Statistics Sampling Methods & Survey Design 2 — Questions and Answers
Question 1: Which type of bias occurs when survey respondents underreport sensitive behaviors because they want to appear socially acceptable?
- Selection bias
- Social desirability bias (Correct answer)
- Non-response bias
- Sampling bias
Correct answer: Social desirability bias
Social desirability bias occurs when respondents give answers they believe are more socially acceptable rather than truthful answers.
Question 2: Non-response bias is most likely to distort survey results when:
- The population is very large
- Survey questions use technical language
- Those who respond differ systematically from those who do not (Correct answer)
- The sample size is too small
Correct answer: Those who respond differ systematically from those who do not
Non-response bias occurs when individuals who choose not to respond differ in meaningful ways from those who do respond, making the obtained sample unrepresentative.
Question 3: A survey question that steers respondents toward a particular answer is classified as:
- A double-barreled question
- An open-ended question
- A demographic question
- A leading question (Correct answer)
Correct answer: A leading question
A leading question is worded in a way that suggests or implies the 'correct' answer, thereby biasing responses.
Question 4: A 5-point Likert scale is primarily designed to measure:
- Physical measurements such as height or weight
- Frequency of observable behavior only
- Demographic characteristics of respondents
- Degree of agreement or disagreement with a statement (Correct answer)
Correct answer: Degree of agreement or disagreement with a statement
Likert scales capture attitudes or opinions by having respondents rate their level of agreement from 'strongly disagree' to 'strongly agree' across ordered response options.
Question 5: What is the primary purpose of conducting a pilot test before deploying a full survey?
- To reduce the required sample size
- To establish the sampling frame
- To identify and correct flaws or ambiguities in the questionnaire (Correct answer)
- To train data analysts in entry procedures
Correct answer: To identify and correct flaws or ambiguities in the questionnaire
A pilot test is a small-scale trial run of the survey that allows researchers to detect confusing questions, technical errors, or other problems before full data collection.
Question 6: How does a census fundamentally differ from a sample survey?
- A census uses only probability sampling methods
- A census is always less expensive to conduct
- A census collects data from every member of the target population (Correct answer)
- A census produces estimates rather than exact measurements
Correct answer: A census collects data from every member of the target population
A census attempts to collect data from all members of the population, while a sample survey collects data from only a selected subset.
Question 7: Why should double-barreled questions be avoided in survey design?
- They inflate the required sample size
- They ask about two separate issues in one question, making responses ambiguous (Correct answer)
- They cannot be processed by standard statistical software
- They are inappropriate for online survey formats
Correct answer: They ask about two separate issues in one question, making responses ambiguous
A double-barreled question combines two distinct issues, so a single answer cannot accurately reflect the respondent's views on both issues separately.
Statistics Sampling Methods & Survey Design 2
Which type of bias occurs when survey respondents underreport sensitive behaviors because they want to appear socially acceptable?