---
title: "Social Desirability Bias — AP Stats Definition & Examples"
description: "Social desirability bias happens when people answer survey questions to look good instead of truthfully. A key response bias in AP Stats Topic 3.4 sampling."
canonical: "https://fiveable.me/ap-stats/key-terms/social-desirability-bias"
type: "key-term"
subject: "AP Statistics"
unit: "Unit 1"
---

# Social Desirability Bias — AP Stats Definition & Examples

## Definition

Social desirability bias is a type of response bias in which people answer survey questions in a way that makes them look good (underreporting embarrassing behaviors, overreporting admirable ones) instead of answering truthfully, systematically pushing results away from the true population value.

## What It Is

Social desirability bias is what happens when someone takes your survey but answers like their grandma is reading over their shoulder. Ask people how often they exercise, and they round up. Ask how much they drink, cheat, or skip class, and they round way down. The responses you collect are systematically shifted toward whatever sounds socially acceptable, which is exactly the CED's definition of [bias](/ap-stats/key-terms/bias "fv-autolink") in [Topic 3.4](/ap-stats/unit-3/justifying-claim-based-on-confidence-interval-for-population-proportion/study-guide/YeTpyj6nyq03j0AJO3Bm "fv-autolink"): certain responses are favored over others.

The key word is *systematically*. Random noise in answers tends to cancel out, but social desirability pushes everyone's answers in the same direction. If every college student shaves a few drinks off their self-reported total, your estimate of average alcohol consumption isn't just imprecise, it's wrong, and no amount of extra data fixes it. This is a flaw in how the data is collected, not in who got sampled. Even a perfect simple random sample produces [biased](/ap-stats/unit-3/biased-unbiased-point-estimates/study-guide/eZ5sR9XOkLB1o9KKpMHF "fv-autolink") results if respondents won't tell the truth.

## Why It Matters

Social desirability bias lives in **[Unit 3](/ap-stats/unit-3 "fv-autolink"): Collecting Data, Topic 3.4 (Potential Problems with Sampling)** and directly supports learning objective **3.4.A: Identify potential sources of bias in sampling methods**. The CED's essential knowledge defines bias as the systematic favoring of certain responses, and social desirability is one of the clearest examples of a *response* problem (as opposed to a *sampling* problem like undercoverage). On the exam, you need to read a study description, spot that the questions touch on something sensitive or self-image-related, and name the likely [direction](/ap-stats/key-terms/direction "fv-autolink") of the bias. It also matters far beyond Unit 3, because everything you do in inference later assumes the data wasn't distorted at the collection stage.

## Connections

### Self-reporting bias and underreporting (Unit 3)

Social desirability is the usual *reason* self-reported data goes wrong. When a question asks about drinking, cheating, or studying, people underreport the bad stuff and overreport the good stuff, so self-report studies on sensitive topics almost always carry this bias.

### [Randomized response technique (Unit 3)](/ap-stats/key-terms/randomized-response-technique)

This is the designed antidote. By adding a random element (like a coin flip deciding which question you answer), respondents get plausible deniability, so they're more willing to tell the truth about sensitive behaviors. If you can name the disease, know the cure.

### [Voluntary Response Bias (Unit 3)](/ap-stats/key-terms/voluntary-response-bias)

Both are biases, but they hit different stages. [Voluntary response bias](/ap-stats/key-terms/voluntary-response-bias "fv-autolink") is about *who ends up in the sample* (people with strong opinions opt in). Social desirability bias is about *what people in the sample say*. A study can suffer from both at once, which is exactly what some exam questions test.

### Inference and confidence intervals (Units 6-7)

Here's the brutal part. [Confidence intervals](/ap-stats/key-terms/confidence-interval "fv-autolink") quantify random sampling error, not bias. If everyone underreports their drinking, your interval is precisely centered on the wrong number. Bias from social desirability can't be fixed by a bigger sample, only by better question design.

## On the AP Exam

This shows up almost entirely in multiple-choice and study-design FRQ contexts. A typical MCQ describes a survey on something sensitive (cheating among college students, alcohol consumption, drug use) and asks you to identify the most significant threat to validity. The right move is recognizing that self-reported answers about sensitive behavior get systematically skewed toward socially acceptable responses. Some stems stack biases, like a landline weekday-afternoon poll, where you have to separate undercoverage (who can't be reached) from response bias (how reached people answer). On a free-response question about study design, you'd need to (1) name the bias, (2) explain the *direction* it pushes the estimate (e.g., the true cheating rate is likely higher than reported), and (3) possibly suggest a fix like anonymity or a randomized response technique. Vague answers like 'people might lie' lose points; tie the lying to a specific, systematic direction.

## social desirability bias vs Nonresponse bias

Both crop up with sensitive survey topics, but they're different failures. Nonresponse bias happens when selected people *don't answer at all*, and the non-answerers differ from answerers. Social desirability bias happens when people *do* answer but shade the truth to look good. Quick test: did the person respond? If no, think nonresponse. If yes but dishonestly, think social desirability (a form of response bias).

## Key Takeaways

- Social desirability bias is a response bias where people answer to look good rather than truthfully, like underreporting drinking or overreporting exercise.
- It fits the CED definition of bias because it systematically favors socially acceptable responses over honest ones, shifting estimates in a predictable direction.
- It's a flaw in how responses are given, not in who gets sampled, so even a perfect simple random sample can produce badly biased results.
- Increasing the sample size does not reduce social desirability bias; only fixes like anonymity or the randomized response technique help.
- On the exam, always state the direction of the bias, such as 'the reported cheating rate is likely lower than the true rate.'

## FAQs

### What is social desirability bias in AP Stats?

It's a type of [response bias](/ap-stats/key-terms/response-bias "fv-autolink") where survey respondents answer in a way they think is socially acceptable instead of truthfully, like underreporting alcohol use or cheating. It's tested in Topic 3.4 (Potential Problems with Sampling) under learning objective 3.4.A.

### Is social desirability bias the same as nonresponse bias?

No. Nonresponse bias happens when selected people refuse to answer or can't be reached, and they differ from those who do respond. Social desirability bias happens when people do respond but bend the truth to look good.

### Does taking a bigger sample fix social desirability bias?

No. Bias is systematic, so a larger sample just gives you a more precise estimate of the wrong value. You fix it with better design, like guaranteeing anonymity or using a randomized response technique.

### How is social desirability bias different from self-reporting bias?

Self-reporting bias is the broad category of errors that come from people reporting their own data; social desirability is the specific mechanism where they distort answers to seem more acceptable. On the AP exam, a self-report study about a sensitive topic is your cue for social desirability.

### How do I spot social desirability bias in an AP Stats multiple-choice question?

Look for self-reported data on a sensitive or image-related behavior, like the classic stem about alcohol consumption among college students. The correct answer usually points out that responses are systematically skewed toward what's socially acceptable, making the estimate untrustworthy.

## Related Study Guides

- [1.12 Potential Problems with Sampling](/ap-stats/unit-1/potential-problems-with-sampling/study-guide/nndgaR2dJGCIQs2UsTYa)

## Structured Data

```json
{"@context":"https://schema.org","@graph":[{"@type":"LearningResource","@id":"https://fiveable.me/ap-stats/key-terms/social-desirability-bias#resource","name":"Social Desirability Bias — AP Stats Definition & Examples","url":"https://fiveable.me/ap-stats/key-terms/social-desirability-bias","learningResourceType":"Concept explainer","educationalLevel":"AP® / High School","about":{"@id":"https://fiveable.me/ap-stats/key-terms/social-desirability-bias#term"},"audience":{"@type":"EducationalAudience","educationalRole":"student"},"dateModified":"2026-06-11T05:22:53.747Z","isPartOf":{"@type":"Collection","name":"AP Statistics Key Terms","url":"https://fiveable.me/ap-stats/key-terms"},"publisher":{"@type":"Organization","name":"Fiveable","url":"https://fiveable.me"}},{"@type":"DefinedTerm","@id":"https://fiveable.me/ap-stats/key-terms/social-desirability-bias#term","name":"social desirability bias","description":"Social desirability bias is a type of response bias in which people answer survey questions in a way that makes them look good (underreporting embarrassing behaviors, overreporting admirable ones) instead of answering truthfully, systematically pushing results away from the true population value.","url":"https://fiveable.me/ap-stats/key-terms/social-desirability-bias","inDefinedTermSet":{"@type":"DefinedTermSet","name":"AP Statistics Key Terms","url":"https://fiveable.me/ap-stats/key-terms"}},{"@type":"FAQPage","mainEntity":[{"@type":"Question","name":"What is social desirability bias in AP Stats?","acceptedAnswer":{"@type":"Answer","text":"It's a type of [response bias](/ap-stats/key-terms/response-bias \"fv-autolink\") where survey respondents answer in a way they think is socially acceptable instead of truthfully, like underreporting alcohol use or cheating. It's tested in Topic 3.4 (Potential Problems with Sampling) under learning objective 3.4.A."}},{"@type":"Question","name":"Is social desirability bias the same as nonresponse bias?","acceptedAnswer":{"@type":"Answer","text":"No. Nonresponse bias happens when selected people refuse to answer or can't be reached, and they differ from those who do respond. Social desirability bias happens when people do respond but bend the truth to look good."}},{"@type":"Question","name":"Does taking a bigger sample fix social desirability bias?","acceptedAnswer":{"@type":"Answer","text":"No. Bias is systematic, so a larger sample just gives you a more precise estimate of the wrong value. You fix it with better design, like guaranteeing anonymity or using a randomized response technique."}},{"@type":"Question","name":"How is social desirability bias different from self-reporting bias?","acceptedAnswer":{"@type":"Answer","text":"Self-reporting bias is the broad category of errors that come from people reporting their own data; social desirability is the specific mechanism where they distort answers to seem more acceptable. On the AP exam, a self-report study about a sensitive topic is your cue for social desirability."}},{"@type":"Question","name":"How do I spot social desirability bias in an AP Stats multiple-choice question?","acceptedAnswer":{"@type":"Answer","text":"Look for self-reported data on a sensitive or image-related behavior, like the classic stem about alcohol consumption among college students. The correct answer usually points out that responses are systematically skewed toward what's socially acceptable, making the estimate untrustworthy."}}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"AP Statistics","item":"https://fiveable.me/ap-stats"},{"@type":"ListItem","position":2,"name":"Key Terms","item":"https://fiveable.me/ap-stats/key-terms"},{"@type":"ListItem","position":3,"name":"Unit 1","item":"https://fiveable.me/ap-stats/unit-1"},{"@type":"ListItem","position":4,"name":"social desirability bias"}]}]}
```