期刊名称：Sankhya. Series A, mathematical statistics and probability
印刷版ISSN：0976-836X
电子版ISSN：0976-8378
出版年度：2008
卷号：70
期号：01
页码：38--72
出版社：Indian Statistical Institute
摘要：Penalized likelihood method offers versatile smoothing techniques in a vari-
ety of stochastic settings, and the proper selection of the smoothing param-
eters and other tuning parameters is crucial to the practical performance
of penalized likelihood estimates. In this article, we study the selection of
the smoothing parameters and the correlation parameters in penalized like-
lihood regression with correlated data. We propose a simple modification
of Mallows¡¯ CL to accommodate the correlation parameters, and derive a
profiled version for use with unknown variance. The proposed methods are
shown to be optimal in a certain sense through asymptotic analysis and nu-
merical simulations. Real-data example is also presented and related issues
discussed.
