I am comparing three proportions for age categories for categorical variables that have also categories. I used Chi-square test but I found that SPSS gave me a note which is for example: a. 2 cells (33.3%) have expected count less than 5. The minimum expected count is .23.

What is the solution>

  • 1
    $\begingroup$ This answer addressed this kind of issue, though you could also perhaps do a version of an exact test for your 2x3 chi-square. $\endgroup$ – Glen_b Apr 23 '13 at 2:12

One of the assumptions of the chi-square test is that each cell should have an expected count of at least 5. If you have cells with lower expected counts, then they can severely bias your chi-square statistic upward.

In your case, you should run Fisher's Exact Test instead of the traditional chi-square. Fisher's test does not have this assumption. Here is a video showing you how to run the test in SPSS: http://www.youtube.com/watch?v=LynasIsG0xI

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.