摘要
We consider the problem of variable selection for the fixed effects varying coefficient models. A variable selection procedure is developed using basis function approximations and group nonconcave penalized functions, and the fixed effects are removed using the proper weight matrices. The proposed procedure simultaneously removes the fixed individual effects, selects the significant variables and estimates the nonzero coefficient functions. With appropriate selection of the tuning parameters, an asymptotic theory for the resulting estimates is established under suitable conditions. Simulation studies are carried out to assess the performance of our proposed method, and a real data set is analyzed for further illustration.
We consider the problem of variable selection for the fixed effects varying coefficient models. A variable selection procedure is developed using basis function approximations and group nonconcave penalized functions, and the fixed effects are removed using the proper weight matrices. The proposed procedure simultaneously removes the fixed individual effects, selects the significant variables and estimates the nonzero coefficient functions. With appropriate selection of the tuning parameters, an asymptotic theory for the resulting estimates is established under suitable conditions. Simulation studies are carried out to assess the performance of our proposed method, and a real data set is analyzed for further illustration.
基金
Supported by National Natural Science Foundation of China(Grant Nos.11471029,11101014 and 11301279)
the Beijing Natural Science Foundation(Grant No.1142002
the Science and Technology Project of Beijing Municipal Education Commission(Grant No.KM201410005010)
the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(Grant No.12KJB110016)
CERG Grant from the Hong Kong Research Grants Council(Grant No.HKBU 202012)
FRG Grant from Hong Kong Baptist University(Grant No.FRG2/12-13/077)