A new class of strategies for mixed model selection, which includes linear and generalized linear mixed models using a statistical fence, or barrier, to carefully eliminate incorrect models.

This research was partially supported by research grants NIH R01-GM085205, NSF DMS 0806076, NSF SES 1122399,NSF DMS 0402824, and NSF DMS 1121794

Jiming Jiang

        University of California-Davis         Department of Statistics

J. Sunil Rao

                     University of Miami                       Division of Biostatistics

Visitors to this Site:

Website Designed By: Elijah Robert

Thuan Ngyuen

Oregon Health and Science University  Division of Biostatistics