Discovering Statistics Using IBM SPSS Statistics, 5th Ed. Practice Test

A one-tailed test is used when you have a directional hypothesis and you care about an effect in only one direction, so the entire alpha level is placed in one tail of the sampling distribution. This makes the test more powerful to detect an effect in the specified direction because the critical region is concentrated in that single tail. However, it cannot detect deviations in the opposite direction, which is why it’s not appropriate if you want to consider effects in both directions. This matches the description of testing a directional hypothesis with emphasis on one tail. The other options describe situations that don’t capture the directional focus: a non-directional hypothesis requires a two-tailed test, non-parametric vs parametric relates to distribution assumptions rather than tail direction, and one-tailed tests aren’t limited to variance comparisons.