Back to Search
Start Over
Test for single-index composite quantile regression
- Source :
- Volume: 43, Issue: 5 861-871, Hacettepe Journal of Mathematics and Statistics
- Publication Year :
- 2013
- Publisher :
- Hacettepe Üniversitesi, 2013.
-
Abstract
- It is known that composite quantile regression estimator could be muchmore efficient and sometimes arbitrarily more efficient than the leastsquares estimator. In this paper, tests for the index parameter andindex function in the single-index composite quantile regression areconsidered. The asymptotic behaviors of the proposed tests are established and their limiting null distributions are demonstrated to followan asymptotically χ2-distribution. The simulation studies and a realdata application are conducted to illustrate the finite sample performance of the proposed methods.&nbsp
Details
- Language :
- English
- ISSN :
- 2651477X
- Database :
- OpenAIRE
- Journal :
- Volume: 43, Issue: 5 861-871, Hacettepe Journal of Mathematics and Statistics
- Accession number :
- edsair.tubitakulakb..7b730ac1c093c46bf829e2dab77e389d