I am currently researching two groups on their willingness with 5 questions on a 7-point Likert-scale.

My hypotheses are:

$H_0$: There is no difference in willingness between the two groups.

$H_1$: There is a difference in willingness between the two groups.

I used a Man-Whitney test to determine if there is a significant difference for each of the questions between the groups. And only for one of the questions there was a significant difference. Does this mean I can reject my $H_0$ hypothesis, or do I need one hypothesis for each question?


You can only reject the null hypothesis for the question which was significantly different. If all questions are measuring the same dimension of willingness, then perhaps you can aggregate the responses across all 5 questions (add up the responses for each participant's 5 questions then divide by 5) and run a 2 group comparison using the MWU. A group comparison of an aggregated willingness score would test the null hypothesis across all questions.

  • $\begingroup$ When testing multiple items separately, you may want to use an alpha correction. Otherwise, w/ enough tests you are bound to find something significant by chance. The simplest strategy is to divide alpha by the number of test, thus you call something significant if p < .01 here. $\endgroup$ – gung - Reinstate Monica Dec 19 '14 at 23:40

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.