Our World Statistics Day conversations have been a great reminder of how much statistics can inform our lives. Do you have an example of how statistics has made a difference in your life? Share your story with the Community!
Choose Language Hide Translation Bar

Contrasts and parameterization in GLMs

Contrast in Generalized Linear Model doesnt save as script and not accessible in script - so if you set up contrasts, the redo only adds the contrasts button and you have to re-enter all the contrasts. 


It would also be good to be able to specify the reference category. In general the parameterisation should be more controllable or at least obvious.  A lot of users seem unaware that standard least squares and nominal logistic personalities use centered X's (ie mean reference category) whereas Generalized Regression and Generalized Linear Model use the reduced rank approach - ie zero'ing one of the levels like SAS does.  It would be good to have control over that, ie specify which level gets zero'ed or if mean subtraction should be used.  IT would be good to have the same approach and features available in all the regression procedures as far as possible and make everything JSl accessible.

Tracking Number:

Defect ID: