A computationally efficient model selection in the generalized linear mixed model
| Autor: | Takuma Yoshida, Masaru Kanba, Kanta Naito |
|---|---|
| Rok vydání: | 2010 |
| Předmět: |
Statistics and Probability
Mathematical optimization Model selection Generalized linear array model Best linear unbiased prediction Random effects model Generalized linear mixed model Computational Mathematics Spline (mathematics) Statistics Probability and Uncertainty Algorithm Generalized estimating equation Smoothing Mathematics |
| Zdroj: | Computational Statistics. 25:463-484 |
| ISSN: | 1613-9658 0943-4062 |
| DOI: | 10.1007/s00180-010-0187-3 |
| Popis: | This paper is concerned with model selection in spline-based generalized linear mixed model. Exploiting the fact that smoothing parameters can be expressed as the reciprocal ratio of the variances of random effect under the setting of estimation by regularization, we propose a computationally efficient model selection procedure. Applications to some real data sets reveal that the proposed method selects reasonable models and is very fast to implement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink