For a one-tailed test of significance, the
A) probability of a Type I error is half as big as for a two-tailed test of significance
B) probability of a Type I error is twice as big as for a two-tailed test of significance
C) $\alpha$ level is twice as big as a two-tailed test
D) none of the other alternatives are correct.

Question

Quizplus · Accepted Answer

In a one-tailed test, the probability of a Type I error (rejecting a true null hypothesis) is not inherently half or twice as big as for a two-tailed test; it depends on how the significance level (alpha) is allocated across the tails of the distribution. The statement about the significance level being twice as big in a one-tailed test compared to a two-tailed test is also incorrect. The significance level is chosen by the researcher and can be the same for both types of tests; it's the allocation that differs, not the total amount.

For a One-Tailed Test of Significance, the A) Probability of a Type

For a One-Tailed Test of Significance, the
A) Probability of a Type