Hello everyone, I am working with binary outcomes and many of the proportions in some of my groups are 1; indicating values at the boundary of the parameter space. I am interested in finding some references in dealing with this issue when estimating standard error. I used the delta method to estimate the SE and the method of moment to estimate the dispersion parameter, but got very high estimates of variance for some of the group. Any reference would be very helpful. ******************************************* Antonio Paredes USDA- Center for Veterinary Biologics Biometrics Unit 510 South 17th Street, Suite 104 Ames, IA 50010 (515) 232-5785 [[alternative HTML version deleted]]