Smoothing Parameter Selection For A New Regression Estimator For Non-Negative Data
In this thesis, the CV selection technique is applied into Chaubey, Laib and Sen (2008)'s estimator, which is a new regression estimation for nonnegative random variables. The estimator is based on a generalization of Hille's lemma and a perturbation idea. The first and second order MSE ar...
| Main Author: | |
|---|---|
| Format: | Others |
| Published: |
2009
|
| Online Access: | http://spectrum.library.concordia.ca/976444/1/MR63095.pdf He, Baohua <http://spectrum.library.concordia.ca/view/creators/He=3ABaohua=3A=3A.html> (2009) Smoothing Parameter Selection For A New Regression Estimator For Non-Negative Data. Masters thesis, Concordia University. |
| Summary: | In this thesis, the CV selection technique is applied into Chaubey, Laib and Sen (2008)'s estimator, which is a new regression estimation for nonnegative random variables. The estimator is based on a generalization of Hille's lemma and a perturbation idea. The first and second order MSE are derived. The ISE criteria for the optimal value of smoothing parameter is discussed and also calculated. The simulation results and the Graphical illustrations on the new estimator, comparing with Fan (1992, 2003)'s local kernel regression estimators are provided. |
|---|