I tried to obtain a p-value for a 2 x 2 contingency table in which one row sums to zero. I used PROC FREQ along with the exact fisher option. The following warning was generated: "Row or column sum zero. No statistics computed for this table." For a Fisher's Exact test, the p-value should be calculated as 1 here. Can anyone tell me why SAS won't produce results when it can be calculated? (I am able to get results for other contingency tables without zero sum rows, so my code is correct.)
0 rows are problematic for sure, especially if the row wouldn't even appear in the data set. It means a p-value cannot be calculated, what makes you think the p-value should be 1?
Find a book on statistics that shows how to manually calculate a chi-square test statistic for a 2x2 table.
Do it with some tables that have a row total count of 0.
Then try to find that test statistic in a Chi-square table.
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.