Autoregression quantiles and related rank score processes for generalized random coefficient autoregressive processes

  • Harel M
  • Puri M
  • 170

    Readers

    Mendeley users who have this article in their library.
  • 2

    Citations

    Citations of this article.

Abstract

Regression quantiles were developed by Koenker and Bassett (Econometrica 46 (1978), 33–50); they provide natural and extremely useful counterparts of the sample quantiles in general linear models. The regression rank scores were introduced by Gutenbrunner and Jurečková (Ann. Statist. 8 (1992), 305–329) as dual variables to regression quantiles. Koul and Saleh (Ann. Statist. 23 (1995), 670–689) developed the procedures based on the regression quantiles of Koenker and Bassett (Econometrica 46 (1978), 33–50) and the regression rank scores of Gutenbrunner and Jurečková Ann. Statist. 8 (1992), 305–329 in linear regression to the pth-order autoregression models. In this paper, we further develop and investigate the analogs of these procedures to a larger class of processes and derive a test for a bilinear model without estimating the bilinear coefficient and the autoregression constants.

Author-supplied keywords

  • 62M10
  • 65G30
  • Absolute regularity
  • Autoregression quantiles
  • Generalized random coefficient autoregressive proc
  • Related rank scores processes
  • Strong mixing

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Michel Harel

  • Madan L. Puri

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free