I'd like to suggest two improvements to the current equivalent test options:
1. Can a Tukey HSD or FDR method be incorporated into the fit model equivalent test to reduce the error rate when looking at lots of factors and levels? Right now the only option is all pairs comparison which can lead to a high number of false positives.
2. Can equivalent tests be incorporated into the response screening platform? Many times we are screen factors for what hasn't caused a change in the response. Also, if we see there hasn't been a change in the response, often the next thing to test is are they equivalent or do we just need more data. Also if the FDR can be used with the equivalence tests in the response screened platform that would be very helpful as well.
Thanks!
Steve