A researcher is deciding between a z-test and a t-test for a hypothesis test about a population mean. Which criterion determines the appropriate test?
- AWhether the sample size is large enough for the Central Limit Theorem
- BWhether the hypothesis is one-sided or two-sided
- CWhether the population standard deviation is known or unknownCorrect
- DWhether the data are categorical or quantitative
Why C is right
The key distinction is whether the population standard deviation (sigma) is known. If sigma is known, a z-test is used. If sigma is unknown and must be estimated by the sample standard deviation s, a t-test is used. In practice, sigma is rarely known, so t-tests are far more common.
Why the other 3 choices miss
- A
- Incorrect because the choice between z and t is not determined by sample size alone. A large sample lets the Central Limit Theorem justify normality of the sample mean, but a t-test is still appropriate when sigma is unknown (though the t-distribution approaches the normal for large df).
- B
- Incorrect because both z-tests and t-tests can be one-sided or two-sided. The direction of the alternative hypothesis does not determine which test to use.
- D
- Incorrect because both z-tests and t-tests for means require quantitative data. Categorical data would call for proportion tests or chi-square tests.