Bandwidth selection through cross-validation for semi-parametric varying-coefficient partially linear models
Authors:
- 14 October 2009
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 79 (11) , 1277-1286
Abstract
We study bandwidth selection for a class of semi-parametric models. The proper choice of optimal bandwidth minimizes the prediction errors of the model. We provide detailed derivation of our procedure and the corresponding computation algorithms. Our proposed method simplifies the computation of the cross-validation criteria and facilitates more complicated inference and analysis in practice. A data set from Wisconsin Diabetes Registry has been analysed as an illustration.Keywords
This publication has 17 references indexed in Scilit:
- Analysis of Longitudinal Data With Semiparametric Estimation of Covariance FunctionJournal of the American Statistical Association, 2007
- Profile likelihood inferences on semiparametric varying-coefficient partially linear modelsBernoulli, 2005
- Efficient estimation for semivarying-coefficient modelsBiometrika, 2004
- The Elements of Statistical Learning2001
- On Profile LikelihoodJournal of the American Statistical Association, 2000
- Generalized Partially Linear Single-Index ModelsJournal of the American Statistical Association, 1997
- Longitudinal Patterns of Glycemic Control and Diabetes Care from Diagnosis in a Population-based Cohort with Type 1 DiabetesAmerican Journal of Epidemiology, 1996
- On the Ergodicity of Tar(1) ProcessesThe Annals of Applied Probability, 1991
- Modelling nonlinear random vibrations using an amplitude-dependent autoregressive time series modelBiometrika, 1981
- The Relationship between Variable Selection and Data Agumentation and a Method for PredictionTechnometrics, 1974