Modern versions of the scale, with a single
adjective, are used as a substitute for the semantic differential when it is difficult to create pairs of
bipolar adjectives. The modified Stapel scale places a single adjective in the center of an even
(49)
number of numerical values (ranging, perhaps, from +3 to -3).The scale measures how close to or
distant from the adjective given stimulus is perceived to be.
The advantages and disadvantages of the Stapel scale are very similar to those of the
semantic differential. However, the Stapel scale is markedly easier to administer, especially over the
telephone. Because the Stapel scale does not require bipolar adjectives, it is easier to construct
than the semantic differential. Research comparing the semantic differential with the Stapel scale
indicates that results from the two techniques are largely the same .
(4) Multi Dimensional Scaling: It consists of a group of analytical techniques which are
used to study consumer attitudes related to perceptions and preferences. It is a computer based
technique. The respondents are asked to place the various brands into different groups like similar,
very similar, not similar, and so on. A goodness of fit is traded off on a large number of attributes.
Then a lack of fit index is calculated by computer program. The purpose is to find a reasonably
small number of dimensions which will eliminate most of the stress. After the configuration for the
consumer's preference has been developed, the next step is to determine the preference with
regards to the product under study.
It is a computer based technique. The· respondents are asked to place the various brands
.into different groups like similar, very similar, not similar, and so on. A goodness of fit is traded off
on a large number of attributes. Then a lack of fit index is calculated by computer program. The
purpose is to find a reasonably small number of dimensions which will eliminate most of the stress.
After the configuration for the consumer's preference has been developed, the next step is to
determine the preference with regards to the product under study. These techniques attempt to
identify the product attributes that are important to consumers and to measure their relative
importance.
Ranking Scales
In ranking scales, the subject directly compares two or more objects and makes choices
among them. Frequently, the respondent is asked to select one as the “best" or the "most
preferred." When there are only two choices, this approach is satisfactory, but it often results in
"ties" when more than two choices are found. For example, respondents are asked to select the
most preferred among three or more models of a product. Assume that 40 percent choose model A,
30 percent choose model B. and 30 percent choose model C. "Which is, the preferred model?" The
analyst would be taking a risk to suggest that A is most referred. Perhaps that interpretation is
correct, but 60 percent of the respondents chose some model other than A. Perhaps all B and C
voters would place A kst, preferring either B or C to it. This ambiguity can be avoided by discussing
the techniques described in this section.
There are two approaches of ranking scales
1) Method of Paired Comparison
2) Method of Rank Order
Processing Operation
Processing of data includes:
1) Editing,
2) Coding,
3) Classification, and
4) Tabulation
(51)
Data Processing
Data Distribution
Tabulation
Data Analysis
Data Interpretation
Diagrammatic Presentation
Figure : Stages in Data Analysis
Editing of Data
The raw data is likely to contain a number of errors during the process of recording the
information in surveys. By means of editing one tries to eliminate the errors or remove the points of
confusion, if any. Alternately, recorded raw data is normally less than perfect and the first phase
through which this data must pass is editing.
For proper analysis and interpretation, it is necessary that the collected data are present,
readable and accurate in the desired form, i.e., data collected has no missing values, all entries are
readable or all information is accurate.
This introduces errors in collected information, which are to be rectified before further
analysis. The errors or points of confusion in ·raw Jata are eliminated through editing.
Editing comprises inspecting, correcting and modifYing the raw data to ensure that
information is available correctly, adequately and relevantly.
Essentials of Editing
(1) Completeness: The editor must find whether there is an answer to every question. If the
interviewer has forgotten to ask a question or to record the answer; it may be possible to deduce
from other data on the questionnaire and fill up the gap. The interviewer may also be able to fill in
the gap from his memory. If the information is vital, it can be collected by a postal enquiry.
(2) Accuracy: The editor must try to check whether the answers are accurate. In the first
place, inconsistencies should be looked for. Every effort should be made to resolve clear
inconsistencies. If this is not possible, then the inconsistent entries should be omitted.
(3) Uniformity: In editing data sets, another keen look out should be for any lack of
uniformity in interpretation of questions and instructions by the data recorders. For Example, the
responses towards a specific feeling could have been queried from a positive as well as a negative
angle. While interpreting the answers, care should be taken as to record the answer as a "positive
question" response or as "negative question" response. In all, uniformity checks for consistency in
coding throughout the questionnaire/interview schedu!e response/data set.
Stages of Editing
The editing may be done in two stages:
(1) Field Editing: The field editing is a preliminary editing done to detect the glaring
omissions and inaccuracies in the data. It is useful for controlling the field force and removing
misunderstanding.
The field editing is done immediately after collection of data because the interviewers then
have a fresh memory about the lapses and wrong statements of answers. The preliminary editing
(52)
should be done by a field supervisor. The editing is done to find out completeness, legibility,
comprehensibility, consistency and uniformity. The completeness-check involves scrutinizing the
data form to ensure that no questions or sections or pages are omitted.
The questions may be left out on account of oversight or not knowing the answers. Such
questions are corrected by observing another questionnaire. The incomprehensible questions
should be calcified at this stage. The responses should be recorded in uniform units. If required, the
interviewers should recontact the respondent and verify the puzzled and inconsistent records.
(2) Office Editing: The office editing is done after the field editing. This implies a complete
and thorough scrutiny of the questionnaire. There should be expert editors in the office to evaluate
and examine the completed returns of the respondents. There may be a division of labor for editing
purposes, and each editor may be assigned a particular portion of the questionnaire. The office
editors decide what to do with the data rather than follow up the procedures of interviewed
responses. They are more concerned with incorrect and incomplete answers.
The incorrect answers may be detected easily when two or more questions are inconsistent.
The handling of such answer depends upon the nature of the inconsistencies. The incorrect
answers may also be verified by observation. When the answers are given in an ambiguous
manner, serious efforts are made to rectify and complete them by consulting another questionnaire.
The earlier answers may form a basis for the correction of the incorrect answers.
Many incomplete answers are known from the responses of "don't know." It is a very difficult
answer because it reflects a variety of answers. It may represent a lack of knowledge or of memory.
The respondents may leave the questions blank intentionally or unintentionally. Such "don't know"
answers may be dealt with by distributing them proportionately among other categories, or
estimating the answers from other data, or showing them as a separate category.
Types of Editing
(1) Manual Editing: Here the editor scans the whole data and amends it in accordance with
the given instructions. Here the drafted instructions are of great significance and helps the editor to
perform his work systematically with little scope of using his own judgment and intuition. The precise
forms in 'which editing instructions are written vary from one organization to the other.
(2) Mechanical Editing: When data are transferred on punch cards then counter sorter can
be used for editing the raw data. lt provides exhaustive and thorough logical checking. Cards which
contain some particular type of error/errors are sorted out. The process i.; extremely quick and
effective. Due to this it is found to be cheap and free from error.
(3) Computer Editing: It is similar to mechanical editing with the difference that several
hundred editing instructions can be executed at one time on a computer. Thus here editing is faster
and accurate.
(B) CODING
Introduction:
Coding is the procedure of classifYing the answers to a question into meaningful categories.
The symbols used to indicate these categories are called codes. Coding refers to the process of
assigning numerals or other symbols to answers so that responses can be put into a limited number
of categories or classes. Such classes should be appropriate to the research problem under
consideration. They must also posses the characteristic of exhaustiveness (i.e., there must be a
class for every data item) and also that of mutual exclusivity which means that a specific answer can
be placed in one and only one cell in a given category set. Another rule to be observed is that of uni-
dimensionality by which is meant that every class is defined in terms of only one concept.
Coding is necessary to carry out the subsequent operations of tabulating and analyzing data.
If coding is not done, it will not be possible to reduce a large number of heterogeneous responses
into meaningful categories with the result that the analysis of data Would be weak and ineffective,
and without proper focus.
Essentials of Coding
(1) Appropriate to the Research Problem: The number of categories should be
reasonable. Generally 3 to 5 categories are considered reasonable. For example, categorization of
respondents on the basis of age, say, under 20 years, 20 to 29 years, 30 to 39 years and above 40
years may be relevant to the study.
(2) Exhaustive: The rule on exhaustiveness states that there must be a category for every
item.
For example, there is a question in the questionnaire. 'What is your favorite form of
entertainment?'
The alternatives will be:
i) Movies,
ii) Skipping,
iii) Boating,
iv) Watching TV,
v) Other (describe).
For each question a separate number shall be assigned. For question 'Other' number 5
should be allotted. If majority has stated 'horse riding' allot the number 5 for that. If some say
reading novels allot the number '6' to them.
(3) Mutually Exclusive: In an occupation survey the classification of respondents m'iy be
professional, managerial, sales, clerical, craftsman, operatives and unemployed. Some respondents
will think of themselves as being in more than one of these groups. A man who views selling as
profession may spend part of his time supervising others. He feels that he fits under three of these
categories say professional, managerial and sales. One of the functions of operational definition is
to provide categories.
(4) Single Dimension: Every class in the category set is defined in terms of one concept.
Suppose a respondent is both a salesman and unemployed. The 'salesman' label expresses the
concept of occupational type while the response unemployed is another dimension.
Coding can be greatly simplified if precoded questionnaires are used. Enormous time is
saved. When the possible answers anticipated, allot extra numbers when new categories emerge.
Coding is a laborious task. The problem can be kept to the minimum if preparations for
coding are made prior to administering the questionnaire/interview schedule.
(5) Code Sheets: Code sheets instruct the coders how to handle each question. When
codes are defined, a listing of all types of responses being assigned to each code should qe made
on the code sheet. The code sheet consists of the following elements:
i) Heading: The heading identifies the study.
ii) Column Identification: Each applicable column is to be listed on the left-hand side of the
page.
iii) Coding Instructions: Limitations/restrictions and required multiple codes are to be
stated next to each code where applicable.
iv) Special Instructions: Instructions for the use of ' borrowed columns'
(C) CLASSIFICATION:
Introduction:
Most research studies result in a large volume of raw data which must be reduced into
homogeneous · groups if we are to get meaningful relationships.
This fact necessitates classification of data which happens to be the process of arranging
data in groups or classes on the basis of common characteristic. Data having a common
characteristic are placed in one class and in this way the entire data get divided into a number of
groups or classes.
(54)
Types of Classification
Classification can be one of the following two types, depending upon the nature of the
phenomenon involved:
(1) Classification According to Attributes: Data are classified on the basis of common
characteristics which can either be descriptive·(such as literacy, sex, Honesty, etc.) or numerical
(such as weight, height, income, etc.) Descriptive characteristics refer to qualitative phenomenon
which cannot be measured quantitatively; only their preser.ce or absence in an individual item can
be noticed. Data obtained this way on the basis of certain attributes are known as statistics of
attributes and their classification is said to be classification according to attributes.
Such classification can be simple classification or manifold classification. In simple
classification we consider only one attribute and divide the universe into two classes-one classes
consisting of items possessing the given attribute and the other class consisting of items which do
not possess the given attribute. In manifold classification we consider two or more attributes
simultaneously, and divide the data into a number of classes (total number of classes of final order
is given by 2" , where n = number of attributes considered).
(2) Classification According to Class-intervals: Unlike descriptive characteristics, the
numerical characteristics refer to quantitative phenomenon, which can be measured through some
statistical units. Data relating to income, production, age, weight, etc. come under this category.
Such data are known as statistics of variables and are classified on the basis of class intervals. For
example, persons whose incomes, say, are within Rs. 201 to Rs. 400 can from one group; those
whose incomes are within Rs. 401 to Rs. 600 can form another group and so on.
Objectives of Classification
(1) To condense the available data in a compact manner for quick understanding and also for
comparison.
(2) To make the data ready for further processing and analysis.
(3) To bring out important facts and also to facilitate comparison with the data of similar nature.
(4) To make data ready for tabulation.
(5) To facilitate easy and quick interpretation of data.
(D) TABULATION:
Tabulation is the primary function of Data Analysis. The data is validated and analyzeJ to
generate tables in a client-specified format that helps the researcher to interpret the results of the
survey and present it to his/her client.
According to Tuttle, "The logical listing of related quantitative data in vertical columns and
horizontal rows of numbers with sufficient explanatory and qualifying words, phrases and
statements in the form of titles, headings and explanatory notes to make clear the full meaning,
context and the origin of the data".
According to Secrist, "Tables are a means of recording in permanent form the analysis that
is made through classification and by placing in juxtaposition things that are similar and should be
compared".
According to L.R. Connor, "Tabulation involves the orderly and systematic presentation of
numerical data in a form designed to elucidate the problem under consideration".
According to Blair, "Tabulation in its broadest sense is an orderly arrangement of data in
columns and rows".
Thus, tabulation is one of the most important and ingenious devices of presenting the data in
a condef!sed and readily comprehensible form. It attempts to furnish the maximum information in
the minimum possible space, without sacrificing the quality and usefulness of the data. However, it
is an intermediate process between the collection of the data and the statistical analysis. In fact,
tabulation is the final stage in collection and compilation of the data and forms the gateway :o further
statistical a'nalysis and interpretation.
Objectives of Tabulation
(1) To Clarify the Object of Investigation: According to Prof. A. L. Bowley, "The function of
tabulation in the general scheme of statistical investigation is to arrange in easily accessible form
the answer with which the investigation is concerned". The presentation of data in tables makes the
problem under study simple and clear and answers many problems that are found there.
(2) To Clarify the Characteristics of Data: A table presents facts clearly and concisely,
eliminating the need for wordy explanation. It brings out the chief characteristics of data.
(3) To Present Facts in the Minimum of Space: A table presents facts in minimum of
space and communicates information in a far better way than textual material.
(4) To Facilitate Statistical Process: It simplifies reference to data and facilitates
comparative analysis and interpretation of the facts.
Types of Tables
Tables may broadly be classified into two categories:
(1) Simple and Complex Tables
(2) General Purpose and Special Purpose (or Summary) Tables
Types of Tables
(1) Simple and Complex Tables: The distinction between simple ar complex table is based
upon the number of characteristics studied.
In a simple table only one characteristic is shown. Hence, this type of tab is known as one-
way table. In a complex table, on the other hand, two or more characteristics are shown. Such
tables are more popular in practice because they enable full information to be incorporated and
facilitate a proper consideration of all related facts. When two characteristics are shown such a table
is known as two-way table or double tabulation. When three characteristics are shown in a table,
this type of tabulation is known as treble tabulation. When four or more characteristics are
simultaneously shown it is a case of manifold tabulation.
i) Simple Table or One-way Table: In this type of table only one characteristic is shown.
This is the simple type of table.
ii) Two-way Table: Such a table shows two characteristics and is formed when either the
stub or the caption is divided into two coordinate parts.
iii) Higher Order Table: When three or more characteristics are represented in the same
table, such a table is called higher order table. The need for such a table arises when we are
interested in presenting a number of characteristics simultaneously. While constructing such a
table it is necessary to first establish an order of precedence among the attributes or
characteristics sought to be classified having regard to their relative importance.
In should be remembered that as the number of characteristics represented increases, the
table becomes more and more confusing and as such normally not more thrut four characteristics
should be represented in the same table. Where more than four characteristics are to be
represented we can have more than one table depicting relationship between the attributes. In the
following two illustrations, three and four characteristics are represented respectively.
General and Special Purpose Tables: General purpose tables also known , s reference
tables or repository tables provide information for general use reference. They usually contain
detailed information and are not onstructed for specific discussion. In other words, these serve as
repository of information and are arranged for easy reference. Tables published by the
governmental agencies are mostly of this kind, such as the tables contained in the Statistical
Abstract of the Indian Union, detailed tables contained in the census reports, etc. Such tables tell
facts which are not for particular discussion. When such tables tell facts which are not for particular
discussion. When such tables are used by a researcher, they arc usually placed in the appendix of
the reports for easy reference .
Advantages of Tabulation
(1) It Simplifies Facts: Tabulation is helpful in presenting mass of complex data clearly, so
that their features can easily be understood.
(2) Economy: It occupies less space than textual reports, hence saving of paper and time.
Required figures can be located more quickly.
(3) Helpful in Comparison: Tabulation makes comparison easy. Comparable figures are
placed in juxtaposed columns; hence a comparative study can be made.
(4) Facilitates Computation: it helps in computation of different statistical measures. For
calculation average, dispersion, correlation, etc. data must be presented in tables.
(59)
(5) Helps Classification: While classification is a theoretical process of data analysis,
tabulation is an applied process. Tabulation is helpful in classification also. After classifYing data,
the characteristics of different classes are not clear till they are placed in a suitable table.
(6) Helps in Reference: tabulated data are good for reference purposes.
(7) Helps in Interpretation and Presentation: It is convenient to interpret tabulated data:-
Tabulated data make it easy to present the facts in a graphical and diagrammatic form.
Disadyantages of Tabulation
(1) No Description: A table contains only figures and not their description. The tables can
be said complementary to textual reports.
(2) Difficult for Layman: It requires a specialized knowledge to understand a table. A
layman cannot derive any conclusion form a table.
(3) Lack of Emphasis: A table does not lay emphasis on any section of particular
importance.
Analysis Procedure:
In order to make effect use of data following tasks are performed by the investigator.
(1) An investigator first of all gathers together all the information collected from the
respondents.
(2) The investigator than arranges the items of information into various groups in a
preliminary way.
(3) To take account of the categories or grouping suggested by the respondents.
(4) The set of categories based on information will be formed.
Then so collected information should he reviewed to assess with reference to objectives of
the study. Then data to he analysed with selected tools. The-result emerging for this analyses than
to be related to the objective of the study.
In qualitative investigation is not only to know the various statements but it is concert with
various interpretations the statements in each category. Report in this investigation indicate how
hypothesis changed during the course of investigation.
Types of Analysis
(1) Qualitative analysis.
(2) Quantitative analysis.
(1) Qualitative analysis. It is less influenced by theoretical assumptions. The limitation of
this type of analysis is that the findings tend to be unreliable. The information categories and
interpreted often differ considerable from one investigator to another one.
In this system researeherto go throl;lgh ''researeh cycle" to increase reliability. Repeating the
researeh cycle is of value in some ways, but it dose not ensure that the findings will have high
reliability. Qualitative analyses are carried out in several different-kinds of study like interview, case
studies and observational studies
(2) Quantitative Analysis. The numerical data collected in study through descriptive
statistics analysis can be conducted through measure of central tendency. So the descriptive
analysis is largely the study of distribution of one variable.
(a) DistriptiveAnalysis. This analysis of one variable.is called one dimensional analysis.
This analysis measures condition at particular time.
(60)
(b) Bivariate Analysis. The analysis in respect of two variables is called bivcriiate
analysis. In this analysis collected data in placed into tabular form, so that the meaning of the data
can be derive. In this method simple dimensional data is developed and put in to two or more
categories.
(c) Casual Analysis. It is concerned with study of one variable affecting another one. The
dependent variable get affected with external factor. There are various ways to find out the
existence on non- existence of coordination's. There analysis is done with the help of statistical
tools. CausaI analysis is important in experimental researches.
(d) Multivariate Analysis. With an advancement of computer lications there is fast
development of multivariate analysis, in which szatistical method simultaneously analyse more
than two variable on sample observations. Multiple regression, discriminate analysis und analysis
variance are commonly used for this type of analysis of hypotheses. One the basis of inferential
analysis ·the task of interpretation is performed by estimating the population values.
(e) Inferential Analysis. In order to decide the validity of data to indicate conclusion this
analysis is concerned with tests for significance of hypotheses. One the basis of inferential
analysis the task of interpretation is performed by estimating the pppulation val\leS.
It is observed that executives are never interested in the methodology adopted by the
researcher in the investigation. They are interested only in the final results. From their viewpoint, the
research report is the written/oral presentation which the executive see/hear of a project carried out
by the researcher but initiated by the decision maker (executive). The research report conveys the
information desired by the decision maker in an understandable form.
According to Lancaster, "A report is a smtement of collected and considered facts, so
drawn-up as to give clear and concise information to persons who are not already in rossession of
the full facts of the subject matter of the report".
A research report is a written document or oral presentation based on a written document
that communicates the purpose, scope, objective(s), hypotheses, methodology, findings, limitations
and finally, recommendations of a research project to others. ·
The researcher has to convince the client (and others who may read the report) that the
research findings can be acted on for their own benefit.
(2) Popular Report: The popular report is one which gives emphasis on simplicity and
attractiveness. The simplification should be sought through clear writing, minimization of technical,
particularly mathematical, details and liberal use of charts and diagrams. Attractive layout along with
large print, many subheadings, even an occasional cartoon now and then is another characteristic
(62)
feature of the popular report. Besides, in such a report emphasis is givw on practical aspects and
policy implications.
We give below a general outline of a popular report:
i) Findings and their Implications: Emphasis in the report is given on the findings of
most practical interest and on the implications of these findings.
ii) Recommendations for Follow-up: Recommendations for action on the basis of the
findings of the study is made in this section of the report.
iii) Objective of the Study: A general review of how the problem arises is presented
along with the specific objectives of the project under study.
iv) Methods Employed: A brief and non- technical description of the methods and
techniques used, including a short review of the data on which the study is based, is given in this
part of the report.
v) Results: This section constitutes the main body of the report where in the results of
the study are presented in clear and non- technical terms with liberal use of all sorts of
illustrations such as charts, diagrams and the like ones.
vi) Technical Appendices: More detailed information on methods used, forms, etc. is
presented in the form of appendices. But the appendices are often not detailed if the report is
entirely meant for general public.
There can be several variations of the form in which a popular report can be prepared. The
only important thing about such a report is that it gives emphasis on simplicity and policy
implications from the operational point of view, avoiding the technical details of all sorts to the extent
possible.
(3) Interim Report: When there is a long time lag oetween data collection and the
presentation of the results in the case of a sponsored project, the study may lose its significance
and usefulness and the sponsor may also lose interest in it. One of the most effective ways to avoid
such eventualities is to present an interim report.
This short repvrt may contain either the first results of the analysis or the final outcome of the
analysis of some aspect/s completely analyzed. Whatever may be the coverage of the interim
report, it fulfills certain functions. It facilitates the sponsoring agency to take action without waiting
for the full report. It helps to keep alive the agency's interest in the study and prevent
misunderstandings about the delay. In addition, it serves to spread over a longer period the time
consuming process of discussion of research findings and their implications. The report also
enables the researcher to find the appropriate style of reporting.
The interim report contains a nmration of what has been done so far and what was its
outcome. It presents a summary of the findings of that part of analysis which has been completed.
(4) Summary Report: A summary report is generally prepared for the consumption of the
lay audience, viz., the general public. The preparation of this type of report is desirable for any study
whose findings are of general interest. It is written in non-technical, simple language with a liberal
use of pictorial charts. It just contains a brief reference to the objective of the study, its major
findings and their implications. It is a short report of two or three pages. Its size is so limited as to be
suitable for publication in daily newspapers.
(5) Algorithmic Research Report: There are problems, viz., production scheduling, JIT,
supply chain management, line balancing, layout design, portfolio management, etc., exist in reality.
The solution for each of the above problems can be obtained through algorithms. So, the
researchersshould come out with newer algorithms or improved algorithms for such problems. For a
combinatorial problem, the researcher should attempt to develop an efficient heuristic. The
algorithmic research report can be classified into the following categories:
i) Algorithmic research report for combinatorial problem.
ii) Exact algorithmic research r:!port for polynomial problem.
(2) Taking Notes: In the course of investigations, the writer keeps on taking notes of
anything that appears to be related to the subject. Then there is no time to analyze them and
determine how they will be of help in the final report. But as the writer keeps turning them in his
mind over and over again, a kind of pattern starts emerging and he begins to be clear about what is
relevant and what is not. It is a very general kind of patterns, but it gives the writer at least a starting
point.
Taking Notes
Making an Outline
(3) Analyzing the Data: Now is the time to analyze the collected data in the light of the
pattern that has evolved. A lot of data will have to be rejected while a need might be felt to collect
more data. The final pattern will emerge at this step. The writer should never hurry through this step,
since this is the most important stage in writing a report.
(4) Making an Outline: Once the final pattern of the report has taken shape in the writer's
mind he should prepare an outline to write the report In this outline the problem is stated, the facts
(65)
are recorded, they are briefly analyzed, and the logical conclusion is arrived. An Ol}tline is not
essential, but it has been found extremely helpful in writing a systematic report.
(5) Writing the Report: The last step is that of writing the report. It will need a constant
shuttling between the outline and the notes. First a rough draft of the report is prepared. Then it is
revised, pruned and polished. If the writer has some more time at his disposal, he will find it
advantageous to come back to his rough draft after, say, a couple of days. This short interval will
make his revision really meaningful. The writer should also be careful that the language of the report
is simple, unambiguous and free from and submit it.