For a population with μ=100, σ=20, and n=25: (a) find P(Xˉ>104), (b) find the value c such that P(Xˉ<c)=0.90.
Example 3
medium
A population has μ=200, σ=40, and we draw samples of size n=64. Find P(Xˉ>210).
Example 4
medium
A population has μ=80, σ=15. For samples of size n=9, find P(78<Xˉ<84).
Example 5
medium
A factory's bolts have μ=10 mm, σ=0.2 mm. A QC inspector samples n=100 bolts. Find P(Xˉ>10.03).
Example 6
medium
A sampling distribution has mean μ=100 and SE 4. Find the 90th percentile of Xˉ (use z0.90=1.28).
Example 7
hard
A population has μ=1000, σ=50. For samples of size n=100, find the value c so that P(Xˉ>c)=0.05 (use z0.95=1.645).
Example 8
hard
A sampling distribution of p^ for p=0.6 and n=150 is approximately normal. Find P(0.55<p^<0.65).
Example 9
hard
Two independent samples of size n1=36 from population A (μA=50, σA=12) and n2=64 from population B (μB=45, σB=16). Find the mean and SE of XˉA−XˉB.
Example 10
challenge
A heavily right-skewed population has μ=5, σ=10. Samples of size n=4 are drawn. Why is it incorrect to claim Xˉ∼N(5,5) here?
Practice Problems
Try each one, then open the solution to compare your method.
Example 1
easy
The standard error of a sample mean is σXˉ=nσ. If σ=10 and n=100, find the standard error. What happens to the SE if n is quadrupled to 400?
Example 2
hard
A population proportion is p=0.40. For samples of size n=100, describe the sampling distribution of p^ and find P(p^>0.45).
Example 3
easy
Does the sampling distribution describe individual data values or a statistic (like the sample mean) across many samples?
Example 4
easy
As sample size n increases, does the sampling distribution of the mean get narrower or wider?
Example 5
easy
A population has σ=10. For samples of size n=25, what is the standard error of the mean?
Example 6
easy
Must you physically take thousands of samples to have a sampling distribution?
Example 7
easy
The central limit theorem says the sampling distribution of the mean approaches what shape as n grows?
Example 8
easy
If the population mean is μ=50, what is the mean of the sampling distribution of xˉ?
Example 9
easy
To halve the standard error of the mean, by what factor must you increase the sample size?
Example 10
easy
True or false: increasing n makes the POPULATION distribution narrower.
Example 11
medium
A population has μ=100, σ=15. For n=9, give the mean and standard error of xˉ.
Example 12
medium
With μ=100,σ=15,n=9 (so SE=5), what is the approximate probability that xˉ exceeds 110? (Use the normal model.)
Example 13
medium
A fair coin is flipped 100 times. The sampling distribution of the proportion of heads has what mean and approximate standard error?
Example 14
medium
Population is heavily skewed. For n=2 the sample mean's distribution is still skewed, but for n=200 it is nearly normal. What principle explains this?
Example 15
medium
Two surveys estimate a mean: one with n=100, one with n=400, same population (σ=20). Compute both standard errors and the ratio.
Example 16
medium
A 95% confidence interval for a mean is xˉ±1.96SE. With xˉ=50, σ=10, n=100, compute the interval.
Example 17
medium
Why can a poll of 1000 people estimate a national proportion within about ±3%, regardless of the country's population size?
Example 18
medium
A population has σ=12. What sample size n gives a standard error of the mean equal to 2?
Example 19
medium
A sample mean xˉ=52 comes from n=64, population σ=16. How many standard errors is xˉ above a hypothesized μ=50?
Example 20
challenge
Derive that the standard error of the sample mean is σ/n from Var(xˉ) for independent observations.
Example 21
challenge
A population is uniform on {1,2,3} (μ=2). List all 9 samples of size 2 (with replacement), compute each sample mean, and verify the mean of the sampling distribution equals 2.
Example 22
challenge
Explain why the sampling distribution of the SAMPLE MAXIMUM does NOT center on the population mean and is not symmetric, contrasting it with the sample mean.
Example 23
easy
A population has σ=16. For samples of size n=64, compute the standard error of the sample mean.
Example 24
easy
If σ=30 and n=9, find the standard error of Xˉ.
Example 25
easy
For a population proportion p=0.5 and n=400, compute SE(p^)=p(1−p)/n.
Example 26
easy
A population has μ=75 and σ=6. For samples of size n=36, give the mean and SE of Xˉ.
Example 27
medium
A population has μ=500, σ=100. For n=25, find P(Xˉ<480).
Example 28
medium
For a population with μ=60 and σ=12, what sample size n gives a standard error of exactly 1.5?
Example 29
medium
A population proportion is p=0.30. For samples of size n=100, find P(p^<0.25).
Example 30
medium
The sampling distribution of Xˉ has mean 50 and SE 2. Within what interval do the middle 95% of sample means lie (use z=1.96)?
Example 31
medium
To cut the SE of Xˉ to one-third of its current value, by what factor must n grow?
Example 32
hard
A teacher's class scores have μ=70, σ=14. She averages n=49 scores. Compute the probability that the average is more than 4 points away from 70.
Example 33
hard
A population has μ=25, σ=5. What is the smallest n such that SE≤0.5?
Example 34
hard
A population is uniform on [0,12] so μ=6 and σ2=12. For n=48, find the SE of the sample mean.
What to focus on
Core idea:A sampling distribution is the spread of a statistic (like the sample mean) over all possible samples of the same size.
Common stuck point:The procedure for sampling distribution is the easy part; the trap is using the population SD σ as the spread of the mean. Asking "Am I describing how a statistic (like xˉ) varies across many samples, rather than how raw values vary?" first is what keeps a correct-looking calculation from being attached to the wrong concept.
Ask yourself:Am I describing how a statistic (like xˉ) varies across many samples, rather than how raw values vary?
Concept recap
The probability distribution of a statistic (such as the sample mean) computed from all possible random samples of the same size drawn from a population.
Imagine many reporters, each polling a different random group of 25 people and announcing the group's average. The sampling distribution is the spread of their headlines. Individual people disagree a lot; the reporters' averages disagree much less, and the more people each reporter asks, the closer the headlines crowd around the truth.