---
title: "Bootstrapping — AP Stats Definition & Exam Guide"
description: "Bootstrapping resamples your one sample (with replacement) to estimate a statistic's sampling distribution. It powered the 2019 AP Stats investigative task."
canonical: "https://fiveable.me/ap-stats/key-terms/bootstrapping"
type: "key-term"
subject: "AP Statistics"
unit: "Unit 5"
---

# Bootstrapping — AP Stats Definition & Exam Guide

## Definition

Bootstrapping is a resampling method that estimates the sampling distribution of a statistic by repeatedly drawing samples with replacement from the original sample and computing the statistic for each resample, letting you study sample-to-sample variation when you only have one sample.

## What It Is

Bootstrapping answers an annoying real-world problem. A sampling distribution is supposed to show how a [statistic](/ap-stats/key-terms/statistic "fv-autolink") varies across many samples from the population, but in practice you usually get exactly one sample. Bootstrapping treats your sample as a stand-in for the population. You draw a new sample of the same size from it **with replacement** (so the same value can show up multiple times), calculate your statistic, and repeat that hundreds or thousands of times. The pile of recalculated statistics is called the bootstrap distribution, and it approximates how much your statistic would bounce around from sample to sample.

The big idea behind it is exactly the question Topic 5.1 opens with. Why is my sample not like yours? Statistics vary from sample to sample, and that [variation](/ap-stats/unit-5 "fv-autolink") may be random or not (the essential knowledge under [AP Stats](/ap-stats "fv-autolink") 5.1.A). Bootstrapping is a hands-on way to *see* that random variation without needing the whole population or a formula.

## Why It Matters

Bootstrapping lives in Unit 5 (Sampling [Distributions](/ap-stats/unit-1/describing-distribution-quantitative-variable/study-guide/4dcjgkWfLu7tmS9bDtjP "fv-autolink")) under Topic 5.1, supporting learning objective AP Stats 5.1.A, which asks you to identify questions raised by variation in statistics for samples from the same [population](/ap-stats/key-terms/population "fv-autolink"). Bootstrapping is the simulation version of that idea. Instead of memorizing that statistics vary, you generate the variation yourself by resampling. It's not a named formula on the AP formula sheet, and that's exactly why it matters. The exam's investigative task loves handing you an unfamiliar method built from familiar logic, and bootstrapping is the classic example. If you understand why resampling with replacement mimics drawing fresh samples from a population, you understand what a sampling distribution actually is, not just how to plug into the standard error formulas later in Unit 5.

## Connections

### [Bootstrap Distribution (Unit 5)](/ap-stats/key-terms/bootstrap-distribution)

Bootstrapping is the process; the [bootstrap distribution](/ap-stats/key-terms/bootstrap-distribution "fv-autolink") is the result. After you resample with replacement many times and record the statistic each time, the distribution of those recorded statistics is your estimate of the real sampling distribution.

### Sample Statistic vs. Population Parameter (Unit 5)

Bootstrapping flips the usual setup. Normally a statistic estimates a [parameter](/ap-stats/key-terms/parameter "fv-autolink") from one sample. In bootstrapping, your sample plays the role of the population, so the original sample's statistic acts like the 'parameter' your resampled statistics scatter around.

### Mean and Sample Standard Deviation (Unit 1)

Every resample needs a statistic computed from it, and that's [Unit 1](/ap-stats/unit-1 "fv-autolink") work. The spread of your bootstrap distribution (measured with a standard deviation) estimates how much your statistic varies, which is the whole point of a standard error.

## On the AP Exam

Bootstrapping is not a named requirement in the CED, so you won't be asked to define it cold. Instead, it shows up as a novel method you have to reason through. The famous example is the 2019 FRQ Q6, the investigative task, where Emma had a random sample of 50 one-bedroom apartment rental prices and the problem walked through repeatedly resampling from that sample to build a simulated distribution of a statistic. You weren't graded on knowing the word 'bootstrap.' You were graded on applying sampling distribution logic, like reading the simulated distribution, describing variability, and judging whether a statistic is a good estimator. Multiple-choice questions in this territory ask you to identify the data-gathering or simulation method described and what question it can answer. Your job is to recognize 'sample with replacement from the original sample, recompute the statistic, repeat' as a way to approximate sampling variability.

## bootstrapping vs Sampling distribution

A sampling distribution is the theoretical distribution of a statistic across all possible samples drawn from the population. A bootstrap distribution approximates it using only one sample, by resampling from that sample with replacement. Sampling distribution is the ideal; bootstrapping is the workaround when you can't keep sampling the population.

## Key Takeaways

- Bootstrapping estimates a statistic's sampling distribution by repeatedly resampling, with replacement, from the one sample you actually have.
- Sampling with replacement is essential, because it lets each resample differ from the original even though both have the same size.
- The bootstrap distribution of recalculated statistics shows you how much your statistic varies from sample to sample, which is the core idea of AP Stats 5.1.A.
- Bootstrapping treats your sample as a stand-in for the population, so it only works well if the original sample is random and representative.
- The AP exam tests bootstrapping as an unfamiliar-method reasoning task, like the 2019 investigative task about apartment rental prices, not as a vocabulary word.

## FAQs

### What is bootstrapping in AP Stats?

Bootstrapping is a resampling method where you repeatedly draw samples with replacement from your original sample, compute a statistic each time, and use the resulting distribution to estimate how that statistic varies from sample to sample.

### Is bootstrapping actually on the AP Statistics exam?

Not as a required term, but yes as a reasoning task. The 2019 FRQ Q6 investigative task had you work with repeated resampling from a sample of 50 rental prices, which is bootstrapping in everything but name. You need the logic, not the vocabulary.

### How is a bootstrap distribution different from a sampling distribution?

A sampling distribution comes from taking many samples from the actual population, which you usually can't do. A bootstrap distribution approximates it by resampling from your single sample with replacement. One is the theoretical target, the other is a practical estimate of it.

### Why does bootstrapping sample with replacement?

Without replacement, every resample of size n from a sample of size n would just be the original sample reshuffled, and every statistic would be identical. Replacement lets values repeat or drop out, so each resample differs and you can see variability.

### Does bootstrapping fix a bad sample?

No. Bootstrapping assumes your original sample represents the population, so resampling a biased sample just gives you a precise picture of a biased estimate. Garbage in, garbage out still applies.

## Related Study Guides

- [Legacy AP Statistics Topic: Sampling Variability Introduction](/ap-stats/unit-5/why-is-my-sample-not-like-yours/study-guide/Mrybsi6gfieJDqF2LNju)

## Structured Data

```json
{"@context":"https://schema.org","@graph":[{"@type":"LearningResource","@id":"https://fiveable.me/ap-stats/key-terms/bootstrapping#resource","name":"Bootstrapping — AP Stats Definition & Exam Guide","url":"https://fiveable.me/ap-stats/key-terms/bootstrapping","learningResourceType":"Concept explainer","educationalLevel":"AP® / High School","about":{"@id":"https://fiveable.me/ap-stats/key-terms/bootstrapping#term"},"audience":{"@type":"EducationalAudience","educationalRole":"student"},"dateModified":"2026-06-11T05:22:54.013Z","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/bootstrapping#term","name":"bootstrapping","description":"Bootstrapping is a resampling method that estimates the sampling distribution of a statistic by repeatedly drawing samples with replacement from the original sample and computing the statistic for each resample, letting you study sample-to-sample variation when you only have one sample.","url":"https://fiveable.me/ap-stats/key-terms/bootstrapping","inDefinedTermSet":{"@type":"DefinedTermSet","name":"AP Statistics Key Terms","url":"https://fiveable.me/ap-stats/key-terms"}},{"@type":"FAQPage","mainEntity":[{"@type":"Question","name":"What is bootstrapping in AP Stats?","acceptedAnswer":{"@type":"Answer","text":"Bootstrapping is a resampling method where you repeatedly draw samples with replacement from your original sample, compute a statistic each time, and use the resulting distribution to estimate how that statistic varies from sample to sample."}},{"@type":"Question","name":"Is bootstrapping actually on the AP Statistics exam?","acceptedAnswer":{"@type":"Answer","text":"Not as a required term, but yes as a reasoning task. The 2019 FRQ Q6 investigative task had you work with repeated resampling from a sample of 50 rental prices, which is bootstrapping in everything but name. You need the logic, not the vocabulary."}},{"@type":"Question","name":"How is a bootstrap distribution different from a sampling distribution?","acceptedAnswer":{"@type":"Answer","text":"A sampling distribution comes from taking many samples from the actual population, which you usually can't do. A bootstrap distribution approximates it by resampling from your single sample with replacement. One is the theoretical target, the other is a practical estimate of it."}},{"@type":"Question","name":"Why does bootstrapping sample with replacement?","acceptedAnswer":{"@type":"Answer","text":"Without replacement, every resample of size n from a sample of size n would just be the original sample reshuffled, and every statistic would be identical. Replacement lets values repeat or drop out, so each resample differs and you can see variability."}},{"@type":"Question","name":"Does bootstrapping fix a bad sample?","acceptedAnswer":{"@type":"Answer","text":"No. Bootstrapping assumes your original sample represents the population, so resampling a biased sample just gives you a precise picture of a biased estimate. Garbage in, garbage out still applies."}}]},{"@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 5","item":"https://fiveable.me/ap-stats/unit-5"},{"@type":"ListItem","position":4,"name":"bootstrapping"}]}]}
```