Learning Objectives
479 words
2 min read
Visual companion
Python
Type and operator map
Python Week 1: the first filter for runtime behavior
View
Revision summary
What this note is really saying
Short form
# Learning Objectives - Design effective surveys and questionnaires - Understand question types and wording best practices - Minimize bias in survey design - Week 1: Research process - Understanding of data collection ## 1. Questionnaire Design **Question Types:** - **Open-ended:** Respondents answer in own words.
Learning Objectives
- Design effective surveys and questionnaires
- Understand question types and wording best practices
- Minimize bias in survey design
- Week 1: Research process
- Understanding of data collection
1. Questionnaire Design
Question Types:
- Open-ended: Respondents answer in own words. Rich insights, but difficult and time-consuming to analyze. Best for exploratory research.
- Closed-ended: Predefined response options. Easy to analyze, but may miss nuances.
- Multiple Choice: Single or multiple select. Most common for surveys.
- Likert Scale: Measure agreement (1=Strongly Disagree to 5=Strongly Agree). Most common for attitude measurement.
- Semantic Differential: Rate between bipolar adjectives (e.g., "Modern : Traditional")
- Ranking: Respondents rank items in order of preference.
- Constant Sum: Respondents allocate 100 points across options.
2. Wording Best Practices
- Simple, clear language - avoid jargon, acronyms
- Avoid leading questions - "Don't you agree that..." biases toward agreement
- Avoid double-barreled questions - "How satisfied are you with quality and price?" is two questions
- Avoid loaded words - "How much do you spend on overpriced coffee?" biases toward negative
- Mutually exclusive and exhaustive options - categories should not overlap and should cover all possibilities
- Balanced scales - equal positive and negative options, include neutral midpoint
3. Survey Bias
| Bias Type | Description | Prevention |
|---|---|---|
| Social Desirability | Respondents give socially acceptable answers | Ensure anonymity, neutral wording |
| Recall Bias | Memory limitations affect accuracy | Limit recall period, use aided recall |
| Order Bias | Question order affects responses | Randomize question order |
| Non-response Bias | Non-respondents differ from respondents | Increase response rate, weight responses |
| Acquiescence Bias | Tendency to agree regardless of content | Include reverse-coded items |
| Central Tendency Bias | Avoid extreme responses | Use forced-choice formats |
Q1: What is a Likert scale and when is it used?Respondents rate agreement on a symmetric scale (1-5 or 1-7). Used for measuring attitudes, opinions, and perceptions. Example: "The product quality is excellent" - Strongly Agree to Strongly Disagree. Q2: What is a double-barreled question? Give an example and correction.Bad: "How satisfied are you with product quality and customer service?" (two issues). Correct: split into two questions - one about quality, one about service. Q3: How do you minimize social desirability bias?Ensure anonymity, use neutral wording, include social desirability scale to detect it, use indirect questioning (e.g., "Some people think X, others think Y. What about you?"), validate with behavioral data. Q4: What is non-response bias and how is it addressed?When survey respondents differ systematically from non-respondents. Solutions: increase response rate (incentives, reminders), compare early vs late respondents, weight responses to match population demographics. Q5: What is the optimal survey length?10-15 minutes maximum for online surveys. Longer surveys increase abandonment rates and reduce response quality. Critical questions first, demographics last. Join Discord PreviousIntroduction to Market ResearchNextSampling Methods