A researcher can't just run multiple t tests when the independent variable has more than two levels because as more statistical tests are run:
A) it becomes harder and harder to reject the null hypothesis.
B) the probability of making a Type I error in one of the tests increases.
C) degrees of freedom are lost.
D) the probability of making a Type III error in one of the tests increases.

Question

Quizplus · Accepted Answer

Running multiple t tests increases the likelihood of making a Type I error (rejecting the null hypothesis when it's actually true) because the overall chance of making at least one Type I error increases with the number of tests being run. To avoid this issue, a researcher should use a statistical test that takes into account multiple comparisons, such as ANOVA (analysis of variance), which compares group means while controlling for the overall Type I error rate.

A Researcher Can't Just Run Multiple T Tests When the Independent