How to find a confidence interval for a population mean
A sample mean gives us one estimate of a population mean. A confidence interval gives that estimate some room for sampling variation. Let’s build intervals with a known and an unknown population standard deviation so we can see what changes.
Start with the sample mean and a margin of error
The sample mean is our point estimate of the population mean . A confidence interval goes the same distance on either side of that estimate. That distance is the margin of error, which is a critical value times the standard error.
A confidence procedure would produce intervals that contain the fixed population mean in about of repeated samples, when the conditions for the procedure hold. The sample and the interval can change each time. The population mean stays fixed.
Use a z interval when the population standard deviation is known
For independent observations from a normal population with known standard deviation , use the standard normal critical value . The same method gives an approximation if the sample mean is approximately normal. With observations, the standard error is .
For a two-sided interval, choose so the central area is the confidence level. The remaining area, , is split equally between the two tails. For confidence, each tail has area . The cutoffs are and .
Find a 90% z interval for mean bottle fill
Suppose bottle fills are normally distributed, with known standard deviation ounce. A random sample of bottles has a mean fill of ounces. We’ll treat the fills as independent. For confidence, each tail has area , so .
So we’re 90% confident that the population mean fill is between about 15.84 and 16.16 ounces. The interval estimates the mean fill across the population of bottles.
Plan the sample size for a fixed margin of error
When planning a interval with known , start with a target margin of error . Since must be at most , solve for the smallest sample size that meets that requirement.
For confidence, . If and , the calculation gives
Round up to so the margin of error is at most under the assumed model.
Use a t interval when the population standard deviation is unknown
If we estimate with the sample standard deviation , the estimated standard error is . Use a critical value with degrees of freedom. The one-sample interval is exact for independent observations from a normal population. For a small sample we need a reasonable normal model, while larger samples can give a good approximation for a wider range of population shapes.
As the degrees of freedom increase, the critical value gets closer to the critical value. We can still use the interval for a large sample when is unknown.
Find a 99% t interval for a mean exam score
Suppose students are selected at random, their scores can be treated as independent, and a normal model for scores is reasonable. The sample has mean and standard deviation . We have degrees of freedom. For confidence, the upper tail area is , which gives .
We’re 99% confident that the population mean score is between about 80.82 and 92.58 points. The confidence level describes how often this method captures the true mean over repeated samples.