Hello all!
I am a grad student working on my doctoral project and I had a few questions.
I have two questionnaires completed by my participants. These questionnaires are identical and contain both multiple choice (one correct answer) and one Likert style question (with 5 possible responses). I am looking to compare responses between the two questionnaires (I provided education to my participant group and am looking for changes in knowledge and attitudes). I am using Qualtrics and have SPSS.
What would the best way to go about doing this? I have outputs that I can load from both projects into SPSS, but I struggle with figuring out how to combine them so I can compare answers. I also am not sure 100% the best way to analyze my data.
I know very little of statistics (yay for having our statistics class be in the first semester so its fresh in our mind).
THANK YOU for your help :)
You need to enter both data sets into the same SPSS file so that you can compare the pre and post test scores. So read about the SPSS Merge command.
I agree with David, you need to enter data from both questionnaires into the same SPSS file. Furthermore, I would suggest creating a dummy variable to represent the two subgroups (control group and treated group). Thus, participants would be given a value of 0 if they are in the control group and a value of 1 if they belong to the treated group.
This would facilitate the use of crosstabs and chi-square tests (provided that assumptions of this test are met) to see if there are any statistically significant associations between the dummy variable (control group / treated group) and other variables in your questionnaire.
SPSS tutorial to using chi-square test and crosstabs
https://www.spss-tutorials.com/spss-chi-square-independence-test/
https://www.spss-tutorials.com/spss-crosstabs-command/
You need to make the data compatible by changing the Linkert data to multiple choice because it's not possible to directly compare different types of questionnaires. Then you can use a two sample t test to compare means
Likert-scored items are very different from multiple choice items. You should use Cronbach’s alpha to determine whether you can combine your items into a single scale.
- Badges
- Science topic