Research Methods: Questionnaires, Interviews and Observation
Choosing a Research Method
Sociologists have a range of methods available when collecting primary data. The choice of method is never arbitrary — it is shaped by the research question, the population being studied, practical constraints such as time and cost, ethical considerations, and the theoretical perspective of the researcher. An interactionist studying how teachers construct expectations of pupils would choose a very different method from a positivist measuring national rates of educational achievement. This lesson covers the three main families of methods: questionnaires, interviews and observation.
Questionnaires
A questionnaire is a standardised set of written questions distributed to a sample. Closed questions offer a fixed set of responses (e.g. yes/no, tick all that apply, a rating scale from 1 to 5) and produce quantitative data. Open questions allow respondents to answer in their own words, producing qualitative data.
Strengths of questionnaires: They can reach large samples quickly and cheaply, especially via online distribution. They allow statistical analysis and comparison across groups. Responses are anonymous, which may encourage honest answers on sensitive topics. They are standardised — all respondents answer the same questions — which improves reliability (the study could be replicated and compared). Weaknesses: Response rates can be low, introducing bias if non-respondents differ systematically from respondents. Closed questions impose the researcher’s categories on respondents’ experience. Questionnaires cannot probe or follow up unexpected answers, and they assume all respondents interpret questions in the same way — which may not be the case across different social groups.
Questionnaires are high in reliability and allow statistical comparison across large samples, making them the preferred method for positivist sociologists. Their weakness is low validity — closed questions may not capture how respondents really think or feel.
Interviews
A sociological interview involves a researcher asking questions directly of participants. The degree of structure varies significantly:
- Structured interview: the interviewer follows a fixed schedule of questions in the same order and wording for every participant, much like a spoken questionnaire. This produces quantitative data that is easy to compare across respondents. The weakness is limited depth — no follow-up is possible.
- Unstructured interview: the interviewer begins with an opening topic and allows the conversation to develop naturally. This resembles an informal conversation and can reveal unexpected themes and rich qualitative data. The weakness is that it is time-consuming, difficult to compare across participants, and the results may reflect the relationship between interviewer and respondent (interviewer effect).
- Semi-structured interview: uses a list of key themes but allows the interviewer to probe and follow up. It combines some comparability with depth.
A critical evaluative point: interviews can be affected by the interviewer effect — respondents may give socially desirable answers rather than honest ones, particularly on sensitive topics such as domestic violence, drug use or attitudes to ethnicity. They may adjust their answers depending on the perceived social characteristics of the interviewer (age, gender, ethnicity, accent).
A sociologist wants to investigate the experiences of women who have left violent relationships. A structured interview would be inappropriate: the fixed questions might miss the aspects of the experience that matter most to the participants, and the formal tone could feel clinical and discouraging for respondents discussing trauma. An unstructured interview would allow participants to lead the conversation, reveal their own frameworks of meaning, and build the rapport needed to discuss sensitive experiences honestly. The weakness is that the resulting data would be harder to compare systematically across participants. The researcher might use semi-structured interviews as a compromise: key themes guide the conversation but the interviewer follows up where the participant goes.
Observation: Participant and Non-Participant
Observation involves directly watching people in their natural social setting. There are two main variants:
Non-participant observation — the researcher watches without taking part. Strengths: the observer remains detached, reducing the risk of “going native” (over-identifying with the group). Weaknesses: the presence of an observer may alter participants’ behaviour (the Hawthorne effect); the observer cannot access the meanings and motivations behind the behaviour they see.
Participant observation — the researcher joins the group and participates in their daily life, either overtly (with the group’s knowledge) or covertly (without it). Willis’s 1977 study Learning to Labour is a classic example: Willis spent time with twelve working-class boys (whom he called “the lads”) in their school and outside it, observing how they actively resisted school culture and produced their own counter-school subculture. This gave him qualitative depth that no survey could have produced. The strength of participant observation is validity — the data reflects real behaviour in natural settings. The weakness is that it is time-consuming, the researcher may influence the group (reactivity), and covert observation raises serious ethical concerns about deception.
The distinction between reliability (can the study be repeated with the same results?) and validity (does the study measure what it claims to, reflecting real behaviour?) is central to methods evaluation. Questionnaires tend to score well on reliability; participant observation tends to score well on validity. Many methods trade one off against the other.
Mixed Methods and Triangulation
Rather than choosing one method, many sociologists use a mixed methods approach. For example, a study of gender inequality in the workplace might begin with a large-scale questionnaire to identify patterns (quantitative), then follow up with in-depth interviews with selected participants to explore the meanings behind those patterns (qualitative). This strategy is sometimes called triangulation — using multiple methods or data sources so that the weaknesses of one approach are compensated for by the strengths of another.
A critical mistake on methods questions is listing generic strengths and weaknesses without applying them to the specific research context. “Observation is time-consuming” is a generic point. “Participant observation would be particularly problematic for a study of gang violence because gaining covert access to a criminal network would put the researcher at significant personal risk and would require sustained deception, raising serious ethical concerns about informed consent” is an applied point, which is what these questions ask for. The spec explicitly requires students to “identify and explain the advantages and disadvantages, strengths and weaknesses of a particular method for a specific area of research.” Every evaluation point must be anchored to the research topic.