首页 | 本学科首页   官方微博 | 高级检索  
     检索      


When can random effects be treated as fixed effects for computing a test statistic for a linear hypothesis?
Authors:Justus F Seely  El-Houssainy Rady
Institution:1. Department of Statistics , Oregon State University , Corvallis, Oregon;2. Institute of Statistical Studies and Research , Cairo University , Cairo, Egypt
Abstract:The Idea of treating the random effects as fixed for constructing a test for a linear hypothesis (of fixed effects) in a mixed linear model is considered in this paper. The paper examines when such a test statistic can be computed and what are its distributional properties with respect to the actual mixed model.
Keywords:mixed linear model  fixed effects  linear hypothesis  F-test
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号