摘要
Single index models are natural extensions of linear models and overcome the so-called curse of dimensionality. They are very useful for longitudinal data analysis. In this paper, we develop a new efficient estimation procedure for single index models with longitudinal data, based on Cholesky decomposition and local linear smoothing method. Asymptotic normality for the proposed estimators of both the parametric and nonparametric parts will be established. Monte Carlo simulation studies show excellent finite sample performance. Furthermore, we illustrate our methods with a real data example.
学科与关键词
关键词
single index modelsCholesky decompositionlocal linear regressionlongitudinaldata
- A Novel Estimation Method in Generalized Single Index ModelsZhang, Dixin; Wang, Yulin; Liang, Hua*JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 2023, 41(2): 399-413.
- Partially Linear Single-Index Model in the Presence of Measurement ErrorLin, Hongmei*; Shi, Jianhong; Tong, Tiejun; Zhang, RiquanJournal of Systems Science & Complexity, 2022, 35(6): 2361-2380.
- ESTIMATION AND INFERENCE FOR DYNAMIC SINGLE-INDEX VARYING-COEFFICIENT MODELSGuan, Xin; Liu, Hua; You, Jinhong*; Zhou, YongStatistica Sinica, 2023, 33(1): 85-105.被引 1
