| Feature | Closed-ended | Open-ended |
|---|---|---|
| Data Type | Quantitative | Qualitative |
| Analysis | Statistical / Automated | Manual Coding / Thematic |
| Respondent Effort | Low | High |
| Flexibility | Limited to options | Unlimited expression |
Identify Question Flaws: In exams, you are often asked to critique a survey. Look for 'double-barreled' questions that ask two things at once, making it impossible to know which part the respondent is answering.
Check for Bias: Always evaluate if a question is 'leading' the respondent toward a specific answer. A neutral question should not use emotionally charged language or suggest a 'correct' viewpoint.
The Importance of the Pilot: Always mention Pilot Testing as a way to verify the clarity of questions and the time required for completion before the full-scale study begins.
Social Desirability Bias: Respondents may answer in a way they think is socially acceptable rather than being honest. This is common in topics involving health, ethics, or illegal activities.
Recall Bias: Relying on a respondent's memory for events that happened long ago can lead to inaccurate data. Questionnaires should focus on recent events or use 'anchors' to help memory.
The 'Middle-Box' Tendency: On Likert scales, respondents often choose the neutral middle option to avoid taking a stand. Researchers sometimes use an even-numbered scale (forced choice) to prevent this.
Statistical Analysis: Data from closed-ended questions is typically analyzed using descriptive statistics (mean, median, mode) and inferential statistics (t-tests, chi-square) to find patterns and correlations.
Triangulation: Questionnaires are often used alongside interviews or observations to validate findings. If a questionnaire shows a trend, an interview can explain why that trend exists.
