In: Statistics and Probability
Consider using a one-tailed as well as a two-tailed test of a null hypothesis regard- ing an estimated regression coefficient. For the same significance level, which test is more stringent? In other words, for which test does rejection of the null hypothesis automatically imply rejection in the other test as well, but not vice versa? Explain.
Ans - If the two tailed hypothesis is rejected then one tailed automatically rejected at tha same level
for example - If we have Alpha=. 05
then in two tailed hypothesis, critical value in z test is 1.96
and z statistics = 2.6
then we reject Ho because Z statistics> greater than Z critical
if the same hypothesis is tested with one tailed then z critical values =1.645
then, here we see that z statistics here also greater than z critical then we reject the hypothesis