I have two questionnaires I want to correlate. One questionnaire has all the questions with answers from 1 to 5, I can make a mean out of that without issue. The second one has 3 parts: questions with 5 possible answers, 3 possible answers and 2 possible answer. I assume making a mean out of that is not good. Can I produce a mean variable for all of them somehow? Is there another way?

Thank you.

P.S. I work with SPSS

2. ## Re: Question about questionnaires

Originally Posted by Lev.alkin
One questionnaire has all the questions with answers from 1 to 5, I can make a mean out of that without issue.
Are you sure that it is unproblematic to take the mean of ordinal data? Usually, our minds perceive the difference between four and five as greater than the difference between three and four. Therefore the arithmetic mean of ordinal data in questionnaires are in general not without issue.

3. ## Re: Question about questionnaires

These questionnaires are supposed to be analyzed like that. It should be equal weight.

 Tweet

#### Posting Permissions

• You may not post new threads
• You may not post replies
• You may not post attachments
• You may not edit your posts