Unit 5: Sampling Distributions

AP Statistics: 52 practice questions with detailed explanations.

Unit Study Guide

Executive Summary

A statistic varies from sample to sample. Its sampling distribution tells us how close estimates land to the parameter.

Parameters vs statistics

A parameter describes a population (fixed); a statistic describes a sample (varies). Sampling distributions are built from many samples of the same size. Bias = center off the parameter; variability = spread across samples. Good estimators are unbiased with low variability.

Proportions

The sampling distribution of p-hat has mean p and standard deviation √(p(1-p)/n). It's approximately normal when np and n(1-p) are both at least 10 (large counts) and the sample is at most 10% of the population.

Means

The sampling distribution of x-bar has mean μ and standard deviation σ / √(n) — averaging reduces spread. If the population is normal, x-bar is normal for any n; otherwise the Central Limit Theorem says x-bar is approximately normal for n at least 30.

Key ideas

Bigger n → smaller standard error (scales as 1/√(n)). To halve the standard error, quadruple n. Sample mean and sample proportion are unbiased; the sample range underestimates the population range.

Exam traps

Standard error shrinks with n, but the population doesn't change. The CLT is about sample MEANS, not individual values. Bias comes from the estimator's center, not its spread.

Top 5 Concepts to Master

  1. 1Distinguish parameters from statistics.
  2. 2Compute standard errors for p-hat and x-bar.
  3. 3State the CLT and its conditions.
  4. 4Judge estimators by bias and variability.

Key Terms & Definitions

Practice with Flashcards
Parameter

Fixed number describing a population.

Statistic

Number computed from a sample.

Sampling distribution

Distribution of a statistic over many samples.

Standard error

Standard deviation of a sampling distribution.

Unbiased estimator

Sampling mean equals the parameter.

Central Limit Theorem

x-bar is approximately normal for large n.

Large counts condition

np ≥ 10 and n(1-p) ≥ 10.

Common Misconceptions: Exam Traps

A bigger sample changes the parameter.

Correct: The parameter is fixed; the estimate gets more precise.

The CLT makes individual data normal.

Correct: It makes the distribution of sample means normal.

Doubling n halves the standard error.

Correct: It divides by √(2); quadrupling halves it.

Bias disappears with more data.

Correct: Bias is structural; only better design removes it.

Question Bank Breakdown

By difficulty

easy 21medium 29hard 2

By topic

Sampling Distribution of a Sample Mean 14Sampling Distributions 12Biased and Unbiased Estimators 10Sampling Distribution of a Sample Proportion 9The Central Limit Theorem 7

All Questions in this Unit