This preview shows page 1. Sign up to view the full content.
Unformatted text preview: ample is more extreme than the critical value, you reject the null hypothesis; otherwise you retain the null. For computing confidence intervals, you always want the critical value for a two
tailed test. A two
tailed test actually has two critical values – one positive and one negative – but these have the same absolute value (i.e., one is the negative of the other), so for confidence intervals we just think about the positive one. For t
tests, we call this positive critical value tcrit. In a two
tailed test, we split the probability, α, of a Type I error equally between the two tails of the distribution. In oth...
View Full
Document
 Spring '08
 MARTICHUSKI
 Psychology

Click to edit the document details