Central Limit Theorem Examples: 44 Problems with Answers
Worked examples of Central Limit Theorem to try before you open each solution, then practice
problems with answers.
Worked Examples
Example 1
medium
A highly skewed population (times between bus arrivals) has μ=15 min and σ=8 min. For samples of n=64, describe the shape, mean, and SD of the sampling distribution of Xˉ, and find P(Xˉ<14).
A fair die (μ=3.5, σ=1.71) is rolled n=100 times. By CLT, find the approximate probability that the sample mean is between 3.3 and 3.7.
Example 3
medium
A population has μ=70, σ=12. For n=36, find P(Xˉ>73).
Example 4
medium
A coin is flipped n=100 times. Let Xˉ be the sample proportion of heads. Use CLT to find P(Xˉ>0.55).
Example 5
medium
A population has μ=120, σ=30. For n=36, what is the probability Xˉ falls within 5 of μ?
Example 6
medium
A casino's roulette bet has expected loss μ=−0.05 per dollar and σ=1. After n=10000 bets, find P(Xˉ>0) (player profits on average).
Example 7
hard
An exponential population (e.g., wait times) has μ=5, σ=5. For n=100, find P(Xˉ>5.5).
Example 8
hard
A factory's items have μ=200g, σ=10g. A box contains n=25 items. Find P(total weight>5050) using CLT.
Example 9
hard
A population has μ=80, σ=16. Find the 95th percentile of Xˉ for n=64 (use z0.95=1.645).
Example 10
challenge
n=100 i.i.d. samples come from a Bernoulli(p=0.02) population. Why might the CLT-based normal approximation for p^ be poor here, and what's the alternative?
Practice Problems
Try each one, then open the solution to compare your method.
Example 1
easy
State the Central Limit Theorem in your own words, including what conditions must be met and what it tells us about the shape of the sampling distribution.
Example 2
hard
Customers arrive at a store with mean μ=2 per minute, σ=1.5 per minute (Poisson-like). For 36-minute observation windows, find P(total arrivals>80) using CLT.
Example 3
easy
A population has standard deviation σ=20. For samples of size n=100, what is the standard deviation of the sample mean (the standard error)?
Example 4
easy
A population has mean μ=50. What is the mean of the sampling distribution of the sample mean for samples of size n=36?
Example 5
easy
According to the common rule of thumb, what minimum sample size makes the CLT a reasonable approximation for the sample mean?
Example 6
easy
True or false: the CLT applies to the sampling distribution of the sample mean, not to individual observations.
Example 7
easy
A population has σ=12. For n=9, find the standard error of the mean.
Example 8
easy
A skewed population has μ=8. The sampling distribution of xˉ for large n is approximately what shape?
Example 9
easy
If the sample size increases from n=25 to n=100 (a factor of 4), the standard error of the mean changes by what factor?
Example 10
easy
A population has σ=15, n=25. Express the standard error of xˉ.
Example 11
medium
A population has μ=70, σ=10. For n=25, find P(xˉ>74). Use P(Z>2)≈0.0228.
Example 12
medium
A population has μ=100, σ=16. For n=64, find P(xˉ<96). Use P(Z<−2)≈0.0228.
Example 13
medium
Heights have μ=168 cm, σ=8 cm. For a sample of n=16, what is the SD of the sample mean?
Example 14
medium
A sample mean is needed to have standard error ≤1 when σ=6. What is the smallest n?
Example 15
medium
A die roll (uniform 1 to 6) has mean 3.5. The average of n=49 rolls is approximately normal centered at what value?
Example 16
medium
A population has σ=25. To cut the standard error of the mean from 5 to 2.5, by what factor must n increase?
Example 17
medium
Package weights have μ=500 g, σ=30 g. For n=36, find the standard error of the mean.
Example 18
medium
A population has μ=40, σ=9. For n=81, find P(xˉ>41). Use P(Z>1)≈0.1587.
Example 19
challenge
A population has mean μ and SD σ. For a sample of size n, by what factor does the standard error of the total (sum) S=∑xi grow relative to the standard error of one observation, in terms of n?
Example 20
challenge
A population is strongly right-skewed with μ=5, σ=5. Explain why n=30 may be insufficient for the normal approximation of xˉ, and state what determines the needed n.
Example 21
challenge
Two independent samples are averaged. Sample A: nA=100, σA=30. Sample B: nB=50, σB=20. Which sample mean has the smaller standard error, and what are the two values?
Example 22
medium
A population has σ=14, n=49. Find the standard error of the sample mean.
Example 23
easy
A population has σ=18. For samples of size n=81, what is the SE of Xˉ?
Example 24
easy
A population has μ=200, σ=50. For n=100, find the SE.
Example 25
easy
For σ=6 and n=36, find the SE of Xˉ.
Example 26
easy
A skewed population has μ=5, σ=4. For n=100, what shape does the sampling distribution of Xˉ have?
Example 27
medium
A truck-weight population has μ=5000 lb, σ=800 lb. For n=64 trucks, find P(Xˉ<4900).
Example 28
medium
For a population with σ=20, what sample size makes the SE equal to 4?
Example 29
medium
The CLT says the SUM S=X1+X2+⋯+Xn is approximately normal with mean nμ and SD σn. If μ=4, σ=2, n=25, find the SD of S.
Example 30
medium
A population has σ=10. By what factor does the SE of Xˉ change when n goes from 25 to 400?
Example 31
hard
A population has μ=50, σ=10. To guarantee SE ≤0.5, what minimum n is needed?
Example 32
hard
For μ=100, σ=25, n=25, find P(95<Xˉ<110).
Example 33
hard
A population proportion is p=0.20. Verify CLT applies for n=50 and find P(p^>0.25).
Example 34
medium
For μ=60, σ=8, n=16, find the SE.
What to focus on
Core idea:The CLT says sample means become approximately normal for large n, whatever the population's shape.
Common stuck point:The procedure for central limit theorem is the easy part; the trap is claiming the raw data becomes normal. Asking "Am I claiming the distribution of a sample MEAN is approximately normal because the sample is large?" first is what keeps a correct-looking calculation from being attached to the wrong concept.
Ask yourself:Am I claiming the distribution of a sample MEAN is approximately normal because the sample is large?
Concept recap
For sufficiently large sample size (n≥30 as a rule of thumb), the sampling distribution of the sample mean is approximately normal with mean μ and standard deviation nσ, regardless of the shape of the population distribution.
Averaging works like mixing paint from randomly chosen cans. One can might be any shade, but a mix of 30 cans almost always comes out a middling color, since an extreme mix needs nearly every can to be extreme. The mixes cluster around the average shade whatever the cans looked like; mixes of only two or three cans still vary a lot.