topic Multiple choice pre/post test comparison in Statistical Procedures

Multiple choice pre/post test comparison

alexita — Tue, 26 Jan 2010 19:36:12 GMT

Hello,

I am analyzing the results of pre/post surveys and when I coded in the responses, I assigned '1' for correct and '0' for incorrect. However, with some of these questions, there were four possible responses (a,b,c,d). My question is: In analyzing this data (doing a Pearsons or Fisher) how do I account for the 4 choice possibility with these specific questions? I have been able to figure out to weight singular observations but not how to weight variables... I'm not even sure that I'm on the right track with this.

Does anyone have any suggestions??

Thank you!!!!!!!!
Alexandra

Re: Multiple choice pre/post test comparison

Dale — Wed, 27 Jan 2010 21:18:50 GMT

Are the response levels ordinal or just categorical? What sort of hypothesis/hypotheses do you have about the pre/post survey responses with regard to these multiple choice variables? For that matter, do you have hypotheses to test or do you simply want to present descriptive statistics?

As you can see, there is a lot of information that you have left out. I may not have asked all of the questions that would need to be addressed, but the questions that I have asked should get you started toward describing more fully just what it is that you need.