COMPARISON OF DATA COLLECTION TOOLS
Basis Chatbot Google Forms Typeform KoboToolbox
AI tool that interacts Open-source data
Free online Interactive form
Meaning like a human collection
survey tool builder
conversation platform
Traditional form Conversational
Type of Conversational Structured survey
(all questions at (one question at a
Interaction (chat-based) forms
once) time)
Moderate (needs Easy but slightly
Ease of Use Very easy Moderate
setup) advanced
Mostly paid (some Free (open-
Cost Completely free Free + Paid plans
free versions) source)
Design & Interactive and Simple and Highly attractive Basic but
Interface engaging basic and professional functional
Online responses
Data Collection Real-time chat Online Online + Offline
with better
Mode responses responses collection
engagement
Internet Can work offline
Required Required Required
Requirement also
Academic Marketing surveys,
Customer support, Field surveys,
Best Use surveys, simple customer
feedback collection rural research
research experience
High (AI-based High (branding &
Customization Limited Moderate
responses) design)
Auto-replies & smart Auto data One-question-at-a- Works without
Special Feature
questioning storage in sheets time format internet
PRIMARY DATA
Meaning of Primary Data
Primary data is the original data collected directly by the researcher for a specific research
purpose.
Observational Method – Meaning
Observation method is a technique of collecting data by watching and recording behavior,
events, or situations without asking questions.
Types of Observational Method
1. Structured Observation
Observation is done in a planned and systematic way with predefined criteria.
Example: Recording how many customers enter a shop in one hour.
2. Unstructured Observation
Observation is informal and flexible, without a fixed plan.
Example: Observing general behavior of people in a market.
3. Participant Observation
The researcher actively participates in the group being studied.
Example: A researcher working in a company to study employee behavior.
4. Non-Participant Observation
The researcher does not participate and only observes from a distance.
Example: Watching students in a classroom without interacting.
5. Controlled Observation
Observation is conducted in a controlled environment (like a lab).
Example: Studying reactions to a product in a test setting.
6. Uncontrolled Observation
Observation takes place in a natural environment without control.
Example: Observing customer behavior in a real shopping mall.
Interview Method – Meaning
The interview method is a technique of collecting data by asking questions directly to
respondents and recording their answers.
Types of Interview Method
1. Structured Interview
Questions are pre-planned and asked in the same order to all respondents.
Example: Survey with fixed questions.
Feature: Easy to compare answers.
2. Unstructured Interview
No fixed questions; the interview is flexible and conversational.
Example: Open discussion with a respondent.
Feature: Provides in-depth information.
3. Semi-Structured Interview
Combination of structured and unstructured methods.
Example: Some fixed questions with freedom to ask additional questions.
Feature: Balanced approach.
4. Personal (Face-to-Face) Interview
Interviewer and respondent interact directly in person.
Example: Door-to-door survey.
Feature: More accurate and detailed responses.
5. Telephone Interview
Interview is conducted over the phone.
Example: Customer feedback calls.
Feature: Quick and cost-effective.
6. Depth Interview
A detailed interview aimed at exploring opinions, feelings, and motivations.
Example: Understanding consumer buying behavior.
Feature: Provides deep insights.
Questionnaire Method
A set of written questions is given to respondents to answer.
Example: Online surveys using forms.
Types of Questionnaire:
a) Structured Questionnaire
• Questions are fixed and pre-planned
• Same for all respondents
Example: Online survey with multiple-choice questions
Use: Easy to analyze and compare data
b) Unstructured Questionnaire
• Questions are open-ended and flexible
• Respondents can answer freely
Example: Asking opinions about a product
Use: Provides detailed insights
c) Closed-ended Questionnaire
• Answers are limited (Yes/No, MCQ, rating scale)
Example: “Are you satisfied? Yes/No”
Use: Quick and easy to analyze
d) Open-ended Questionnaire
• Respondents can give their own answers
Example: “What do you think about the product?”
Use: Gives in-depth information
Schedule Method
Similar to a questionnaire, but it is filled by the researcher/enumerator.
Example: Census data collection.
Types of Schedule:
a) Interview Schedule
• Filled by researcher during an interview
Use: Suitable when respondents cannot fill forms
b) Observation Schedule
• Researcher records data based on observation
Use: Used in behavior studies
Experiment Method
Data is collected through controlled experiments to study cause-and-effect relationships.
Example: Testing the effect of advertising on sales.
Types of Experimental Method:
a) Laboratory Experiment
• Conducted in a controlled environment
Example: Testing product reaction in lab
b) Field Experiment
• Conducted in a real-life situation
Example: Testing advertisement impact in a real market
Secondary Data – Meaning
Secondary data refers to data already collected, processed, and published by others,
especially government agencies, for research or policy purposes.
Researchers use this data to save time, cost, and effort.
Government Portals for Data Collection
1. Ministry of Statistics and Programme Implementation (MOSPI)
MOSPI is the main agency for official statistical data in India.
Data Provided:
• National income (GDP, GNP)
• Consumer Price Index (CPI), inflation
• Employment and unemployment data
• Industrial production (IIP)
• NSSO survey data
How it is used in research:
• Used for economic analysis and policy research
• Helps in trend analysis (growth, inflation, employment)
• Used in academic projects, research papers, and government planning
Example: Studying India’s GDP growth over 10 years using MOSPI data.
2. Reserve Bank of India (RBI)
RBI provides data related to banking, finance, and monetary policy.
Data Provided:
• Interest rates (repo rate, reverse repo)
• Inflation data
• Banking statistics
• Exchange rates
• Money supply
How it is used in research:
• Helps in financial and economic research
• Used to study inflation, monetary policy, and banking trends
• Useful for stock market and investment analysis
Example: Analyzing how interest rate changes affect inflation.
3. Securities and Exchange Board of India (SEBI)
SEBI regulates the stock market and securities market in India.
Data Provided:
• Stock market trends
• Mutual fund data
• IPO details
• Investor statistics
• Corporate disclosures
How it is used in research:
• Helps in capital market and investment research
• Used to analyze stock performance and investor behavior
• Useful for finance students and market analysts
Example: Studying IPO performance using SEBI data.
Secondary Data from Institutional Reports
Reports published by organizations like Centre for Monitoring Indian Economy, Associated
Chambers of Commerce and Industry of India, and Federation of Indian Chambers of Commerce
& Industry are important sources of secondary data.
1. CMIE (Centre for Monitoring Indian Economy)
Data Provided:
• Economic indicators
• Employment/unemployment data
• Business and market trends
• Consumer sentiment
Use in Data Collection:
• Provides real-time and detailed economic data
• Used for statistical analysis and forecasting
Use in Report Writing:
• Helps in adding facts, figures, and charts
• Supports arguments with reliable data
Example: Using CMIE unemployment data in a research paper.
2. ASSOCHAM (Industry Association) Associated Chambers of Commerce and Industry of
India
Data Provided:
• Industry reports
• Sectoral growth analysis
• Policy recommendations
• Business environment insights
Use in Data Collection:
• Useful for industry-specific information
• Helps understand market conditions and challenges
Use in Report Writing:
• Provides case studies and expert opinions
• Strengthens analysis of industries
Example: Using ASSOCHAM reports to study MSME sector growth.
3. FICCI (Business Organization) Federation of Indian Chambers of Commerce & Industry
Data Provided:
• Economic and industrial reports
• Trade and investment data
• Policy insights
• Market research
Use in Data Collection:
• Helps collect business and trade-related data
• Useful for market and economic research
Use in Report Writing:
• Adds credibility and professional insights
• Helps in policy analysis and recommendations
Example: Using FICCI data in a report on foreign investment.
Comparison of CMIE, ASSOCHAM, and FICCI
Centre for Associated Chambers of Federation of Indian
Basis Monitoring Indian Commerce and Industry Chambers of Commerce
Economy of India & Industry
Type of Private economic Business and industry
Industry association
Organization research organization chamber
Economic and Industry development and Business growth, trade,
Main Focus
statistical data policy advocacy and investment
Employment, GDP Sector-specific reports, Trade, investment, policy,
Type of Data
trends, consumer data industry analysis and market reports
Quantitative (numbers,
Nature of Data Qualitative + Quantitative Qualitative + Quantitative
statistics)
Use in Data For detailed economic For industry insights and For business and market
Collection analysis sector studies research
Adds professional
Use in Report Adds accurate Provides case studies and
insights and policy
Writing statistics and graphs expert views
analysis
Unemployment rate MSME or sector growth Foreign investment or
Example Use
study analysis trade report
HYPOTHESIS
A hypothesis is a tentative statement or assumption about the relationship between two or
more variables, which can be tested through research. A hypothesis must be clear, testable,
and based on logic or existing knowledge.
Example:
• “There is a relationship between study time and marks.”
• “Advertising increases sales.”
Characteristics of Hypothesis
• A good hypothesis should have the following characteristics:
• 1. Clear and Precise
The hypothesis should be clearly stated and easy to understand, avoiding ambiguity.
• 2. Testable
It must be capable of being tested through observation or experimentation.
3. Specific
• The hypothesis should be focused and limited in scope, not vague or too broad.
4. Based on Theory or Evidence
It should be supported by existing knowledge, theory, or prior research.
5. Relates to Variables
A hypothesis must show a relationship between two or more variables (independent
and dependent).
6. Logical and Consistent
It should be logically derived and consistent with known facts.
7. Simple
The hypothesis should be simple and not overly complicated, making it easy to test.
• 8. Predictive
It should predict the expected outcome or relationship between variables.
• 9. Verifiable
The results of the hypothesis should be capable of verification or rejection based on
data.
• 10. Feasible
The hypothesis should be practical and possible to test within available time and
resources.
TYPES OF HYPOTHESIS
a) Null hypothesis
b) Alternative hypothesis
1. Null Hypothesis (H₀)
The null hypothesis is a statement that there is no relationship, difference, or effect
between variables.
It assumes that any observed result is due to chance.
Example:
“There is no relationship between study time and marks.”
2. Alternative Hypothesis (H₁ / Hₐ)
The alternative hypothesis is the opposite of the null hypothesis.
It states that there is a relationship, difference, or effect.
Example:
“There is a relationship between study time and marks.”
Concept of Hypothesis Testing
• Research always starts with the null hypothesis (H₀)
• Data is collected and tested using statistical methods
• Based on results:
o If evidence is strong → Reject H₀
o If evidence is weak → Fail to reject H₀
TEST IN HYPOTHESIS
a) Parametric hypothesis
b) Non parametric hypothesis
Meaning of Parametric Data
Parametric data refers to numerical data that follows a normal distribution and meets certain
statistical assumptions.
In simple terms, it is data with known characteristics (parameters) like mean and standard
deviation.
Key Features:
• Data is quantitative (numerical)
• Follows normal distribution (bell-shaped curve)
• Has measurable parameters like:
o Mean
o Standard deviation
• Suitable for parametric tests (like t-test, Z-test)
Examples:
• Heights of students
• Marks obtained in exams
• Income levels
TYPES OF PARAMETRIC TEST
1. t-Test
Meaning
The t-test is used to compare means when the sample size is small (n < 30) and
population variance is unknown.
Assumptions of t-test
• Data is normally distributed
• Sample is randomly selected
• Observations are independent
• Population standard deviation is unknown
Characteristics of t-test
• Used for small sample sizes
• Based on t-distribution
• Compares means between one or two groups
• Types: one-sample, independent, paired
2. Z-Test
Meaning
The Z-test is used to test means when the sample size is large (n > 30) and population
variance is known.
Assumptions of Z-test
• Data follows normal distribution
• Sample size is large
• Population variance is known
• Observations are independent
Characteristics of Z-test
• Based on normal distribution
• Suitable for large samples
• Provides more precise results when variance is known
• Used for mean and proportion testing
NON PARAMETRIC TEST
A non-parametric test is a statistical test that does not assume any specific distribution (like
normal distribution) of the data.
Key Features:
• Used for non-numerical (qualitative) or ordinal data
• Does not require normal distribution
• Suitable for small sample sizes
• Based on ranks or frequencies rather than exact values
Examples of Non-Parametric Tests:
• Chi-square test
• Mann-Whitney U test
• Wilcoxon signed-rank test .
Chi-Square Test (χ²) – Brief Meaning
The Chi-square test is a non-parametric test used to examine the relationship between
categorical variables or to compare observed and expected frequencies.
Assumptions of Chi-Square Test
1. Data in Frequency Form
Data should be in the form of counts (frequencies), not percentages or averages.
2. Independence of Observations
Each observation should be independent of others.
3. Large Sample Size
Sample size should be sufficiently large (generally n > 30).
4. Expected Frequency Condition
Expected frequency in each cell should be at least 5 for valid results.
5. Categorical Data
Data should be nominal or categorical (e.g., gender, preference).
Characteristics of Chi-Square Test
1. Non-Parametric Test
Does not require normal distribution.
2. Based on Frequencies
Works with observed and expected frequencies.
3. Tests Relationship
Used to test association or independence between variables.
4. Flexible Application
Can be used in different fields like marketing, social sciences, etc.
5. Simple to Use
Easy to calculate and interpret.