Non-inferiority. Farrington–Manning test extended to the Mantel–Haenszel type adjustment.

[AndreyMyslivets]

Dear Sirs and Madams!

I have faced with the following planned study:

The primary variable is the proportion of respondents.

The hypothesis is non-inferiority.

At the same time, stratification is planned for 2 factors, and this should be taken into account in the analysis of the primary variable.

Is it real to perform the procedure "the Farrington–Manning test extended to the Mantel–Haenszel type adjustment" in SAS?

How to use Cochran-Mantel-Haenzel weights for the stratum weights in the calculation of the CI (this method corresponds to the expanded Farrington-Manning test (Farrington CP and Manning G 1990) for stratified designs with Cochran-Mantel-Haenzel weights)?

The data is attached.

Thanks in advance!

Andrey

[Jack2012]

I am facing the same question as well, have anybody has solution?