Sign in to save

Bookmark this page so you can find it later.

Sign in to save

Bookmark this page so you can find it later.

Sampling Distributions and CLT cheat sheet - grade 11-12

Click image to open full size

Statistics Grade 11-12

Sampling Distributions and CLT Cheat Sheet

A printable reference covering sampling distributions, standard error, the Central Limit Theorem, sample means, and sample proportions for grades 11-12.

TopicsProbabilityData AnalysisStudy GuideStatistics
Download PNG

Related Tools

Related Labs

Related Worksheets

Related Infographics

Study as Flashcards

Sampling distributions describe how a statistic, such as a sample mean or sample proportion, varies from sample to sample. Students need this cheat sheet because inference in statistics depends on knowing the center, spread, and shape of these distributions. The Central Limit Theorem helps predict when sampling distributions are approximately normal.

This makes confidence intervals and hypothesis tests possible even when population data are not perfectly normal.

The most important ideas are that unbiased statistics are centered at the true population parameter and that larger samples produce less variability. For sample means, the standard error is σn\frac{\sigma}{\sqrt{n}} when the population standard deviation is known. For sample proportions, the standard error is p(1−p)n\sqrt{\frac{p(1-p)}{n}}.

The Central Limit Theorem says that for large enough nn, the sampling distribution of xˉ\bar{x} is approximately normal with mean μ\mu and standard deviation σn\frac{\sigma}{\sqrt{n}}.

Key Facts

  • A sampling distribution is the distribution of a statistic, such as xˉ\bar{x} or p^\hat{p}, from all possible samples of the same size nn.
  • The sampling distribution of the sample mean has mean μxˉ=μ\mu_{\bar{x}} = \mu when samples are random and independent.
  • The standard error of the sample mean is σxˉ=σn\sigma_{\bar{x}} = \frac{\sigma}{\sqrt{n}} when the population standard deviation σ\sigma is known.
  • The Central Limit Theorem states that if nn is large, then xˉ\bar{x} is approximately normal with mean μ\mu and standard deviation σn\frac{\sigma}{\sqrt{n}}.
  • For a sample proportion, the sampling distribution has mean μp^=p\mu_{\hat{p}} = p and standard error σp^=p(1−p)n\sigma_{\hat{p}} = \sqrt{\frac{p(1-p)}{n}}.
  • A sample proportion is approximately normal when np≥10np \ge 10 and n(1−p)≥10n(1-p) \ge 10.
  • A sample mean is approximately normal if the population is normal or if the sample size is large, often n≥30n \ge 30.
  • Increasing sample size reduces standard error because both σn\frac{\sigma}{\sqrt{n}} and p(1−p)n\sqrt{\frac{p(1-p)}{n}} get smaller as nn increases.

Vocabulary

Sampling distribution
A sampling distribution is the distribution of a statistic calculated from many random samples of the same size.
Statistic
A statistic is a number calculated from a sample, such as xˉ\bar{x} or p^\hat{p}.
Parameter
A parameter is a number that describes an entire population, such as μ\mu, σ\sigma, or pp.
Standard error
Standard error is the standard deviation of a sampling distribution and measures how much a statistic varies from sample to sample.
Central Limit Theorem
The Central Limit Theorem states that sampling distributions of means become approximately normal as sample size increases.
Unbiased estimator
An unbiased estimator is a statistic whose sampling distribution is centered at the true population parameter.

Common Mistakes to Avoid

  • Confusing σ\sigma with σxˉ\sigma_{\bar{x}} is wrong because σ\sigma describes individual population values, while σxˉ=σn\sigma_{\bar{x}} = \frac{\sigma}{\sqrt{n}} describes sample means.
  • Using the Central Limit Theorem for very small skewed samples is wrong because xˉ\bar{x} may not be approximately normal unless the population is normal or nn is large enough.
  • Forgetting to divide by n\sqrt{n} in standard error is wrong because variability decreases with sample size, so σxˉ\sigma_{\bar{x}} is not equal to σ\sigma.
  • Checking only np≥10np \ge 10 for proportions is wrong because the normal approximation also requires n(1−p)≥10n(1-p) \ge 10.
  • Treating one sample statistic as a sampling distribution is wrong because a sampling distribution describes the pattern of a statistic over many possible samples.

Practice Questions

  1. 1 A population has mean μ=80\mu = 80 and standard deviation σ=12\sigma = 12. For samples of size n=36n = 36, find μxˉ\mu_{\bar{x}} and σxˉ\sigma_{\bar{x}}.
  2. 2 A population proportion is p=0.40p = 0.40 and the sample size is n=100n = 100. Find the mean and standard error of p^\hat{p}.
  3. 3 A population has μ=50\mu = 50 and σ=10\sigma = 10. For samples of size n=25n = 25, find the zz-score for a sample mean of xˉ=54\bar{x} = 54.
  4. 4 Explain why increasing the sample size makes a sample mean more reliable as an estimate of the population mean.

Understanding Sampling Distributions and CLT

A sampling distribution is easiest to understand as a thought experiment. Imagine taking many random samples from the same population, each with the same number of people or objects. Calculate one statistic from every sample, then record the results.

Individual samples will disagree because chance affects which observations are selected. Some sample means fall high, some fall low. The pattern made by all those calculated means shows the uncertainty built into the sampling process.

In real work, researchers usually collect only one sample. The thought experiment tells them how much trust to place in that one result.

It is important to separate the spread of the original data from the spread of sample statistics. A class may have widely different test scores, yet the averages from groups of thirty students tend to be much closer together. The standard deviation describes variation among individual values.

Standard error describes variation among estimates from repeated samples. Students often confuse these because both measure spread.

A small standard error does not mean every person is similar. It means a statistic such as an average is likely to be fairly stable across samples of the chosen size.

The Central Limit Theorem is useful because many populations are not shaped like a bell curve. Waiting times can be strongly right skewed. Income data often have a few extremely large values.

Measurements may have unusual clusters. When random independent observations are averaged, the averaging process reduces the effect of ordinary random ups and downs. With a sufficiently large sample, the distribution of the averages becomes close enough to normal for probability methods to work.

The sample size of thirty is a common classroom guideline, not a guarantee. Very skewed populations or populations with extreme outliers can need much larger samples. If the population itself is normal, sample means follow a normal pattern even for small samples.

Random selection matters as much as sample size. A large sample taken only from volunteers can give a precise estimate of the wrong population value. Independence matters too.

If one selected person influences the next selection, the usual standard error calculations can be unreliable. When sampling without replacement, a common check is that the sample is no more than ten percent of the population. For proportions, count expected successes and expected failures before using a normal model.

Polls, product quality checks, medical studies, and school surveys all use these ideas. Pay attention to what parameter is being estimated, whether the statistic is a mean or a proportion, and whether the conditions for a normal approximation are actually met. Those checks prevent a calculation from looking correct while giving a misleading conclusion.