Research

Research may be very broadly defined as systematic gathering of data and information and its

analysis for advancement of knowledge in any subject. Research attempts to find answer

intellectual and practical questions through application of systematic methods. Webster’s

Collegiate Dictionary defines research as "studious inquiry or examination; esp: investigation or

experimentation aimed at the discovery and interpretation of facts, revision of accepted theories

or laws in the light of new facts, or practical application of such new or revised theories or laws".

Some people consider research as a movement, a movement from the known to the unknown. It

is actually a voyage of discovery. We all possess the vital instinct of inquisitiveness for, when

the unknown confronts us, we wonder and our inquisitiveness makes us probe and attain full and

fuller understanding of the unknown. This inquisitiveness is the mother of all knowledge and the

method, which man employs for obtaining the knowledge of whatever the unknown, can be

termed as research. Research is an academic activity and as such the term should be used in a

technical sense. According to Clifford Woody research comprises defining and redefining

problems, formulating hypothesis or suggested solutions; collecting, organizing and evaluating

data; making deductions and reaching conclusions; and at last carefully testing the conclusions to

determine whether they fit the formulating hypothesis. D. Steiner and M. Stephenson in the

Encyclopedia of Social Sciences define research as “the manipulation of things, concepts or

symbols for the purpose of generalizing to extend, correct or verify knowledge, whether that

knowledge aids in construction of theory or in the practice of an art.” Research is, thus, an

original contribution to the existing stock of knowledge making for its advancement. It is the

pursuit of truth with the help of study, observation, comparison and experiment. In short, the
search for knowledge through objective and systematic method of finding solution to a problem

is research. The systematic approach concerning generalization and the formulation of a theory is

also research. As such the term ‘research’ refers to the systematic method consisting of

enunciating the problem, formulating a hypothesis, collecting the facts or data, analyzing the

facts and reaching certain conclusions either in the form of solutions(s) towards the concerned

problem or in certain generalizations for some theoretical formulation.

RESEARCH PROCESS

Identification and conceptualization of Problem

Finding an issue or formulating a research question is the first step. A well-defined research

problem will guide the researcher through all stages of the research process, from setting

objectives to choosing a technique. There are a number of approaches to get insight into a topic

and gain a better understanding of it. Such as:

 A preliminary survey

 Case studies

 Interviews with a small group of people

 Observational survey

Survey of literature

A thorough examination of the relevant studies is essential to the research process. It enables the

researcher to identify the precise aspects of the problem. Once a problem has been found, the

investigator or researcher needs to find out more about it.

This stage gives problem-zone background. It teaches the investigator about previous research,

how they were conducted, and its conclusions. The researcher can build consistency between his

work and others through a literature review. Such a review exposes the researcher to a more

significant body of knowledge and helps him follow the research process efficiently.

Selection of hypothesis

Formulating an original hypothesis is the next logical step after narrowing down the research

topic and defining it. A belief solves logical relationships between variables. In order to establish

a hypothesis, a researcher must have a certain amount of expertise in the field.

It is important for researchers to keep in mind while formulating a hypothesis that it must be

based on the research topic. Researchers are able to concentrate their efforts and stay committed

to their objectives when they develop theories to guide their work.

Collection of information

Data collection is important in obtaining the knowledge or information required to answer the

research issue. Every research collected data, either from the literature or the people being

studied. Data must be collected from the two categories of researchers. These sources may

provide primary data.

 Experiment

 Questionnaire

 Observation
  Interview

Secondary data categories are:

 Literature survey

 Official, unofficial reports

 An approach based on library resources

RESEARCH PROBLEMS

Research Problem/Topic and Research Questions Research question is the actually identified and

carefully framed questions, based on literature and identified existing problems which the

researcher wants to answer through systematic study/investigation. The research questions are

thus the specific questions asked by the researcher with the intention of finding answers to. A

research topic/problem means the identified problem that warrants conducting the study.

Although the two (research questions and topic/problem) are inter-twined and or related, they are

different. The research problem has to be clearly identified, formulated for a proper literature

review, relevant and robust data collection as well as the successful conduct of a study. The

research question has to also be worthy of investigation, otherwise it makes the research

insignificant. For research problem, it is key to conduct of every study and is a major

determinant of what method and or design should appropriately be used in the study –

qualitative, quantitative, and mixed, case study, etc. any research problem to be addressed must

take into consideration the relevance and significance of the problem to the audience, availability

of and accessibility to data, the contribution/change it will make from the existing conditions,
can the research be successfully concluded within stipulated/available time, energy, resources,

and other ethical issues.

Selection, identification, formulation of a research problem largely depends on doing an

appropriate review of literature. This review enables the researcher to measure up and understand

what have so far been done on the problem/topic, how such were done (methods/designs), who

did what, what strengths and weaknesses are there in what have been done and what gaps are

there that need to be filled by future studies. Overall, literature review provides the researcher

with a clear picture and feasibility or otherwise of the study to be conducted.

RESEARCH DESIGN

This is an outline, main plan and or a basic scheme of conducting a particular research using

some specific means of collection and measurement of primary, secondary or both data, and

procedural analysis of the same data in order to address/answer some research questions and or

test some hypotheses. In research, several designs are used and each is important, unique and

appropriate in its context of usage. There are numerous research designs which are seen as ‘a

general strategy for conducting a research study’, in use and they vary from one researcher,

scholar to another. Generally however, several research designs have been identified which

include: Experimental, Survey, Ethnographic, Correlational, Case Study, Action Research,

Qualitative, Ex post facto, Descriptive, Introspection, Grounded Theory, Narrative, Historical,

Evaluation, Causal-Comparative, Interactional analysis, Critical Theory, Constructivism, Content

analysis, Ethnomethodology, Feminist Research Design, Hermeneutics and Phenomenology.

Descriptive Research Design

In Descriptive Research Design, the scholar explains/describes the situation or case in depth in

their research materials. This type of research design is purely on a theoretical basis where the

individual collects data, analyses, prepares and then presents it in an understandable manner. It is

the most generalised form of research design. To explore one or more variables, a descriptive

design might employ a wide range of research approaches. Unlike in experimental research, the

researcher does not control or change any of the variables in a descriptive research design;

instead, he or she just observes and measures them. In other words, while qualitative research

may also be utilised for descriptive reasons, a descriptive method of research design is typically

regarded as a sort of quantitative research

Experimental Research Design

Experimental research is a type of research design in which the study is carried out utilising a

scientific approach and two sets of variables. The first set serves as a constant against which the

variations in the second set are measured. Experimentation is used in quantitative research

methodologies, for example. If you lack sufficient evidence to back your conclusions, you must

first establish the facts. Experimental research collects data to assist you in making better

judgments. Experimentation is used in any research undertaken in scientifically appropriate

settings. The effectiveness of experimental investigations is dependent on researchers verifying

that a variable change is due only to modification of the constant variable. The study should

identify a noticeable cause and effect. The traditional definition of experimental design is “the

strategies employed to collect data in experimental investigations.” There are three types of

experimental designs:
  Pre-experimental research design

 True experimental research design

 Quasi-experimental research design

Diagnostic Research Design

Diagnostic research design is a type of research design that tries to investigate the underlying

cause of a certain condition or phenomenon. It can assist you in learning more about the

elements that contribute to certain difficulties or challenges that your clients may be

experiencing. This design typically consists of three research stages, which are as follows:

 Inception of the issue

 Diagnosis of the issue

 Solution for the issue

Explanatory Research Design

Explanatory research is a method established to explore phenomena that have not before been

researched or adequately explained. Its primary goal is to notify us about where we may get a

modest bit of information. With this strategy, the researcher obtains a broad notion and uses

research as a tool to direct them more quickly to concerns that may be addressed in the future. Its

purpose is to discover the why and what of a subject under investigation. In short, it is a type of

research design that is responsible for finding the why of the events through the establishment of

cause-effect relationships.
 Variables, Measurement, and Scaling Technique

VARIABLES

In this universe, there are two types of entities— the first one varies over different situations and

the second one remains fixed. An entity which varies over different situations (e.g., time,

individuals, places) is known as the variable.

Discrete Variable

A discrete variable is one which takes only an integer value within a given range. For example,

the number of grains per panicle of a particular variety of paddy varies between 40 and 60 grains.

Dependent Variable

A dependent variable is a type of variable whose values are dependent on the values taken by the

other variables and their relationship. Generally in relational studies, a variable is influenced/

affected by other related variables. In a production function analysis, there exists a functional

relationship between the output and the factors of production.

Explanatory Variables

Independent variables are sometimes known as explanatory variables. Any variable which

explains the response/dependent/predicted variable is known as explanatory variable. In a simple

regression analysis, there are only one predictor and one response variable.

Stimulus Variable
The idea of stimulus and response variables is familiar in agriculture, socioeconomic, and

clinical studies. A stimulus is a type of treatment applied to the respondents to record their

response.

In clinical studies generally, the doses, concentrations, different chemicals, etc., form a

stimulus, whereas the response may be in the form of quantal response or quantitative response.

MEASUREMENT

Measurement is a process of assigning numbers to some characteristics or variables or events

according to scientific rules. It is the process observing and recording the observations that are

collected as part of a research effort. Measurement means the description of data in terms of

numbers – accuracy; objectivity and communication. The combined form of these three is the

actual measurement. Accuracy: The accuracy is as great as the care and the instruments of the

observer will permit. Objectivity: Objectivity means interpersonal agreement. Where many

persons reach agreement as to observations and conclusions, the descriptions of nature are more

likely to be free from biases of particular individuals. Communication: Communication is the

sharing of research between one person with another one.

Levels Of Measurement

Measurement is important in the process of data collection. Researcher need to measure Several

characteristic of variable such as human subject ,animal ,object and event. Level of measurement

refers to the relationship among the values that are assigned to the attributes for a variable. It is

important because - First, knowing the level of measurement helps you decide how to interpret

the data from that variable. When you know that a measure is nominal, then you know that the
numerical values are just short codes for the longer names.The most widely used classification of

measurement scales are

: (a) nominal scale; (b) ordinal scale; (c) interval scale; and (d) ratio scale. : (a) Nominal Scale-

The nominal scale (also called dummy coding) simply places people, events, perceptions, etc.

into categories based on some common trait. Some data are naturally suited to the nominal scale

such as males vs. females, white vs. black vs. blue, and American vs. Asian. The nominal scale

forms the basis for such analyses as Analysis of Variance (ANOVA) because those analyses

require that some category is compared to at least one other category. Coding of nominal scale

data can be accomplished using numbers, letters, labels, or any symbol that represents a category

into which an object can either belong or not belong. In research activities a Yes/No scale is

nominal.

(b) Ordinal Scale-An ordinal level of measurement uses symbols to classify observations into

categories that are not only mutually exclusive and exhaustive; in addition, the categories have

some explicit relationship among them.. Most of the commonly used questions which ask about

job satisfaction use the ordinal level of measurement. For example, asking whether one is very

satisfied, satisfied, neutral, dissatisfied, or very dissatisfied with one’s job is using an ordinal

scale of measurement.

(c) Interval Scale-In the case of interval scale, the intervals are adjusted in terms of some rule

that has been established as a basis for making the units equal. The units are equal only in so far

as one accepts the assumptions on which the rule is based. Interval scales can have an arbitrary
zero, but it is not possible to determine for them what may be called an absolute zero or the

unique origin.An interval level of measurement classifies observations into categories that are

not only mutually exclusive and exhaustive, and have some explicit relationship among them,

but the relationship between the categories is known and exact. This is the first quantitative

application of numbers. In the interval level, a common and constant unit of measurement has

been established between the categories. For example, the commonly used measures of

temperature are interval level scales. We know that a temperature of 75 degrees is one degree

warmer than a temperature of 74 degrees, just as a temperature of 42 degrees is one degree

warmer than a temperature of 41 degrees. Numbers may be assigned to the observations because

the relationship between the categories is assumed to be the same as the relationship between

numbers in the number system. For example, 74+1= 75 and 41+1= 42. The intervals between

categories are equal.

(d) Ratio Scale-The ratio level of measurement is the same as the interval level, with the

addition of a meaningful zero point. There is a meaningful and non-arbitrary zero point from

which the equal intervals between categories originate. For example, weight, area, speed, and

velocity are measured on a ratio level scale. In public policy and administration, budgets and the

number of program participants are measured on ratio scales. In many cases, interval and ratio

scales are treated alike in terms of the statistical tests that are applied. A ratio scale is the top

level of measurement and is not often available in social research.

SCALING OF MEASUREMENT
Scaling is the branch of measurement that involves the construction of an instrument that

associates qualitative constructs with quantitative metric .Stevens stated the simplest and most

straightforward definition of scaling… “Scaling is the assignment of objects to numbers

according to a rule”. In most scaling, the objects are text statements, usually statements of

attitude or belief. People often confuse the idea of a scale and a response scale

Thurstone or Equal-Appearing Interval Scaling

Psychologist Robert Thurstone was one of the first and most productive scaling theorists. He

actually invented three different methods for developing a unidimensional scale: the method of

equal-appearing intervals; the method of successive intervals; and the method of paired

comparisons. The three methods differed in how the scale values for items were constructed, but

in all three cases, the resulting scale was rated the same way by respondents Thurstone

developed the method of equal-appearing intervals. This technique for developing an attitude

scale compensates for the limitation of the Likert scale in that the strength of the individual items

is taken into account in computing the attitude score. It also can accommodate neutral

statements. Constructing the Scale Step –

1. Collect statements on the topic from people holding a wide range of attitudes, from extremely

favorable to extremely unfavorable. For this example, attitude toward the use of Yaba. Example

statements are - It has its place. Its use by an individual could be the beginning of a sad situation.

It is perfectly healthy; it should be legalized.

2. Step - 2. Duplicates and irrelevant statements are omitted. The rest are typed on 3/5 cards and

given to a group of people who will serve as judges.

3. Step - 3. Originally, judges were asked to sort the statements into eleven (11) stacks

representing the entire range of attitudes from extremely unfavourable (1) to extremely

favourable (11). The middle stack is for statements which are neither favourable nor

unfavourable (6). Only the end points (extremely favourable and extremely unfavourable) and

the midpoint are labelled. The assumption is the intervening stacks will represent equal steps

along the underlying attitude dimension. With a large number of judges, for example, using a

class or some other group to do the preliminary ratings, it is easier to create a paper-and-pencil

version.

SAMPLING DESIGN

Sampling is the process of systematic selection of elements from a population of interest so that

by studying the sample a researcher can fairly generalize the results about the population. Size of

population ranges from few individuals, for example, nuclear scientists in the country, to a very

large number, for example, school going children in the country. In the first example, it is fairly

less difficult for a researcher to identify the population for the study as the number of scientists

specialised in nuclear science in the country is less. Given the resources and time, sometimes

researcher might collect data from entire population. Operational, technical and material

constraints of research may demand collection of data from a set of elements drawn from

population instead. If data are collected from all the elements of population, it is referred to as

census data. If data are collected from few select respondents, it is referred to as sample data.
The important issue here is that how the researcher arrives at generalizations or explanations

about population based on the data collected from a sample.

Interval Sampling

This kind of sampling may be characterised by its systematic nature of sampling may be

characterised by its systematic nature of uncertainty. Interval sampling is random in the sense

that there is no basis for deciding the units to be chosen, yet it follows a systematic format of

choosing the uncertain units. The prerequisite of interval sampling is to have a list of all units in

the universe. The researcher randomly chooses one of the units that may or may not be the first

one in the list. Thereafter the units following after an interval of a certain ‘n’ number will be

chosen. That is to say, every ‘n th ’ unit will be chosen for the sample. This ‘n’ number may be

any number of the researcher’s choice. Interval sapling is not purely Probability Sampling, as all

the units do not stand an equal chance of being represented in the sample. Once the r searcher

decides the gap, then the units falling in between the intervals straightaway lose their chance of

being in the sample purely Probabilities. This is the reason Interval Sampling cannot be

considered sampling. However, it is not Non-Probability also, as there is no discretion of the

researcher to choose the units, except that the researcher chooses the number of interval after

which the units shall be selected.

Stratified Sampling

The universe to be studied by the researcher is not always homogeneous. Heterogeneous

population is often formed in such a way that it can be divided into different strata of
homogeneous population. Stratified Sampling is helpful for doing drawing samples out of such a

population. First the population is divided into different strata or layers and then samples are

drawn out of each stratum. The units from each sample from the various strata form the final

sample for carrying out the research. Strata can be purposely formed by the researcher, by

putting together the units having common characteristics. Thus each stratum will be a mini-

universe composed of homogeneous population. Any technique may be used to draw out sample

from the strata. Since the population in the strata is homogeneous, simple random sampling is

also a or Interval Sampling is the most preferred choice. Stratified form of ‘Mixed Sampling’ as

it is neither purely Probability Sampling nor purely Non-Probability Sampling’. Samples from

each stratum may be selected by the researcher proportionate to the strata or randomly. That is

entirely the choice of the researcher. However, if samples are selected proportionately, the

representation of each stratum in the final sample is more authentic. For example for a study of

1,000 persons, the population consists of persons belonging to four different religions in this

manner: 400 people in Religion A, 300 people in Religion B, 200 people in Religion C and 100

people in Religion D. the researcher decides to create a sample of 200 people, that is 20% of the

population. Now for the final sample to proportionately represent each stratum, the researcher

must draw out 20% of sample from each stratum as well. Thus, there will be 80 persons from

Religion A, 60 persons from Religion B, 40 persons from Religion C and 20 persons from

Religion D.

Purposive Sampling

Purposive sampling is also known as ‘Judgment Sampling’, as it relies entirely on the wish and

judgment of the researcher. This is the purest form of Nonprobability Sampling. No unit in the

universe stands any chance of being included in the sample except the ones that the researcher
himself/herself chooses. That is to say all the units in the universe do not have an equal chance of

being included in the sample. In purposive sampling the researcher purposely selects units to

include in the sample. The basis for selection of the units is entirely the wish and judgment of the

researcher.

Cluster Sampling

Cluster sampling involves drawing samples from smaller clusters that the population is divided

into. It should not be confused with stratified sampling. In cluster sampling, the population is

either studied in multi-phase method, in different clusters, or samples are drawn from each

cluster. This type of sampling is useful only where the population can be looked at, in a cluster.

Unlike stratified sampling, cluster sampling does not require the population to be divided into

homogeneous groups; that is to say the clusters may be heterogeneous. For example, an

accrediting study is to be conducted on a private university in India. A university is a collection

of students, teachers, visiting faculty, office staff, etc., and it cannot be divided into strata

because it is best to be seen in its functional mode. But the University has various departments,

which can be considered each as a cluster. The clusters may be studied one by one in multi-phase

method or else samples may be formed out of each of the clusters, and studied together, just like

we saw in.

Quota Sampling

Quota sampling is a very useful method of sampling where a large body of persons is to be

studied. In quota sampling the population is divided into different categories on the basis of some

characteristics, and selection of units in the sampling is done according to the proportion that

group represents in the entire population. For quota sampling the researcher must first define the
characteristics on the basis of which the population shall be divided into groups. The researcher

must have knowledge about the proportion that each characteristic group possesses in the

population. The sample drawn from the universe would proportionately represent the

characteristics in the population.

COLLECTION OF DATA

Data represents information collected in the form of numbers and text. Data collection is done

after an experiment or an observation. Data collection is useful in planning, estimation and it also

saves lot of time and resources. Data collection is either qualitative or quantitative. Data

collection methods are used in businesses and sales organizations to analyze the outcome of a

problem, arrive at a solution, draw conclusions about the performance of a business and so on.

Primary Data Collection Methods

Primary data collection is the original form of data that is collected directly from the source. For

example, data collected through surveys, opinion polls from people, conducting experiments,

Primary data can be classified in to the following two types. They are,

 Quantitative data collection methods

 Qualitative data collection methods

Qualitative Data Collection Methods

Qualitative data collection methods does not include any mathematical calculation to collect

data. It is mainly used for analyzing the quality, or understanding the reason behind something.

Some of the common methods used for qualitative data collection are discussed below.
Interview method

As the name suggests data collection is made by verbal conversation of interviewing people in

person or in a telephone or using any computer aided model. A short note on each of these

methods is given below.

Personal or Face to Face Interview: This is done by an interviewer with a person from whom

data is collected. The interview may be structured or it may not be structured. Data to be

collected is directly got from the person who is interviewed by straight forward questions or

investigations.

Telephonic Interview: This is done by asking questions in a telephonic call. There are many

online calling software readily available to carry out this data collection method. Data is

collected from people directly by collecting their views or opinions on a topic.

Computer Assisted Interview: This type of interview is same as that of a personal interview,

except that the interviewer and the person being interviewed are doing it in a desktop or a laptop.

Also, the data collected is directly updated in a database in a aim of making the process quicker

and easier and it eliminates lot of paper work to be done in updating the collection of data.

Questionnaire Method of Collecting Data

Questionnaire method is nothing but conducting surveys with a set of questions targeting the

quantitative research. These survey questions are easily made using online survey questions
creation software. It also ensures that the trust of the people attending the surveys are

legitimized. Some types of questionnaire methods are,

Web Based Questionnaire: Web based questionnaire is a method in which a survey link is sent

to the targeted audience. They click on the link which takes them to the survey questions. This is

a very cost efficient and a quick method which people can do it at their own convenient time.

The survey has the flexibility of doing in any device also. So it is really reliable and flexible.

Mail Based Questionnaire: In this type of questionnaire mails are sent to the target audience

which contains sheets of paper containing survey questions. Basically it contains the purpose of

conducting the survey and the type of research that is being made. Some incentives are also

given to complete this survey which is a main attraction. The benefit of this method is that the

respondents name remains undisclosed to the researchers and they are free to take any time to

complete this survey.

Observation method

As the word 'observation' suggests, in this method data is being collected directly by observing.

This can be achieved by counting the number of people or umber of events that take place in a

particular time frame. The main skill needed here is to observe and arrive at the numbers

correctly. Structured observation is a type of observation method in which a researcher observes

for certain specific behaviors.

Processing and analysis of data

The information/data collected/collated either from primary or secondary sources at the initial
stage is known as raw data. Raw data is nothing but the observation recorded from individual

units. Raw data, particularly the primary data, can hardly speak anything unless and otherwise

arranged in order or processed. Data are required to be processed and analyzed as per the

requirement of a research problem outlined. Working with data starts with the scrutiny of data;

sometimes it is also known as editing of data.

Scrutiny and Arrangement of Data

Raw data set is put under careful examination to find out the existence of any abnormal/doubtful

observation, to detect errors and omissions, if any, and to rectify these. Editing/scrutiny of data

ensures the accuracy, uniformity, and consistency of data. If the observations are few in number,

during scrutiny, one can have an overall idea about the information collected or collated. If the

number of observations is large, then one may go for arrangement of observations in order, that

is, either ascending or descending order and then go for scrutiny.

Coding of Data

Sometimes the information collected may be qualitative in nature like male/female,

black/yellow/ white/green, determinate/indeterminate, and educated/illiterate. Coding refers to

the process of assigning numerals or other symbols to the responses so that these could be

categorized. Coding should be made in such a way that these are nonoverlapping and all the

observations are categorized in one of the categories framed for the purpose. That means the

coding should be made in such a way that categories are exclusive and exhaustive in nature.
Generally, the numerical information does not require coding. Coding helps researchers in

understanding the data in a more meaningful way.

Analysis of Data

Once after the processing and data presentation, it is now imperative for a researcher to explain

and describe the nature of the research in a deeper sense. In the first attempt, the researcher tries

to explain/describe the nature of the information through measures of central tendency, measures

of dispersion, measures of asymmetry, etc., taking one variable at a time—known as univariate

analysis. In his/her next endeavor, he/she tries to find out the association among the variables—

which are coming under either bivariate (taking two variables at a time) or multivariate analysis

(taking more than two variables at a time). Once after completion of the description (through

univariate/bivariate/ multivariate analysis), the researcher tries to infer or draw conclusion about

the population characteristics from the sample behaviors studied

so far through inferential statistics.

Correlation Analysis

While conducting research works, a researcher needs to deal with a number of factors/variables

at a time, instead of a single variable/factor. And all these variables may not be independent of

each other; rather they tend to vary side by side. Most of the growth/social/economic and other

variables are found to follow the above characteristics. For example, while dealing with yield

component analysis of any crop, it is found that yield is an ultimate variable contributed/

influenced/affected by a number of other factors. If we consider the yield of paddy, then one can

find that the factors like the number of hills per square meter, number of tillers per hill, number
of effective/panicle-bearing tillers per hill, length of the panicle, number of grains per panicle,

and test (1,000 grain) weight of grains are influencing the yield. Variation in one or more of the

abovementioned factors results in variations of the yield. Thus, yield may vary because of

variation in the number of hills per square meter or variations in the number of tillers per hill or

so on. Again, yield may vary because of variation in the number of hill per square meter and/or

in the number of tiller per hill and other factors. When we consider variations in one variable

due to variations in any other variable, then it becomes a bivariate case.

Analysis of Variance and Experimental Designs

The analysis of variance technique, in short ANOVA, is a powerful technique used in

the field of agriculture, social science, business, education, medicine, and several other fields.

Using this tool the researcher can draw inference about the samples whether these have been

drawn from the same population or they belong to different populations. Using this technique

the researcher can establish whether a no. of varieties differ significantly among themselves

with respect to their different characteristics like yield, susceptibility to diseases and pests,

nutrient acceptability, and stress tolerance and efficiency of different salesmen; for example,

one can compare different plant protection chemicals, different groups of people with

respect to their innovativeness, and different drugs against a particular disease, different

programs of poverty reduction, performances of different business houses, and so on.

Data Transformation
Among the different types of transformation generally used to make the data corrected for

analysis of variance, logarithmic transformation, square root transformation, and angular

transformation are widely used.

Logarithmic Transformation

The number of plant insects, number of egg mass per unit area, number of larvae per unit

area, etc., are typical examples wherein variance is proportional to the mean and logarithmic

transformation can be used effectively. The procedure is to take simply the logarithm of each and

every observation and carry out the analysis of variance following the usual procedure with the

transformed data.

Completely Randomized Design (CRD)

Among all experimental designs, completely randomized design (CRD) is the simplest one

where only two principles of design of experiments, that is, replication and randomization,

have been used. The principle of local control is not used in this design. CRD is being analyzed

as

per the model of one-way ANOVA. The basic characteristic of this design is that the whole

experimental area (1) should be homogeneous in nature and (2) should be divided into as many

numbers of experimental units as the sum of the number of replications of all the treatments. Let

us suppose there are five treatments A, B, C, D, and E replicated 5, 4, 3, 3, and 5 times,

respectively, then according to this design, we require the whole experimental area to be divided

into 20 experimental units of equal size. Under laboratory condition, completely randomized

design is the most accepted and widely used design.

Latin Square Design (LSD)

LSD is a design in which known sources of variation in two perpendicular directions, that

is, north to south and east to west or south to north and west to east, could be taken into

consideration. In this type of field, we require framing of blocks into perpendicular directions

which take care of the heterogeneity in both directions. A Latin square is an arrangement of

treatments in such a way that each treatment occurs once and only once in each row and each

column. If t is the number of treatments, then the total number of experimental units needed for

this design is t _ t.

Analysis Related to Breeding Researches

The analysis of covariance can be taken up for one-way and two-way layouts and other specific

types of experimental design. In the analysis of covariance, there is one dependent variable (y)

and one or more concomitant variables. The basic difference between the analysis of variance

and the analysis of covariance models is that in the former, each response (y) is partitioned into

two components, one because of its true value and the error part.

There are several examples where the analysis of covariance can be used effectively in

augmenting the precession of the experimental results. For example, in yield component analysis

of paddy, the yield components, namely, the number of hills per unit area, the number of

effective tillers per hill, and the number of grains per panicles, can be used as covariates or

concomitant variables. In a study of health drinks on the growth and physique of

school-going children, initial body weight, height, age, physical agility, etc., can be taken as

concomitant variables during the analysis of covariance. In the analysis of covariance, there are
two types of variables: the characteristic of the main interest and the information on the

secondary or auxiliary interest or the covariates.

In the analysis of covariance, the expected (true) value of the response is the resultant of two

components, one because of the linear combination of the values of the concomitant variables

which are functionally related with the response and another one already obtained in the analysis

of variance. During regression analysis, generally one dependent variable is taken at a time to

find out its relationship with independent variables. But in many situations, the researchers need

to consider a group of dependent and independent variables.

The researchers become interested in getting the relationship between a group of dependent

variables and a group of independent variables. Canonical correlation analysis facilitates in

getting the interrelationship between these two groups of variables. Canonical correlation is a

powerful multivariate technique which provides the information of higher quality and in a more

interpretable manner. Canonical analysis suggests the number of ways in which two groups

(independent and dependent) of variables are related, their strength of linear relationship, and the

nature of the relationship which otherwise might be unmanageable by judging huge number of

bivariate correlations between sets of variables.