Business Research Methods

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 28

UNIT-1

❖ Introduction to Research: Definition, why study Business Research,


Objectives, Importance of research applications in functional areas
of business, Emerging trends in Business research

Research is a systematic process of collecting and analyzing information to answer


questions or solve problems. It is a process that involves gathering data, evaluating
the data, and drawing conclusions.

Why study business research?

Business research is important for a number of reasons. First, it can help businesses
to make better decisions. By understanding the market, the competition, and the
needs of customers, businesses can make more informed decisions about their
products, services, and strategies.

Second, business research can help businesses to identify new opportunities. By


researching trends and emerging markets, businesses can identify new opportunities
to grow and expand.

Third, business research can help businesses to improve their performance. By


measuring and analyzing their performance, businesses can identify areas where
they can improve.

Objectives of business research

The objectives of business research can vary depending on the specific needs of the
business. However, some common objectives of business research include:

• To identify and understand market trends


• To assess the competitive landscape
• To understand customer needs and preferences
• To develop new products and services
• To improve existing products and services
• To make better business decisions

Importance of research applications in functional areas of business

Business research can be applied to all functional areas of business, including:


• Marketing: Business research can be used to identify market trends, assess
the competitive landscape, and understand customer needs and preferences.
This information can then be used to develop and implement effective
marketing strategies.
• Sales: Business research can be used to identify potential customers,
understand their needs, and develop targeted sales pitches.
• Product development: Business research can be used to identify new product
opportunities, assess customer demand, and test new products.
• Operations: Business research can be used to improve efficiency, reduce
costs, and improve quality.
• Finance: Business research can be used to make better investment decisions,
assess risk, and forecast financial performance.
Emerging trends in business research

• Artificial Intelligence (AI) and Machine Learning: AI is being increasingly used


in business research to analyse large datasets, make predictions, and
automate decision-making processes.
• Blockchain Technology: Research related to blockchain has grown,
particularly in the areas of supply chain management, finance, and data
security.
• Digital Transformation: Research is focused on how businesses can adapt to
the digital age, incorporating e-commerce, data analytics, and remote work
strategies.
• Consumer Behavior in the Digital Age: Understanding how consumers interact
with digital platforms and make purchasing decisions online.

❖ Steps in Research Process: From defining the problem to Report


Writing
The research process is a systematic and iterative way of gathering and
analyzing information in order to answer a research question or solve a
problem. It can be broken down into the following steps:

1. Define the problem or research question. What do you want to know? What is
the purpose of your research?
2. Review the literature. What have other researchers found on this topic? This
will help you to understand the current state of knowledge and identify any
gaps in research.
3. Develop a research design. How will you collect and analyze your data? This
will depend on the nature of your research question and the available
resources.
4. Collect data. This may involve conducting surveys, interviews, experiments, or
observations.
5. Analyze data. This involves using statistical or qualitative methods to make
sense of your data.
6. Interpret findings. What do your findings mean? How do they answer your
research question?
7. Write a research report. This should clearly communicate your findings and
their implications.

The research process is not always linear, and you may need to go back and forth
between steps as you gather more information and refine your ideas. However,
following these steps will help you to conduct a rigorous and systematic research
project.

The research process can be challenging, but it is also a rewarding way to learn
about the world. By following these steps, you can conduct a rigorous and
systematic research project that will help you to answer your research question and
make a contribution to knowledge.
❖ The research ‘onion’: Philosophies, Approach, Methodological
choices, Strategy, Time Horizons, Technique and Procedures

The research onion is a model that helps researchers to think about the different
layers of their research methodology. The different layers are:

• Research philosophies: These are the underlying beliefs about the nature of
reality and knowledge that guide the research. There are three main research
philosophies: positivism, interpretivism, and pragmatism.
• Approaches: These are the broader methods that researchers use to collect
and analyze data. There are two main approaches: quantitative and
qualitative.
• Methodological choices: These are the specific methods that researchers use
within a particular approach. For example, within the quantitative approach,
researchers might choose to use a survey, experiment, or observational study.
• Research strategy: This is the plan for how the research will be conducted. It
includes the research questions, the data collection methods, the data
analysis methods, and the ethical considerations.
• Time horizons: These are the points in time at which data will be collected. For
example, a cross-sectional study collects data at one point in time, while a
longitudinal study collects data at multiple points in time.
• Techniques and procedures: These are the specific procedures that
researchers use to collect and analyze data. For example, within a survey,
researchers might use a Likert scale or open-ended questions.
The research onion is a useful tool for thinking about the different layers of research
methodology and how they are interrelated. By considering all of these layers,
researchers can develop a more comprehensive and rigorous research design.

❖ Language of Research: Concept, construct, proposition, hypothesis,


research question, constant, variable, Decision Support System,
Business Intelligence (Expected at conceptual level)

Concept: A concept is an abstract idea or a general notion that represents


something in the mind. In research, concepts can serve as the foundation for
building theories or understanding phenomena.

Construct: A construct is an abstract or theoretical concept that is created for a


specific research purpose. It often involves defining and measuring abstract ideas,
such as intelligence or happiness, through observable indicators.

Proposition: A proposition is a statement that suggests a relationship between two


or more concepts. It forms the basis for developing hypotheses and theories in
research.

Hypothesis: A hypothesis is a testable statement or prediction that is derived from a


proposition. It is used to guide empirical research and is either supported or rejected
based on evidence.

Research Question: A research question is an inquiry that a researcher seeks to


answer through their study. It defines the scope of the research and guides the
collection and analysis of data.

Constant: A constant is a factor or element in a study that remains unchanged or is


held consistent throughout the research. It is used to control for potential
confounding variables.

Variable: A variable is an element or concept that can take on different values in a


study. Independent variables are manipulated or controlled, while dependent
variables are measured and observed.

Decision Support System (DSS): A Decision Support System is a computer-based


tool or software that aids decision-makers in making informed choices by providing
relevant information, data analysis, and modeling.

Business Intelligence (BI): Business Intelligence is a set of technologies,


processes, and tools that help organizations collect, analyze, and present business
information to support decision-making. It involves data gathering, reporting, and
data-driven insights for strategic planning.

❖ Research Proposal: Elements of a Research Proposal, drafting a


Research Proposal, Evaluating a research proposal

A research proposal is a document that outlines the research that you plan to
conduct. It is typically written for a professor or other academic advisor, but it
can also be used to apply for funding or to present your research to a wider
audience.

The elements of a research proposal vary depending on the discipline and the
specific requirements of the institution or organization that you are submitting it to.
However, there are some common elements that are typically included:

• Title: The title should be clear and concise, and it should accurately reflect the
content of the proposal.
• Introduction: The introduction should provide an overview of the research
topic, the research problem, and the purpose of the study.
• Literature review: The literature review should discuss the current state of
knowledge on the research topic. It should identify the gaps in knowledge that
your research will address.
• Research questions: The research questions should be specific and
answerable. They should provide the focus for the rest of the research
proposal.
• Research design: The research design should describe the methods that you
will use to collect and analyze data.
• Timeline and budget: The timeline and budget should provide a realistic
estimate of the resources that you will need to complete your research.
• Ethical considerations: The ethical considerations should address any
potential ethical issues that may arise during the course of your research.

When drafting a research proposal, it is important to be clear and concise.


The proposal should be well-organized and easy to read. It is also important to
use proper grammar and punctuation.

When evaluating a research proposal, it is important to consider the following


factors:

• Is the research problem clearly defined?


• Is the literature review comprehensive and up-to-date?
• Are the research questions clear and answerable?
• Is the research design appropriate for the research questions?
• Is the timeline and budget realistic?
• Have the ethical considerations been addressed?

By considering these factors, you can evaluate a research proposal and determine
whether it is well-written and feasible

Evaluating a research proposal

Evaluating a research proposal involves assessing its quality, feasibility, and


potential impact. Here are some key steps and criteria to consider:

• Clarity and Structure:

Is the proposal well-organized and clearly written?

Does it have a clear title, abstract, introduction, methods, results, and conclusion
sections?

• Research Question and Objectives:

Is the research question well-defined and relevant?

Are the research objectives clearly stated?

• Literature Review:

Does the proposal provide a comprehensive review of existing literature in the field?

Is there a rationale for the study based on previous research?

• Methodology:

Are the research methods clearly outlined?

Are the data collection and analysis methods appropriate?

Is the proposed sample size adequate for the research question?


• Budget and Funding:

Is the budget well-detailed and justified?

Are potential sources of funding identified?

• References:

Are all references properly cited and relevant to the proposal?

UNIT-2

❖ Literature Review: Drafting review of literature, usage of Annotated


Bibliography, Introduction to Meta analysis

A literature review is an essential component of research papers and projects,


providing a comprehensive overview of existing research on a specific topic. Here's
how to draft a literature review, use annotated bibliography, and introduce meta-
analysis:

Drafting a Literature Review:

Select Your Topic: Define the scope and focus of your literature review. What specific
aspect of the topic are you exploring?
Search for Sources: Conduct a thorough search using academic databases,
journals, books, and reputable online sources. Keep detailed records of the sources
you find.
Categorize Sources: Organize your sources into categories or themes. Identify key
concepts and trends in the literature.
Write the Review: Summarize and synthesize the findings from each source. Discuss
the main ideas, methodologies, and key findings. Highlight gaps, contradictions, and
areas of agreement.

Annotated Bibliography:

What is it: An annotated bibliography is a list of sources with brief summaries and
evaluations of each source.
Purpose: It helps you keep track of sources, evaluate their relevance, and provide a
quick overview of each source's content and quality.
Annotations: Include a concise summary of the source, an evaluation of its credibility,
and its relevance to your research topic.
Introduction to Meta-Analysis:

Definition: Meta-analysis is a statistical technique used to combine the results of


multiple studies on a specific research question to provide a more robust and
generalizable conclusion.
Search and Select Studies: Conduct a systematic search for relevant studies and
apply inclusion/exclusion criteria.
Data Extraction: Collect and record data from each study, including effect sizes and
sample sizes.
Meta-Analysis: Use statistical software to combine the effect sizes and analyze the
overall effect.

❖ Research Design: Concept, features of a good research design, Use


of a good research design.

Concept: Research design is the blueprint or plan that outlines how a research
study will be conducted. It encompasses the overall structure, methodology, and
procedures of the research, including data collection and analysis.

Features of a Good Research Design:

• Clear Objectives: A research design should have well-defined research


questions or objectives.
• Appropriate Methods: It should use suitable data collection and analysis
methods.
• Validity and Reliability: Ensure that the design leads to credible and consistent
results.
• Ethical Considerations: Ethical guidelines must be followed in the design and
implementation.

Use of a Good Research Design:

A well-structured research design helps researchers systematically investigate


a problem, collect relevant data, and draw meaningful conclusions. It ensures
that research is conducted in a systematic and organized manner.
Qualitative Research and Quantitative Research Designs:

 Qualitative research and Quantitative research Designs


Qualitative research is an approach to research that seeks to understand the
meaning that people give to their experiences. It is typically used to study human
behavior and interactions in natural settings. Qualitative researchers use methods
such as interviews, focus groups, and participant observation to collect data. Then
analyze the data using methods such as thematic analysis and content analysis to
identify patterns and themes.

Quantitative research is an approach to research that seeks to quantify the


relationship between variables. It is typically used to study large populations or
groups. Quantitative researchers use methods such as surveys, experiments, and
observational studies to collect data. They then analyze the data using statistical
methods to test hypotheses and make inferences about the population or group.

The choice of qualitative or quantitative research design depends on the research


question, the available resources, and the researcher's own preferences.

Here is a table summarizing the key differences between qualitative and quantitative
research:
Feature Qualitative research Quantitative research

Underlying The world is subjective and that The world is objective and that there
assumptions people's experiences are shaped by is a single reality that can be studied
their own perspectives. through scientific methods.

Data collection Interviews, focus groups, participant Surveys, experiments, observational


methods observation studies

Data analysis
Thematic analysis, content analysis Statistical analysis
methods

Can provide rich insights into Can be used to test hypotheses and
Strengths people's experiences and make inferences about large
perspectives. populations.

Can be impersonal and may not


Can be time-consuming and difficult capture the richness of human
Weaknesses to generalize the results. experience.

Here are some examples of qualitative research designs:

• Case study: A case study is an in-depth investigation of a single individual,


group, or event.
• Ethnography: Ethnography is the study of a culture or subculture through
participant observation.
• Phenomenology: Phenomenology is the study of the lived experiences of
individuals.
• Grounded theory: Grounded theory is a method of developing theory from
data.

Here are some examples of quantitative research designs:

Exploratory Research Design: Concept, Types: Qualitative techniques - Projective


Techniques, Depth Interview, Experience Survey, Focus Groups, Observation

Exploratory research is a preliminary phase of research that is conducted when the


topic or problem is not well understood or defined. It aims to gain insights, clarify
concepts, and gather information to better define research objectives. Qualitative
techniques are often used in exploratory research, and some common ones include

Projective Techniques: These involve indirect methods to understand a person's


thoughts, feelings, or attitudes. Examples include word association tests, sentence
completion tests, and picture interpretation tests

Depth Interview: In-depth interviews are one-on-one conversations with open-ended


questions. They allow researchers to explore a respondent's thoughts, experiences,
and opinions in detail.

Experience Survey: An experience survey involves gathering information from


people who have had direct experience with the subject of interest. It can provide
valuable insights and anecdotal data.

Focus Groups: Focus groups bring together a small group of participants to discuss
a specific topic. They are led by a moderator who encourages open discussion, and
they can reveal a range of perspectives and insights.

Observation: Observational research involves directly observing and recording


behaviors or events. It can be done in a natural setting (naturalistic observation) or in
a controlled environment (controlled observation).

❖ Descriptive Research Designs: Concept, types and uses. Concept of


Cross-sectional and Longitudinal Research

Descriptive research designs aim to describe and explain a phenomenon without


manipulating it. These designs provide a snapshot of the current state of affairs and
are often used to gather information about variables, relationships, and
characteristics.
• Types of Descriptive Research Designs:

Cross-Sectional Research: This type involves collecting data from a sample or


population at a single point in time. It provides a snapshot of the subject of study at
that specific moment. Cross-sectional research is often used in surveys and opinion
polls to understand characteristics, opinions, or behaviors of a group at a particular
time.

Longitudinal Research: In longitudinal research, data is collected from the same


subjects over an extended period, often years or even decades. This design helps
researchers observe changes and trends over time, making it useful for studying
developmental processes, tracking the evolution of variables, and examining cause-
and-effect relationships.

• Uses of Descriptive Research:

Understanding Trends and Characteristics: Descriptive research helps researchers


understand the characteristics, behaviors, and attitudes of a particular population or
group.

Identifying Relationships: It can be used to identify relationships between variables,


which can be a precursor to more in-depth exploratory or explanatory research.

Monitoring Changes Over Time: Longitudinal research, in particular, is valuable for


tracking changes and developments over time.

Policy and Decision-Making: Government agencies and organizations use


descriptive research to gather data for policy development, resource allocation, and
decision-making.

Market Research: Businesses use descriptive research to gain insights into market
trends, consumer preferences, and competitive landscapes.

Healthcare and Social Sciences: Descriptive research is employed to assess the


health status of populations, understand societal issues, and monitor public health
trends.

 Hypothesis: Qualities of a good Hypothesis –Framing Null Hypothesis &


Alternative Hypothesis. Testing of Hypothesis at 5 % level of significance

A hypothesis is a statement about the relationship between two or more variables. It


is an educated guess about what the outcome of a research study will be.

A good hypothesis should be:


• Specific: It should be clear and concise, and it should state the relationship
between the variables in a specific way.
• Measurable: It should be possible to measure the variables in the hypothesis.
• Testable: It should be possible to test the hypothesis using research methods.
• Plausible: It should be based on existing knowledge and theory.
• Original: It should not have been tested before.
The null hypothesis is a statement that there is no relationship between the
variables. The alternative hypothesis is a statement that there is a relationship
between the variables.

For example, a researcher might hypothesize that there is a relationship between the
amount of sleep a person gets and their academic performance. The null hypothesis
would be that there is no relationship between the amount of sleep a person gets
and their academic performance. The alternative hypothesis would be that there is a
positive relationship between the amount of sleep a person gets and their academic
performance.

The level of significance is the probability of rejecting the null hypothesis when it is
actually true. The standard level of significance is 0.05, which means that there is a
5% chance of rejecting the null hypothesis when it is actually true.

To test a hypothesis, researchers collect data and then use statistical methods to
analyze the data. If the results of the analysis are statistically significant, then the
researcher can reject the null hypothesis and accept the alternative hypothesis.

Here are some of the steps involved in testing a hypothesis:

1. State the hypothesis.


2. Set the level of significance.
3. Collect data.
4. Analyze the data.
5. Make a decision about the hypothesis.

UNIT-3

❖ Concept of Measurement: What is measured? Problems in


measurement in management research - Validity and Reliability.
Different types of Validity and Reliability measurement.

Measurement in management research is the process of assigning numbers or


labels to represent certain characteristics, attributes, or variables. In this context,
what is measured can vary widely, including aspects like employee performance,
customer satisfaction, or financial metrics. However, it's essential to ensure the
measurements are accurate and meaningful.

Problems in measurement in management research:


• Validity: Validity refers to the extent to which a measurement accurately
represents the concept it's intended to measure. Common issues include
construct validity (whether the measurement accurately captures the intended
concept) and content validity (whether all relevant aspects of the concept are
included).

• Reliability: Reliability concerns the consistency and stability of measurements.


If a measurement is unreliable, it cannot be trusted. Problems related to
reliability include test-retest reliability (consistency over time), inter-rater
reliability (consistency between different raters), and internal consistency
(consistency within a set of items in a measurement scale).

Different types of validity:


• Content Validity: Ensures that the measurement includes all relevant aspects
of the concept being measured.

• Construct Validity: Determines whether the measurement accurately reflects


the underlying theoretical concept. This can be assessed through factor
analysis, convergent validity (correlation with similar measures), and
discriminant validity (lack of correlation with dissimilar measures).

• Criterion Validity: Involves comparing the measurement with a specific


criterion to assess its accuracy. This can be concurrent (measuring at the
same time as the criterion) or predictive (predicting future outcomes).

Different types of reliability:

• Test-Retest Reliability: Measures the consistency of results when the same


measurement is applied to the same subjects at different times.

• Inter-Rater Reliability: Assesses the consistency of measurements when


different raters or observers are involved.

• Internal Consistency: Examines the consistency of items within a


measurement scale. Common techniques include Cronbach's alpha for
assessing the internal reliability of a scale


 Nominal, Ordinal, Interval, and Ratio scales
Nominal, ordinal, interval, and ratio are four levels of measurement in statistics. They
are used to describe the type of information recorded within the values of your
variables. Variables take on different values in your data set. For example, you can
measure height, gender, and class ranking. Each of these variables uses a distinct
level of measurement.

• Nominal scale is the simplest level of measurement. It is used to categorize


data into mutually exclusive categories or groups. The categories do not have
any order or ranking. For example, gender is a nominal variable with two
categories: male and female.

• Ordinal scale is a level of measurement that allows you to rank data in order.
However, the intervals between the ranks are not equal. For example, a
survey question that asks respondents to rate their satisfaction with a product
on a scale of 1 to 5 is an ordinal scale. The rating of 1 is better than the rating
of 2, but the difference between 1 and 2 is not the same as the difference
between 4 and 5.

• Interval scale is a level of measurement that allows you to rank data in order
and the intervals between the ranks are equal. However, the scale does not
have a natural zero point. For example, temperature is measured on an
interval scale. The difference between 10 degrees Celsius and 20 degrees
Celsius is the same as the difference between 20 degrees Celsius and 30
degrees Celsius. However, there is no natural zero point for temperature.

• Ratio scale is the highest level of measurement. It allows you to rank data in
order, the intervals between the ranks are equal, and there is a natural zero
point. For example, weight is measured on a ratio scale. The difference
between 10 kilograms and 20 kilograms is the same as the difference
between 20 kilograms and 30 kilograms. There is also a natural zero point for
weight, which is 0 kilograms.
The level of measurement that you choose for your variables will depend on the type
of data that you are collecting and the statistical analyses that you want to perform.

• Here is a table summarizing the key differences between the four levels of
measurement:

Level of
Description measurement Example

Nominal scale Data is categorized into mutually Gender (male, female)


exclusive categories.
Customer satisfaction
Data is ranked in order, but the
(very satisfied, satisfied,
Ordinal scale intervals between the ranks are
dissatisfied, very
not equal.
dissatisfied)

Data is ranked in order and the


Temperature (degrees
Interval scale intervals between the ranks are
Celsius)
equal. There is no natural zero point.

Data is ranked in order, the intervals


between the ranks are equal, and
Ratio scale there is a natural zero point. Weight (kilograms)
 Rating Scales viz. Likert Scales, Semantic Differential Scales, Constant
Sum Scales

Rating scales are a type of scale used to measure people's attitudes, beliefs, or
opinions. They are typically used in surveys and questionnaires. There are many
different types of rating scales, but some of the most common ones include:

• Likert scales: Likert scales are the most common type of rating scale. They
consist of a series of statements, and respondents are asked to indicate their
agreement or disagreement with each statement on a scale of 1 to 5, 1 to 7,
or 1 to 10.

www.scribbr.com Opens in a new window


Likert scale example

• Semantic differential scales: Semantic differential scales are used to


measure people's attitudes towards an object or concept. They consist of a
series of bipolar adjectives, and respondents are asked to indicate their
position on the scale between the two adjectives.
www.alchemer.com Opens in a new window
Semantic differential scale example

• Constant sum scales: Constant sum scales are used to measure the relative
importance of different items. Respondents are given a fixed number of
points, and they are asked to distribute the points among the items in a way
that reflects their relative importance.

www.questionpro.com Opens in a new window

Constant sum scale example

• Guttman scales: Guttman scales are used to measure people's attitudes in a


more precise way than Likert scales. They consist of a series of statements,
and respondents are asked to indicate whether they agree or disagree with
each statement. The statements are arranged in such a way that if a
respondent agrees with one statement, they must also agree with all of the
statements that are below it in the scale.

www.questionpro.com Opens in a new window

Guttman scale example


The choice of rating scale will depend on the research question that you are trying to
answer and the type of data that you are collecting.

❖ Types of Data: Concept of Primary Data and Secondary data,


parametric and non-parametric data.

Primary data is data that is collected for the first time, specifically for the research
being conducted. It is collected by the researcher directly from the source. For
example, a researcher may conduct a survey to collect primary data about people's
attitudes towards a particular issue.

Secondary data is data that has already been collected by someone else. It can be
found in a variety of sources, such as government reports, academic journals, and
company databases. Secondary data is often used to supplement primary data or to
provide background information for a research project.

Parametric data is data that is assumed to be normally distributed. This means that
the data is bell-shaped and that the mean, median, and mode are all equal.
Parametric data can be analyzed using a variety of statistical tests, such as t-tests
and ANOVA.

Non-parametric data is data that is not normally distributed. This means that the
data does not have a bell-shaped curve and that the mean, median, and mode may
not be equal. Non-parametric data can be analyzed using a variety of statistical
tests, such as the Mann-Whitney U test and the Kruskal-Wallis test.

 Here is a table summarizing the key differences between primary and


secondary data, and parametric and non-parametric data:
Type of data Description
Primary data Data that is collected for the first time, specifically for the
research being conducted.

Secondary data Data that has already been collected by someone else.

Data that is assumed to be normally distributed.

Parametric data

Non-
parametric data Data that is not normally distributed.
❖ Methods of collecting secondary data: Searching World Wide Web
for data, edatabases, books, journals, periodicals. Issues to be
considered for secondary data, sufficiency, adequacy, reliability,
consistency.

Here are some of the most common methods of collecting secondary data:

• Searching the World Wide Web: The World Wide Web is a vast resource of
information, and it can be a great place to start your search for secondary
data. However, it is important to be aware of the limitations of web-based
data, such as the potential for bias and inaccuracy.
• Electronic databases: There are many electronic databases that contain
secondary data, such as academic journals, government reports, and
company financial statements. These databases can be a great way to find
data that is relevant to your research question.
• Books: Books can be a valuable source of secondary data, especially if you
are looking for historical or in-depth information. However, it is important to be
aware of the age of the data, as it may not be up-to-date.
• Journals: Journals are a good source of secondary data, as they typically
contain peer-reviewed articles that have been published by experts in the
field. However, it is important to be aware of the journal's reputation, as some
journals are more reputable than others.
• Periodicals: Periodicals are a good source of up-to-date secondary data, as
they are published on a regular basis. However, it is important to be aware of
the periodical's bias, as some periodicals may have a particular viewpoint.

Here are some of the issues that should be considered when using secondary data:

• Sufficiency: The data must be sufficient to answer the research question.


• Adequacy: The data must be adequate to support the conclusions of the
research.
• Reliability: The data must be reliable, meaning that it is accurate and
consistent.
• Consistency: The data must be consistent with other sources of data
❖ Methods of collecting primary data: Questionnaire, Personal
Interviews, Telephonic survey Interviewing, Email/Internet survey,
Google Forms (Hands on demo of Google Form), Design research
questionnaire

Questionnaire: A questionnaire is a list of questions that are used to collect


data from a group of people. Questionnaires can be administered in person,
over the phone, or online.

chattermill.com Opens in a new window


Questionnaire survey

Personal interview: A personal interview is a conversation between a


researcher and a participant. Personal interviews can be conducted in person
or over the phone.

www.questionpro.com Opens in a new window

Personal interview survey

Telephonic survey: A telephonic survey is a survey that is conducted over the


phone. Telephonic surveys can be a cost-effective way to collect data from a
large number of people.
www.questionpro.com Opens in a new window

Telephonic survey interview

Email/Internet survey: An email/Internet survey is a survey that is sent to


participants via email or a website. Email/Internet surveys can be a
convenient way to collect data from a large number of people.

www.objectplanet.com Opens in a new window


Email/Internet survey

Google Forms: Google Forms is a free online tool that can be used to create
and administer surveys. Google Forms is a user-friendly tool that can be used
to collect data from a large number of people.

Opens in a new window www.google.com


Google Forms survey

Design research questionnaire: A design research questionnaire is a type of


questionnaire that is used to collect data about people's needs, wants, and
experiences. Design research questionnaires are often used in the early
stages of the design process to help designers understand the needs of the
people who will be using the product or service
❖ Basic Concepts: Define Universe, Element vs. Unit, Concepts of
Population, Sample, characteristics of a good sample. Sampling
frame, sampling errors, non-sampling errors, methods to reduce the
errors, sample size constraints
Universe (Population):The universe, also known as the population, refers to
the entire group or set of items, people, or entities that you are interested in
studying or analyzing. It is the complete collection of elements that share a
common characteristic.
Element vs. Unit:An element is an individual member or data point within a
population. For example, if you're studying the population of students in a
school, an element could be a specific student.
A unit is a more general term and can refer to any individual entity you are
analyzing. In some cases, the terms "element" and "unit" can be used
interchangeably, but "unit" is a broader term that doesn't necessarily have to
be part of a population.
Sample:A sample is a subset of the population. It is a smaller group of
elements or units selected from the larger population for the purpose of
conducting research or analysis. Sampling is often done to make it more
manageable and cost-effective to study a population.
Characteristics of a Good Sample:
Representativeness: A good sample should accurately reflect the characteristics of
the entire population.
Randomness: Samples should be selected randomly to reduce bias and ensure that
each element or unit has an equal chance of being included.
Adequate Size: The sample size should be sufficient to draw meaningful
conclusions, with a balance between precision and practicality.
Unbiased Selection: The sampling process should not favor any specific group within
the population.
Accuracy: The sample should yield results that are as close as possible to what
would be obtained if the entire population were studied.
Sampling Frame:A sampling frame is a list or source that contains all the
elements or units from which the sample will be selected. It serves as the
basis for selecting the sample and should ideally match the population.
Sampling Errors:Sampling errors are the differences between the
characteristics of the sample and the population due to the random nature of
sampling. These errors can lead to inaccuracies in the estimates made from
the sample.
Non-Sampling Errors:Non-sampling errors are errors that can occur in the
data collection and analysis process but are not related to the sampling itself.
These errors can include mistakes in data recording, non-response bias, or
measurement errors.
Methods to Reduce Errors:To reduce sampling errors, you can use random
sampling techniques, increase the sample size, and ensure a representative
sampling frame.
To reduce non-sampling errors, careful data collection procedures, validation,
and minimizing human errors are important.
Sample Size Constraints:Sample size constraints can include limitations on
resources, time, and access to the population. Researchers often need to
strike a balance between the desired sample size and practical constraints to
conduct their study effectively.

❖ Probability Sample: Simple Random Sampling, Systematic Sampling,


Stratified Sampling, Area Sampling & Cluster Sampling

Simple Random Sampling:Involves selecting a random subset of individuals


from the population, where each individual has an equal chance of being
chosen.Typically done using random number generators or drawing lots.
Systematic Sampling:Involves selecting every nth individual from a list of the
population after a random start.
For example, if you have a list of 1000 people and you want a sample of 100,
you could select every 10th person.
Stratified Sampling:Divides the population into subgroups or strata based on
certain characteristics (e.g., age, gender).A random sample is then taken from
each stratum.
It ensures that each stratum is represented in the sample, making it useful for
comparing subgroups.
Area Sampling:Involves dividing the population into geographical areas or
regions.
Randomly select specific areas and then sample all individuals within those
chosen areas.
Useful when the population is spread across distinct geographical regions.
Cluster Sampling:Divides the population into clusters or groups (e.g.,
schools, neighborhoods).
Randomly select a few clusters and then sample all individuals within those
selected clusters.
It's more practical when the population is large and dispersed
❖ Non-Probability Sample: Judgment Sampling, Convenience
Sampling, Purposive Sampling, Quota Sampling & Snowball
Sampling methods. Determining size of the sample – using online
sample size calculator
Non-probability sampling methods are commonly used in research when it's
difficult to obtain a random sample. Here's a brief overview of the methods
you mentioned:
Judgment Sampling: In this method, the researcher selects specific individuals or
items based on their judgment, expertise, or knowledge of the subject matter. It's a
subjective approach and relies on the researcher's discretion.
Convenience Sampling: This involves selecting the most readily available
individuals or items. It's often used for quick and easy data collection, but it can
introduce bias as it may not represent the entire population.
Purposive Sampling: Researchers deliberately choose specific individuals or items
based on defined criteria. This method is useful when certain characteristics are of
interest.
Quota Sampling: Researchers divide the population into subgroups or quotas
based on certain characteristics and then sample proportionally from each subgroup.
It's commonly used in market research.
Snowball Sampling: This method is often used for hard-to-reach populations.
Researchers start with a small group of individuals and then ask them to refer others,
creating a "snowball" effect.
To determine the size of the sample for these methods, you can use online sample
size calculators. These calculators typically take into account factors like the desired
level of confidence, margin of error, and the estimated population size to provide you
with a sample size recommendation.

UNIT-5
❖ Data Analysis: Editing, Coding, Univariate analysis - Tabular
representation of data, frequency tables, construction offrequency
distributions and their analysis.

Data Editing: This step involves reviewing and cleaning the raw data to
identify and correct any errors or inconsistencies. This may include dealing
with missing values, outliers, and data entry errors. The goal is to ensure that
the data is accurate and reliable for analysis.

Coding: Coding refers to the process of assigning numerical or categorical


codes to the variables in your dataset. This is often necessary to make the
data suitable for analysis. For example, you might assign numerical codes to
categorical variables or recode variables to simplify analysis.
Univariate Analysis: Univariate analysis focuses on examining individual
variables one at a time. Common techniques in univariate analysis include:

Tabular Representation of Data: This involves creating tables to summarize


and display data. For categorical variables, you can create frequency tables to
show the distribution of values.

Frequency Tables: Frequency tables display the counts or percentages of


each category or value within a categorical variable. They help you
understand the distribution of data.

Construction of Frequency Distributions: Frequency distributions are used


to group data into intervals or bins and show the frequency of data points in
each interval. This is often done for continuous numerical variables.

Analysis of Frequency Distributions: Analyzing frequency distributions can


help you identify patterns, central tendencies, and variations within the data.

❖ Graphical Representation of Data: Appropriate usage of Barcharts,


Pie charts, Histogram, Leaf and stem, Candle stick, Boxplots, Scatter
plots.

Bar Chart
Use to compare discrete categories or groups.
Good for showing the frequency, count, or percentage of different categories.
Not suitable for displaying continuous data.

Pie Charts:
Use to show the parts of a whole, especially when you want to emphasize the
contribution of each category to the whole.
Limited to a small number of categories to avoid clutter.

Histograms:
Ideal for displaying the distribution of continuous data.
Shows the frequency or probability of data falling into specific bins or
intervals.

Leaf and Stem Plots:


Effective for displaying the distribution of small to moderately sized datasets.
Useful for visualizing individual data points within a range.

Candlestick Charts:
Primarily used in financial analysis to represent stock price movements over
time.
Shows opening, closing, high, and low prices for a given period.
Box Plots (Box-and-Whisker Plots):
Helpful for displaying the summary statistics and distribution of a dataset,
including outliers.
Provides information about the median, quartiles, and potential outliers.

Scatter Plots:
Used to visualize the relationship between two continuous variables.
Helps identify patterns, correlations, or clusters in the data.

❖ Bivariate Analysis: Cross tabulations, Use of percentages, Bivariate


Correlation Analysis - meaning & types of correlation,Karl Pearson’s
coefficient of correlation, Chi-square test including testing
hypothesis of Association

Bivariate analysis is a statistical method used to analyze the relationship between


two variables. It involves various techniques, including cross-tabulations, the use of
percentages, and bivariate correlation analysis.

Cross Tabulations: This technique is used to examine the relationship between two
categorical variables. It creates a contingency table that displays the frequency
distribution of the variables and helps identify patterns or associations.

Use of Percentages: Percentages are often used in cross-tabulations to express the


distribution of one variable within the categories of another variable. This can provide
insights into the relative proportions of different categories.

Bivariate Correlation Analysis: Bivariate correlation analysis assesses the strength


and direction of the relationship between two continuous variables. It is used to
determine if there is a statistical association between the variables. There are
several types of correlations, including:

Pearson's Correlation Coefficient: This measures the linear relationship


between two continuous variables. It ranges from -1 to 1, with -1 indicating a
perfect negative correlation, 1 indicating a perfect positive correlation, and 0
indicating no linear correlation.

Spearman's Rank Correlation: This is a non-parametric measure of correlation


that assesses the monotonic relationship between two variables. It's suitable
for ordinal or non-normally distributed data.

Kendall's Tau: Another non-parametric correlation measure that assesses the


strength and direction of association between two variables, especially when
dealing with ranked data.

Karl Pearson's Coefficient of Correlation: Karl Pearson's coefficient, also


known as Pearson's r, is a widely used measure of linear correlation between
two continuous variables. It quantifies how well the relationship between
variables can be represented by a straight line.

Chi-Square Test: The chi-square test is used to determine whether there is a


significant association between two categorical variables. It assesses whether
the observed frequency distribution in a contingency table is significantly
different from what would be expected by chance.

Testing Hypothesis of Association: When conducting a chi-square test, the


null hypothesis typically states that there is no association between the two
categorical variables. The test aims to determine whether the observed
association is statistically significant or if it could have occurred by random
chance.

❖ Introduction to SPSS – Hands on usage of SPSS – Data entry,


Descriptive Statistics, One-way ANOVA & Simple Regression.

Introduction to SPSS:
SPSS (Statistical Package for the Social Sciences) is a software program
used for statistical analysis and data management. It provides a user-friendly
interface for performing various statistical analyses.

Hands-on Usage of SPSS:


Data Entry:

Launch SPSS.
Create a new dataset or open an existing one.
Enter your data into the spreadsheet view, with variables in columns and
cases in rows.
Define variable properties (e.g., variable name, data type) in the "Variable
View."
Descriptive Statistics:

Go to "Analyze" in the menu and select "Descriptive Statistics."


Choose the variables you want to analyze.
Specify the statistics you want (e.g., mean, standard deviation).
Click "OK" to generate descriptive statistics for your data.

One-way ANOVA:

Go to "Analyze" and select "Compare Means," then choose "One-Way


ANOVA."
Select the dependent variable (the one you want to test) and the grouping
variable (categorical factor).
Configure options and perform the analysis.
Simple Regression:
Go to "Analyze" and select "Regression," then choose "Linear."
In the dialogue box, select the dependent variable and the predictor variable.
Specify options such as saving residuals or standardized values.
Click "OK" to perform a simple regression analysis.

❖ Research reports typically follow a structured format to effectively


communicate the research findings. Here's a basic outline of how
research reports are structured:

Title Page:

Title of the report.


Author(s) names and affiliations.
Date of publication.

Abstract:

A concise summary of the research, including objectives, methods, key


findings, and conclusions.

Table of Contents:

A list of sections and subsections with page numbers for easy navigation.
List of Figures and Tables (if applicable):
Enumerates the figures and tables used in the report with corresponding page
numbers.

Introduction:

An overview of the research problem, its significance, and the research


objectives or questions.

Literature Review:
A review of relevant literature and previous research on the topic.

Methodology:
Explanation of the research methods, data collection, and analysis
techniques.

Results:

Presentation of the research findings using tables, charts, and graphs.

Discussion:
Interpretation of the results, their implications, and a comparison with existing
literature.

Conclusion:

Summary of the key findings and their relevance to the research objectives.
Recommendations (if applicable):
Suggestions for further research or practical recommendations based on the
findings.

References:
A list of all sources cited in the report, following a specific citation style (e.g.,
APA, MLA).

You might also like