|
|||||
|
|
Robust influence diagnostics for generalized linear models with continuous responses |
|
| Authors: | Li‐Chu Chien Tsung‐Shan Tsou |
| Institution: | 1. Division of Biostatistics and Bioinformatics, Institute of Population Health Sciences, National Health Research Institutes, , Zhunan, Miaoli County, Taiwan;2. Institute of Statistics, National Central University, , Jhongli City, Taoyuan County, Taiwan;3. Institute of Systems Biology and Bioinformatics, National Central University, , Jhongli City, Taoyuan County, Taiwan;4. Center for Biotechnology and Biomedical Engineering, National Central University, , Jhongli City, Taoyuan County, Taiwan |
| Abstract: | This article introduces two parametric robust diagnostic methods for detecting influential observations in the setting of generalized linear models with continuous responses. The legitimacy of the two proposed methods requires no knowledge of the true underlying distributions so long as their second moments exist. The performance of the two proposed influence diagnostic tools is investigated through limited simulation studies and the analyses of an illustration. |
| Keywords: | robust influence diagnostic method generalized linear model influential observation robust normal regression |