JSM 2004 - Toronto

Abstract #301278

This is the preliminary program for the 2004 Joint Statistical Meetings in Toronto, Canada. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2004); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2004 Program page
Activity Number: 378
Type: Contributed
Date/Time: Wednesday, August 11, 2004 : 2:00 PM to 3:50 PM
Sponsor: General Methodology
Abstract - #301278
Title: Rao-type Tests for B-spline Estimators of Conditional Quantiles with Varying Coefficients
Author(s): Mi-Ok Kim*+
Companies: University of Kentucky
Address: 817 Patterson Office Tower, Lexington, KY, 40506-0027,
Keywords: quantile regression ; lack-of-fit test for regression quantiles ; B-splines
Abstract:

When a nonparametric regression model is in use, model validation is warranted by the principle of parsimony. In case of varying-coefficient models, whether the coefficients indeed vary needs to be checked. While there exist many studies on the estimation of the model, just a few discuss model validation. For the conditional mean regression, the confidence interval method and a likelihood-ratio-type test has been suggested. We propose a Rao-type test for validating the varying-coefficient model in estimating conditional quantiles with B-spline estimators. The proposed test is consistent against all alternatives with the number of knots growing, while when the number of knots is fixed, the proposed test is inconsistent against a certain form of alternatives. We identify the set of the alternatives against which the test is inconsistent and observe the limiting distribution of the proposed test statistic. A simulation study is conducted to assess the the performance of the proposed test.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2004 program

JSM 2004 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2004