|
|||||
|
|
Diagnostics for quasi-likelihood nonlinear models |
|
| Authors: | Tian Xia Xuejun Jiang Xueren Wang |
| Affiliation: | 1. School of Mathematics and Statistics, Guizhou University of Finance and Economics, Guiyang, China;2. Department of Mathematics, South University of Science and Technology of China, Shenzhen, China;3. Department of Statistics, Yunnan University, Kunming, China |
| Abstract: | Quasi-likelihood nonlinear models (QLNMs) are an extension of generalized linear model and include a widen class of models as special cases. This article investigates some diagnostic methods in QLNMs. An equivalency between a case-deletion model and a mean-shift outlier model in QLNM is established. Two simulation study and a real dataset are used to illustrate the proposed diagnostic methods. |
| Keywords: | Case-deletion models Cook's distance Diagnostics Quasi-likelihood nonlinear models. |