Fundamentals of Research Methodology in Economics - Notes

Methods of Data Collection

• The task of data collection begins after a research

  problem has been defined and research design/plan

  chalked out. While deciding about the method of data

  collection, the researcher should keep in mind two

  types of data viz., primary and secondary

• Two main types of data:

  • Primary Data: Collected for the first time, original in nature.

  • Secondary Data: Pre-collected by others, often compiled from existing sources.

Collection of Primary Data

• Primary data collection methods differ from secondary methods, focusing more on original collection. Common methods include:

  • Observation Method

  • Interview Method

  • Questionnaires

  • Schedules

Observation Method

• Utilizes direct observation by the researcher, noting behavior without respondent input.

• Observation becomes a scientific tool and the method

  of data collection for the researcher, when it serves

  formulated research purpose, is systematically planned

  and recorded and is subjected to checks and controls

  on validity and reliability

  • Scientific vs. Casual Observation: Scientific observation is systematic and controls for validity.

  • Example: In consumer behavior studies, observing product choices instead of asking the consumer directly.

Advantages of Observation Method

1. Eliminates Subjective Bias: Direct data collection reduces inaccuracies often found in surveys or interviews due to dishonesty or memory issues.

   • Example: Observing food choices in restaurants yields more reliable data than self-reported surveys.

2. Captures Real-Time Behavior: Records actions as they happen, free from the influence of past experiences.

3. Independent of Willingness: The method does not depend on respondents' consent to participate or provide accurate answers.

   In interviews and surveys, some respondents may refuse to

   participate or provide false answers. In contrast, observation

4. Suitable for Non-Verbal Subjects: Effective for individuals unable to articulate responses (e.g., children or non-native speakers).

   Some individuals cannot accurately express their feelings due

   to age, disability, or language barriers. Observation is useful in

   such cases

Limitations of Observation Method

1. Costly: Requires trained staff and advanced tools; can become expensive over time.

   • Example: Monitoring customer behavior through surveillance systems.

2. Limited Data Scope: Only captures observable actions, not underlying motivations.Observation only records visible behavior, not inner

   thoughts, motivations, or reasons behind actions

3. External Interference: Uncontrolled factors (e.g., weather) can distort findings. External elements like weather, crowd density, or unexpected

   events can impact observations and distort findings.

4. Access Restrictions: Certain groups are inherently difficult to observe due to privacy issues. Certain groups are difficult to observe due to privacy concerns, security restrictions, or social settings

Structured vs. Unstructured Observation

• Structured Observation: Structured observation refers to a carefully planned and defined method of observing and recording data. It is systematic, and every aspect, including what should be observed, how the data should be recorded, and under what conditions the

  observation should occur, is predefined.

• Unstructured Observation: Unstructured observation occurs when there is no predefined plan for what to observe or how to record

  the data No specific plan; free-form observation focuses on relevant phenomena as they arise.

  Aspect	Structured Observation	Unstructured Observation

  Meaning

  Observation using a pre-defined plan, checklist, or framework.

  Observation done freely without a strict plan; more open and flexible.

  Planning

  Highly planned (what to observe is decided in advance).

  No rigid plan; observations evolve during the study.

  Data Type

  Quantitative (countable, measurable data).

  Qualitative (descriptive, detailed notes).

  Example

  Watching how many times students raise their hand in class.

  Observing overall classroom atmosphere and students’ engagement without specific counts.

  Suitable For

  Studies needing measurable data or comparisons.

  Exploratory research to generate ideas or understand complex behavior.

Participant vs. Non-Participant Observation

• Participant Observation: In participant observation, the researcher actively

  engages with the group they are studying, becoming a

  part of the group to some degree. Researcher actively engages with the group being studied, gaining richer insights.

• Non-Participant Observation: In non-participant observation, the researcher does not become involved with the group being studied.

  They observe the group from the outside, without

  interacting or influencing the group's behavior Researcher observes from a distance without influencing the group behavior.

  Aspect	Participant Observation	Non-Participant Observation
  Meaning	Researcher becomes part of the group being studied.	Researcher remains detached and just observes.
  Interaction	Direct interaction with the group.	No or very little interaction with the group.
  Advantage	Deeper insights into behavior and emotions.	Objective, unbiased observations.
  Example	A researcher joins a local protest group to study activism.	A researcher sits at the back of a protest and just observes behaviors.
  Suitable For	Studying hidden behaviors, emotions, group dynamics.	Studying visible behaviors, routines, general trends.

Controlled vs. Uncontrolled Observation

• Controlled Observation: In controlled observation, the researcher manipulates the

  environment or uses pre-arranged plans and instruments to

  systematically collect data. Researcher manages the environment to gather specific data under experimental conditions.

• Uncontrolled Observation: Uncontrolled observation takes place in natural settings

  without any pre-arranged experimental conditions or precision

  instruments Data collected in natural settings without manipulation, capturing authentic behavior.

  Aspect	Controlled Observation	Uncontrolled Observation
  Meaning	Observation happens in a planned, artificial, or experimental setting.	Observation happens in a natural, real-world environment.
  Environment	Researcher controls variables and conditions.	Researcher has no control over variables; just observes naturally.
  Advantage	More accuracy and repeatability.	More realistic, true-to-life data.
  Example	Observing customer reactions in a simulated shopping mall built for research.	Observing customers in a real shopping mall.
  Suitable For	Laboratory experiments, psychology tests.	Ethnographic studies, field research.

Errors in Measurement

• Various errors can jeopardize measurement accuracy:

  • Respondent Errors: Inaccurate reporting due to reluctance, ignorance, or situational influences.

  • Situational Errors: Environmental factors affecting responses.

  • Interviewer Errors: Mistakes made by the researcher during questioning or data recording.

  • Instrument Errors: Flaws in measurement tools affecting data reliability.

Tests of Sound Measurement

1. Validity

• The extent to which a measurement accurately captures what it intends.

  • Content Validity: Agreement among experts that a measurement covers all relevant aspects of a construct.

  • Criterion-Related Validity: Effectiveness of a measure in predicting outcomes based on comparisons to established criteria.

  • Construct Validity: Relationship between the measure and theoretical concepts it aims to measure.

2. Reliability

• Consistency of measurements over time; focuses on repeated results from a stable tool.

3. Practicality

• Feasibility of using a measurement tool in practical settings; considers cost, convenience, and clarity.

Interview Method of Data Collection

• Involves verbal communication for data gathering, via personal or telephone conversations. The interview method of data collection involves

  gathering information through direct verbal

  communication between an interviewer and a

  respondent.

  • The responses are also communicated orally, which

  makes this method different from written surveys or

  observation methods.

  • This approach can be implemented in two primary

  ways: personal interviews and telephone interviews

Personal Interviews

• Face-to-face interaction, suitable for detailed and nuanced data collection but time-consuming.A personal interview is a face-to-face interaction

  between an interviewer and the respondent. It allows

  for direct communication, where the interviewer asks

  questions to collect the required information.

  – Example: A market researcher visits households to

  ask people about their product preferences and

  purchasing habits.

  – This method is suitable for intensive studies where

  accurate and detailed data is needed. However, it

  may not be feasible for large-scale research due to

  time and resource constraints

Telephone Interviews

• Quick and cost-effective, with advantages such as ease of recall and higher response rates, but limited by time constraints. This method of collecting

  information consists in contacting respondents on

  telephone itself. It is not a very widely used method,

  but plays important part in industrial surveys,

  particularly in developed regions.

  • The chief merits of such a system are:

  • 1. It is more flexible in comparison to mailing

  method.

  • 2. It is faster than other methods i.e., a quick way of

  obtaining information.

  • 3. It is cheaper than personal interviewing method;

  here the cost per response is relatively low

Questionnaires

• A self-administered method of gathering information through prepared questions.This method of data collection is quite popular,

  particularly in case of big enquiries. It is being adopted

  by private individuals, research workers, private and

  public organisations and even by governments.

  • In this method, a set of questions is prepared in

  advance and mailed to the respondents, who are

  expected to fill out their answers and send the

  questionnaire back. This approach is particularly useful

  for collecting data from a large number of people who

  may be geographically dispersed.

Advantages

1. Cost-effective for larger populations.

2. Avoids interviewer bias.

3. Provides sufficient response time for thoughtful answers.

4. Can reach hard-to-contact individuals.

5. Allows large sample sizes.

Disadvantages

1. Low response rate can skew data.

2. Requires literate and cooperative respondents.

3. Loss of control after distribution.

4. Inflexible once sent out; hard to adjust questions.

5. Ambiguous responses can flub data accuracy.

Collection of Data through Schedules

• Similar to questionnaires, but completed by trained enumerators.

Differences from Questionnaires

• Schedules are filled out through direct interaction while questionnaires are mailed for self-completion.

Measurement Scales in Research

• Important for categorizing and interpreting data correctly according to its nature.

Types of Scales

1. Nominal Scale: Categories without inherent order or quantitative value; used for counting frequencies.

2. Ordinal Scale: Categories with a meaningful order but unequal intervals.

3. Interval Scale: Equal intervals without a true zero point; allows for meaningful addition and subtraction.

4. Ratio Scale: All properties of nominal, ordinal, and interval scales, distinguished by a true zero point, allowing all arithmetic operations including multiplication and division.

Summary

• Scientific data collection methods are crucial in Economics research to ensure reliability and validity. Understanding various methods, their advantages, limitations, and types is essential for effective research design and implementation.