Quantitative Research Methods in Linguistics

DATA COLLECTION
(Detailed Learning Notes – According to Ranjit Kumar)
Data collection is one of the most critical stages in the research process because the
quality of research findings depends directly on the quality of data collected.
According to Ranjit Kumar, data collection refers to the systematic process of
gathering information relevant to the research problem to answer research
questions, test hypotheses, or explore a phenomenon. It is an operational step that
comes after formulating the research problem, designing the study, and selecting
the sample.
Data collection is not merely about gathering information; rather, it is about
collecting accurate, valid, reliable, and relevant data using scientifically tested
methods. Any weakness in data collection leads to biased results and invalid
conclusions, regardless of how advanced the analysis techniques may be.

QUESTIONNAIRE
(According to Ranjit Kumar – Detailed Notes)
Meaning of Questionnaire
• A questionnaire is a written data collection instrument consisting of a list of
carefully structured questions designed to obtain information from
respondents.
• According to Ranjit Kumar, it is one of the most commonly used tools in
social research because it allows standardised data collection from a large
number of people.
• Questionnaires are mainly used in quantitative research but may include
limited qualitative elements through open-ended questions.
Types of Questionnaires
Based on Structure
• Structured Questionnaire
o Contains fixed questions with predetermined response categories.
o Ensures uniformity and is suitable for statistical analysis.
• Semi-Structured Questionnaire
o Includes both closed-ended and open-ended questions.
o Allows limited flexibility and explanation by respondents.

Based on the Administration

• Self-administered Questionnaire
o Respondents read and answer the questions themselves.
o Commonly used in mail surveys and online surveys.
• Interviewer-administered Questionnaire
o Questions are asked by the interviewer and responses are recorded.
o Useful when respondents have low literacy levels.

Types of Questions Used in Questionnaires

Open-Ended Questions
• Allow respondents to answer in their own words.
• Useful for exploring opinions, attitudes, and experiences.
• Difficult to code and analyse due to variability in responses.
Closed-Ended Questions
• Provide fixed response options such as Yes/No, multiple-choice, or rating
scales.
• Facilitate easy coding, comparison, and statistical analysis.
• Limit the depth of responses.
Principles of Questionnaire Construction
• Questions should be simple, clear, and easy to understand.
• Technical and ambiguous terms should be avoided.
• Each question should address only one issue; double-barrelled questions
must be avoided.
• Leading and loaded questions that influence responses should not be
included.
• Questions should be arranged logically, starting with general questions and
moving towards sensitive ones.
• An introductory statement should explain the purpose of the study and
assure confidentiality.

Advantages of the Questionnaire Method

• Economical in terms of time and cost, especially for large samples.
• Enables data collection from respondents spread over wide geographical
areas.
• Minimises interviewer bias due to self-administration.
• Ensures uniformity and standardisation of data.

Limitations of the Questionnaire Method

• Low response rates are common, especially in mail and online
questionnaires.
• Misinterpretation of questions may lead to inaccurate responses.
• Not suitable for illiterate respondents.
• No opportunity for probing or clarification of answers.
SURVEY
(According to Ranjit Kumar – Detailed Notes)
Meaning of Survey
• A survey is a systematic method of collecting information from a sample of
individuals to describe, compare, or explain their characteristics, attitudes, or
behaviour.
• Ranjit Kumar considers a survey a complete research strategy involving
sampling, instrument design, data collection, and analysis.

Types of Surveys
Based on Time Dimension
• Cross-Sectional Survey
o Data are collected at a single point in time.
o Used to study current conditions or characteristics of a population.
• Longitudinal Survey
o Data are collected from the same respondents over different time
periods.
o Useful for studying change and trends.

Based on Purpose
• Descriptive Survey
o Aims to describe the characteristics or distribution of variables in a
population.
• Analytical Survey
o Examines relationships between variables and tests hypotheses.

Survey Process
• Defining clear objectives that guide the entire study.
 • Identifying the target population and selecting an appropriate sample.
• Designing a suitable data collection instrument, usually a questionnaire or
interview schedule.
• Pre-testing the instrument to ensure clarity and reliability.
• Collecting data systematically and ethically.
• Processing, analysing, and interpreting data.

Advantages of Survey Research

• Allows collection of large amounts of data efficiently.
• Facilitates generalisation of findings when probability sampling is used.
• Provides standardised and comparable data.
• Suitable for policy-oriented and large-scale research.

Limitations of Survey Research

• Often provides superficial information lacking depth.
• Subject to sampling errors and non-response bias.
• Quality of results depends heavily on instrument design.
• Relies on respondents’ honesty and accuracy.
INTERVIEW
(According to Ranjit Kumar – Detailed Notes)
Meaning of Interview
• An interview is a data collection method in which information is obtained
through direct verbal interaction between the interviewer and the respondent.
• Ranjit Kumar describes the interview as a flexible and powerful technique,
especially useful for collecting in-depth information.

Types of Interviews
Based on Structure
• Structured Interview
o Uses a fixed set of questions asked in the same order.
o Ensures uniformity and is suitable for quantitative research.
• Semi-Structured Interview
o Uses an interview guide but allows probing and follow-up questions.
o Balances structure and flexibility.
• Unstructured Interview
o Informal and conversational.
o Commonly used in qualitative research to explore experiences in
depth.

Based on Mode of Interaction

• Face-to-Face Interview
o Conducted in person, allowing observation of non-verbal cues.
• Telephone Interview
o Conducted over the phone; cost-effective but limited in depth.
 • Group Interview / Focus Group
o Conducted with multiple participants simultaneously to explore
shared views.

Conducting an Interview
• Establishing rapport with the respondent to build trust.
• Explaining the purpose of the study and ensuring informed consent.
• Asking questions clearly and neutrally without influencing responses.
• Probing when necessary to obtain complete information.
• Recording responses accurately.

Advantages of the Interview Method

• Allows collection of detailed and in-depth data.
• Provides flexibility and opportunity for clarification.
• Suitable for complex and sensitive topics.
• Higher response rate compared to questionnaires.

Limitations of the Interview Method

• Time-consuming and expensive.
• Requires skilled and trained interviewers.
• Susceptible to interviewer bias.
• Data recording and analysis can be difficult.
SAMPLING
(According to Ranjit Kumar – Detailed Notes)
Meaning of Sampling
• Sampling is the process of selecting a small group of individuals from a
larger population in such a way that the selected group represents the
characteristics of the entire population.
• Ranjit Kumar explains that sampling is used because studying the whole
population is often impractical due to constraints of time, cost, and
resources.
• A well-designed sample allows the researcher to draw valid conclusions
about the population.

Key Sampling Terminology

Population
• The population refers to the total group of individuals, objects, or events that
the researcher wants to study.
• It may be finite or infinite, depending on the nature of the research.
Sample
• A sample is a subset of the population selected for actual data collection.
• The quality of research findings depends heavily on how well the sample
represents the population.
Sampling Frame
• A sampling frame is a complete list of all elements of the population from
which the sample is drawn.
• Errors in the sampling frame may result in biased samples.
Sampling Unit
• A sampling unit is the basic element or group of elements selected during the
sampling process, such as individuals, households, or institutions.
Sample Size
• Sample size refers to the number of units selected from the population.
• Ranjit Kumar emphasises that sample size depends on study objectives,
population variability, time, and resources.

Principles of Sampling
• The sample should be representative of the population to ensure valid
generalisation.
• Selection of sample units should be free from researcher bias.
• The sample size should be adequate to capture population variability.
• The sampling method should be appropriate to the research design.

Types of Sampling
Probability Sampling
• In probability sampling, every unit of the population has a known and equal
chance of being selected.
• This method allows statistical generalisation of findings.
Simple Random Sampling
• Each member of the population has an equal chance of selection.
• Selection may be done using random number tables or computer-generated
numbers.
• It reduces selection bias but requires a complete sampling frame.
Systematic Sampling
• The population is listed, and every kth unit is selected after a random start.
• It is easier to implement than simple random sampling but may be biased if
the list has a hidden pattern.
Stratified Sampling
• The population is divided into subgroups or strata based on characteristics
such as age, gender, or education.
• Samples are drawn from each stratum to ensure representation.
• This method increases precision and reduces sampling error.
Cluster Sampling
• The population is divided into clusters, usually based on geographical areas.
• Entire clusters are selected randomly.
• Useful when the population is widely dispersed, though sampling error may
increase.

Non-Probability Sampling
• In non-probability sampling, the probability of selection is unknown.
• This method is commonly used in qualitative research.
Convenience Sampling
• Participants are selected based on ease of access.
• It is quick and inexpensive but lacks representativeness.
Purposive Sampling
• Participants are selected deliberately because they possess specific
characteristics relevant to the study.
• Common in qualitative research where depth is more important than
representativeness.
Quota Sampling
• The population is divided into categories, and a fixed number of units are
selected from each category.
• Selection within categories is non-random.
Snowball Sampling
• Initial respondents refer the researcher to other potential participants.
• Useful for studying hidden or hard-to-reach populations.

Sampling in Qualitative Research

• Qualitative research relies mainly on non-probability sampling.
• Sample size is determined by the concept of saturation, where no new
information emerges.
• The focus is on depth, diversity, and richness of data rather than
representativeness.

VALIDITY AND RELIABILITY

(According to Ranjit Kumar – Detailed Notes)
Validity
Meaning of Validity
• Validity refers to the extent to which a research instrument measures what it
is intended to measure.
• A valid instrument accurately captures the concept under investigation.

Types of Validity
Face Validity
• Refers to whether the instrument appears to measure what it claims to
measure.
• It is based on subjective judgment rather than statistical testing.
Content Validity
• Examines whether the instrument covers all relevant aspects of the concept.
• Achieved through expert review and careful alignment with research
objectives.
Construct Validity
• Determines whether the instrument truly measures a theoretical construct.
• Established by examining relationships between variables.
Concurrent Validity
• Assesses the instrument by comparing it with another established measure
taken at the same time.
Predictive Validity
• Measures the ability of the instrument to predict future outcomes.

Reliability
Meaning of Reliability
• Reliability refers to the consistency and stability of a measurement
instrument.
• A reliable instrument produces the same results when used repeatedly under
similar conditions.

Factors Affecting Reliability

• Ambiguous or poorly worded questions.
• Inconsistent administration procedures.
• Respondent fatigue or lack of motivation.
• Interviewer bias.

Methods of Assessing Reliability

Test–Retest Method
• The same instrument is administered to the same respondents at two
different times.
• Consistency of results indicates reliability.
Split-Half Method
• The instrument is divided into two halves, and responses are compared.
• High correlation indicates reliability.
Inter-Rater Reliability
• Used when multiple observers or interviewers are involved.
• Measures consistency among different raters.

Validity and Reliability in Qualitative Research

• Credibility refers to confidence in the truth of findings.
• Dependability focuses on consistency of the research process.
• Confirmability ensures findings are shaped by respondents, not researcher
bias.
• Transferability refers to applicability of findings to other contexts.

ETHICS OF RESEARCH / DATA ETHICS

(According to Ranjit Kumar – Detailed Notes)
Meaning of Research Ethics
• Research ethics refers to moral principles and guidelines that govern
research activities from planning to reporting.
• Ranjit Kumar emphasises that ethical research protects participants, ensures
integrity, and maintains public trust.

Stakeholders in Research Ethics

• Research participants who provide data.
• Researchers responsible for ethical conduct.
• Sponsoring organisations funding the research.
• Society, which is affected by research outcomes.
Ethical Issues Related to Research Participants
Informed Consent
• Participants must be fully informed about the purpose, procedures, risks, and
benefits of the study.
• Participation should be voluntary.
Voluntary Participation
• Participants should not be coerced or pressured into participating.
• They must have the right to refuse participation.
Confidentiality
• Information provided by participants must be kept confidential.
• Data should not be disclosed without permission.
Anonymity
• Participants’ identities should not be revealed in any form.
Protection from Harm
• Researchers must avoid physical, psychological, social, or emotional harm.
Right to Withdraw
• Participants should be allowed to withdraw from the study at any stage
without penalty.

Ethical Issues Related to the Researcher

• Researchers must avoid bias and personal interest.
• Data should not be fabricated, falsified, or manipulated.
• Findings must be reported honestly and accurately.
Ethical Issues Related to Data
• Data must be stored securely.
• Access to data should be restricted.
• Data should be used only for stated research purposes.

Ethics in Reporting Research

• Results should be presented truthfully without exaggeration.
• Limitations of the study must be acknowledged.
• All sources should be properly cited to avoid plagiarism.