The data is one time only assessment not before and after and there is a higher response rate among mothers
I would think you would want to use the Chi-square test. http://www.theanalysisfactor.com/difference-between-chi-square-test-and-mcnemar-test/
Since you are not testing before and after chi-square would be correct test.
Because your data are normally distributed (> 30) you can you e.g. Chi square.
i am not aware of a requirement that data be normally distributed to use chi square test for independence. However you can you can use chi square to test of goodness of fit to determine if data comes from normal distribution. As I understand it you would use McNemar if you are testing pre and post intervention results. If you introduce a reading program in a school and you test participants before and after the introduction of the program and determine does the failure rate on test go up go down or stay the same? You would use McNemar to test whether there was a statistically significant difference in the number of participants who failed or passed test pre program compared to number that failed or passed after program introduction. That is how many participants who failed test pre program passed after exposure to program; and how many participants who passed pre program failed after exposure to program. An ordinary chi square is not appropriate for this type of analysis because it should be used with cross section data not with panel or longitudinal data.
- Badges
- Science topic
- Similar topics
- Publishing