Nonparametric goodness-of-fit test for heteroscedastic regression models

Wang, Lan;Akritas, Michael G.;Van Keilegom, Ingrid
(2002) , 29 pages

Files

ISBADP0230.pdf
  • Open Access
  • Adobe PDF
  • 291.73 KB
Download

Details

Authors
  • Wang, LanPennsylvannia State University
    Author
  • Akritas, Michael G.Pennsylvannia State University
    Author
  • Van Keilegom, IngridUCLouvain
    Author
Abstract
For the heteroscedastic nonparametric regression model Yni = m(xni)+σ(xni)Є ni; i = 1; ...; n; we propose a new test procedure for testing that the regression function m is constant. The test statistic is modeled after the usual lack-of-fit statistic for constant regression in the case of replicated observations, and thus is very easy to compute. The asymptotic theory uses recent developments in the asymptotic theory for analysis of variance when the number of factor levels is large. Comparisons with competing procedures and analysis of a data set are included.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Wang, L., Akritas, M. G., & Van Keilegom, I. (2002). Nonparametric goodness-of-fit test for heteroscedastic regression models (STAT Discussion Papers 0230). https://hdl.handle.net/2078.5/32770