Robust variance estimators for fixed-effect estimates with hierarchical-likelihood |
| |
Authors: | Youngjo Lee |
| |
Institution: | (1) Department of Statistics, Seoul National University, Seoul, 151-742, Korea;(2) Department of Mathematics, Imperial College, London, SW7 2AZ, UK;(3) Division of Mathematical Sciences, Pukyong National University, Busan, 608-737, Korea |
| |
Abstract: | In longitudinal studies, robust sandwich variance estimators are often used, and are especially useful when model assumptions are in doubt. However, the usual sandwich estimator does not allow for models with crossed random effects. The hierarchical likelihood extends the idea of the sandwich estimator to models not currently covered. By simulation studies, we show that the new sandwich estimator is robust against heteroscedastic errors and against misspecification of overdispersion in the y | v component. |
| |
Keywords: | likelihood hierarchical likelihood marginal likelihood robust model misspecification hierarchical generalized linear models |
本文献已被 SpringerLink 等数据库收录! |
|