Hi Craig, Its a little difficult to say without seeing the data but, from what you say, I would have thought a simple Chi Sq might fit your needs.
Good luck!
Dear Craig G Filipkowski, the better alternative to compare a pre-post binary response is using a McNermar's chi-squared test, that would give you a significant advantage. However, it is highly snsitive to large sample sizes;therefore, you should take that into account. This following link might be useful for you:
https://ncss-wpengine.netdna-ssl.com/wp-content/themes/ncss/pdf/Procedures/PASS/Tests_for_Two_Correlated_Proportions-McNemar_Test.pdf
Best,
Omar.
Thank everyone for considering my question.
I looked into Chi Square and was steered away from it toward the McNemar Test. "Although McNemar Test is the most appropriate tool for analyzing pre-post differences in dichotomous items (e.g., “yes” or “no”, “correct” or “incorrect”, etc.), many scholars have noted the inappropriate use of Pearson’s Chisquare Test by researchers, including social scientists and evaluators, for the analysis of related or dependent dichotomous variables" ( Analysis of Paired Dichotomous Data: A Gentle Introduction to the McNemar Test in SPSS, Omolola by A. Adedokun, Purdue University and Wilella D. Burgess, Purdue University)
Unfortunately, I don't meet the assumptions for this test.
Assumptions for the McNemar Test
- You must have one nominal variable with two categories (i.e. dichotomous variables) and one independent variable with two connected groups.
- The two groups in your the dependent variable must be mutually exclusive. ...
- Your sample must be a random sample.
- Badges
- Science topic
- Similar topics
- Statistics
- Survey