One Sample Is Data; Many Possible Samples Form a Sampling Distribution

Three distributions answer different questions

A population distribution describes individual units. A sample distribution describes the units observed in one selected sample. A sampling distribution describes a statistic, such as a sample mean or sample proportion, across repeated samples produced by the same sampling process. Its observations are statistics, not people or measurements.

Why it has a centre and spread

Random sampling makes samples differ by chance, so the statistic varies. For common estimators, the sampling distribution is centred near the population quantity being estimated; this does not mean every sample gives that quantity.


A more informative sampling design or a larger sample often makes the statistic less variable, but sample size alone does not establish representativeness or causal identification.

Hold the process fixed

To imagine repeated samples, keep the target population, selection method, sample size, and statistic fixed. Changing any of these can change the sampling distribution. This introductory idea is separate from choosing a particular confidence interval or hypothesis test.

A researcher repeatedly draws samples of the same size from one population and records the mean from each sample. What does the distribution of recorded means represent?

Choose an answer

Create a free account to get started

Unlock full course notes by signing up

  • Video lessons taught by top educators
  • Practice questions with guided solutions
  • Written review notes for reference
  • Expert answers anytime from course tutors

A population has a fixed mean. A random sample is drawn and its mean is below the population mean. Which statement is justified?

Choose an answer

Create a free account to get started

Unlock full course notes by signing up

  • Video lessons taught by top educators
  • Practice questions with guided solutions
  • Written review notes for reference
  • Expert answers anytime from course tutors

Two teams use the same random-sampling procedure and calculate the same sample mean. Team B uses a larger sample size than Team A. What is the most appropriate expectation about repeated samples?

Choose an answer

Create a free account to get started

Unlock full course notes by signing up

  • Video lessons taught by top educators
  • Practice questions with guided solutions
  • Written review notes for reference
  • Expert answers anytime from course tutors