When performing inference on population means we require that the data are normal and/or that the sample size is large (to use the Central Limit Theorem) so that the sample means have a sampling distribution that is at least approximately normal. The exact same statement (in bold) holds for performing inference on population variance(s) using the χ 2 or F-test.
TOPIC:Normal approximation for the test of variances.
Get Answers For Free
Most questions answered within 1 hours.