The Central Limit Theorem (College Board AP® Statistics): Revision Note

Mark Curtis

Written by: Mark Curtis

Reviewed by: Dan Finlay

Updated on

Central Limit theorem

What is the Central Limit theorem?

  • The Central Limit theorem states that

    • if a population is not normally distributed

      • but has a population mean μ

      • and population standard deviation σ

    • and a large enough random sample of size n is taken

      • where n30

      • and sample values are independent of each other

    • then the sampling distribution for sample means:

      • is approximately normally distributed

      • with mean μ

      • and standard deviation σn

  • The approximation gets better as the sample size, n, increases

Examiner Tips and Tricks

The mean, μ, and the standard deviation, σn, are given in the exam under 'Sampling distributions for means', in the row called 'For one population'.

In your exam, you just need to state that the sample size is large enough. n30 is not a rule that you are expected to learn.

How do I use the Central Limit theorem?

  • You can use the Central Limit theorem to calculate probabilities involving sample means, x¯, taken from any population distribution

    • including population distributions that

      • are heavily skewed

      • are completely uniform (horizontal)

      • have multiple peaks

    • as long as the sample size is at least 30

Skewed, uniform or multi-peaked population distributions.
Skewed, uniform or multi-peaked population distributions
  • Probabilities using the Central Limit theorem will be estimates

    • as sample means follow an approximate normal distribution

    • Its standardized z-score is approximately x¯μσn

      • μ and σ are usually given in the question

  • If either μ or σ are not given in the question then you may have to find them from the context or from other parts of the question

Examiner Tips and Tricks

In Central Limit theorem questions, always show that you have checked the sample size satisfies n30!

What happens if the population is normally distributed?

  • If the population is normally distributed, then the Central Limit theorem is not needed

    • The sampling distribution for sample means will be exactly normally distributed

      • not approximately

    • It will have a mean of μand a standard deviation of σn, where n is any sample size

      • not just n30

Worked Example

The number of minutes that it takes to wait for a bus at a particular bus stop is distributed evenly between 0 minutes and 50 minutes. Any particular number of minutes that a person is required to wait between these two times is equally likely to occur. The standard deviation of waiting times is 14.4 minutes.

(a) If a person travels on the bus from this bus stop 40 times, estimate the probability that the mean time they have to wait exceeds 26 minutes.

(b) If, instead, the person travels on the bus from this bus stop 15 times, explain whether or not the method used in part (a) is still appropriate.

Answer:

(a)

This a probability question about the mean of a sample (a sample of 40 waiting times)

Waiting times are not normally distributed (they are evenly distributed)

This means the Central Limit theorem is required (check n30)

The sample size is n=40 which satisfies n30

The Central Limit theorem states that sample means follow an approximate normal distribution with mean μ and standard deviation σn

The question gives σ but not μ, so work this out from the context

The mean waiting time between 0 and 50 minutes, if all times are equally likely, is 25 minutes

μ=25

Use the standard deviation of 14.4 minutes and n=40 to find σn

σn=14.440=2.2768399...

Find the probability the sample mean exceeds 26, P(X>26)

The z-score is

26252.2768399...=0.4392...

Using 0.44 from the tables gives 0.6700 as the probability of being less than z

Subtract this from 1 to find the probability of exceeding z

1 - 0.6700

The probability that the mean waiting time exceeds 26 minutes is approximately 0.3300

(b)

The method used in part (a) involves the Central Limit theorem

The Central Limit theorem requires that n30

However the sample size here is n=15 which is less than 30

So the method in part (a) is not appropriate

Unlock more, it's free!

Join the 100,000+ Students that ❤️ Save My Exams

the (exam) results speak for themselves:

Build on this topic

Mark Curtis

Author: Mark Curtis

Expertise: Maths Content Creator

Mark graduated twice from the University of Oxford: once in 2009 with a First in Mathematics, then again in 2013 with a PhD (DPhil) in Mathematics. He has had nine successful years as a secondary school teacher, specialising in A-Level Further Maths and running extension classes for Oxbridge Maths applicants. Alongside his teaching, he has written five internal textbooks, introduced new spiralling school curriculums and trained other Maths teachers through outreach programmes.

Dan Finlay

Reviewer: Dan Finlay

Expertise: Portfolio Lead

Dan graduated from the University of Oxford with a First class degree in mathematics. As well as teaching maths for over 8 years, Dan has marked a range of exams for Edexcel, tutored students and taught A Level Accounting. Dan has a keen interest in statistics and probability and their real-life applications.