https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/non-inferiority-analysis/m-p/1451#M84 My question is how to perform a non-inferiority analysis with SAS. Which PROC statements should be use? Is this completed in one step or are there several steps in this type of analysis?<BR /> <BR /> The study is an observational cohort and the methods will be something like this: Our hypothesis is that Drug X 5mg is non-inferior to the same Drug X 10mg, evaluating percent lowering of cholesterol from baseline at 3 months. The cost is almost twice for 10mg than 5mg. <BR /> <BR /> Literature states that Drug X 10mg lower cholesterol 15% from baseline. We feel that if Drug X 5mg lowers cholesterol by 12% this would clinically be non-inferior to the 10mg strength and thus not worth the additional extra cost. There will also be 4-5 covariates to control for potential bias.<BR /> <BR /> Any help would be appreciated. I have search the SAS database and internet without success. Thu, 28 Sep 2006 17:58:04 GMT deleted_user 2006-09-28T17:58:04Z https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/non-inferiority-analysis/m-p/1451#M84 My question is how to perform a non-inferiority analysis with SAS. Which PROC statements should be use? Is this completed in one step or are there several steps in this type of analysis?<BR /> <BR /> The study is an observational cohort and the methods will be something like this: Our hypothesis is that Drug X 5mg is non-inferior to the same Drug X 10mg, evaluating percent lowering of cholesterol from baseline at 3 months. The cost is almost twice for 10mg than 5mg. <BR /> <BR /> Literature states that Drug X 10mg lower cholesterol 15% from baseline. We feel that if Drug X 5mg lowers cholesterol by 12% this would clinically be non-inferior to the 10mg strength and thus not worth the additional extra cost. There will also be 4-5 covariates to control for potential bias.<BR /> <BR /> Any help would be appreciated. I have search the SAS database and internet without success. Thu, 28 Sep 2006 17:58:04 GMT https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/non-inferiority-analysis/m-p/1451#M84 deleted_user 2006-09-28T17:58:04Z https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/non-inferiority-analysis/m-p/1452#M85 I have read that one way to perform non-inferiority (= one-sided) tests is to build two-sided tests with the alpha risk twice the wanted value. Eg : if you want to test non-inferiority with 5% alpha risk, test equality with 10% alpha risk.<BR /> One way to do this with SAS using covariates to stratify analysis is through GLM (fixed effects only) or MIXED (fixed and random effects) procedures.<BR /> <BR /> I am not sure if this way of performing one-sided tests is really exact, or just a workaround with close results to the true method (or something totally insane, by the way, but I'm sure I've read some people doing so).<BR /> <BR /> Olivier Fri, 29 Sep 2006 12:31:34 GMT https://communities.sas.com/t5/SAS-Health-and-Life-Sciences/non-inferiority-analysis/m-p/1452#M85 Olivier 2006-09-29T12:31:34Z