Generalized varying-coefficient single-index model |
| |
| Authors: | Weihua Zhao Jicai Liu Zhensheng Huang Yazhao Lv |
| |
| Affiliation: | 1. School of Science, NanTong University, NanTong 226007, P.R. China;2. School of Finance and Statistics, East China Normal University, Shanghai 200241, P.R. China;3. School of Science, NanJing University of Science and Technology, NanJing 210094, P.R. China;4. Institute of Operational Research and Cybernetics, Hangzhou Dianzi University, Hangzhou 310018, P.R. China |
| |
| Abstract: | In this paper, the generalized varying-coefficient single-index model is discussed based on penalized likelihood. All the unknown functions are fitted by penalized spline. The estimates of the unknown parameters and the unknown coefficient functions are obtained and the estimation approach is rapid and computationally stable. Under some mild conditions, the consistency and the asymptotic normality of these resulting estimators are given. Two simulation studies are carried out to illustrate the performance of the estimates. An application of the model to the Hong Kong environmental data further demonstrates the potential of the proposed modelling procedures. |
| |
| Keywords: | varying-coefficient single-index P-spline generalized linear model |
|
|
