Gilmour's approach to mixed and stochastic restricted ridge predictions in linear mixed models
| Autor: | Özge Kuran, M. Revan Özkale |
|---|---|
| Přispěvatelé: | Çukurova Üniversitesi |
| Rok vydání: | 2016 |
| Předmět: |
Numerical Analysis
Mathematical optimization Algebra and Number Theory Mean squared error 05 social sciences Estimator Mean square error Variance (accounting) Ridge (differential geometry) 01 natural sciences Generalized linear mixed model Data set 010104 statistics & probability Multicollinearity Stochastic restricted ridge predictor 0502 economics and business Discrete Mathematics and Combinatorics Applied mathematics Geometry and Topology 0101 mathematics Linear combination Mixed predictor 050205 econometrics Mathematics |
| Zdroj: | Linear Algebra and its Applications. 508:22-47 |
| ISSN: | 0024-3795 |
| DOI: | 10.1016/j.laa.2016.06.040 |
| Popis: | This article is concerned with the predictions in linear mixed models under stochastic linear restrictions. Mixed and stochastic restricted ridge predictors are introduced by using Gilmour's approach. We also investigate assumptions that the variance parameters are not known under stochastic linear restrictions and attain estimators of variance parameters. Superiorities the linear combinations of the predictors are done in the sense of mean square error matrix criterion. Finally, a hypothetical data set is considered to illustrate the findings. © 2016 Elsevier Inc. FDK-2015-3968 This research was supported by Research Fund of Çukurova University under Project Number FDK-2015-3968 . Appendix A |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect