AN INTERIOR-POINT ALGORITHM FOR NONLINEAR QUANTILE REGRESSION

Authors
KOENKER R PARK BJ
Citation
R. Koenker et Bj. Park, AN INTERIOR-POINT ALGORITHM FOR NONLINEAR QUANTILE REGRESSION, Journal of econometrics, 71(1-2), 1996, pp. 265-283
Citations number
44
Categorie Soggetti
Social Sciences, Mathematical Methods",Economics,"Mathematical, Methods, Social Sciences
Journal title
Journal of econometrics → ACNP
ISSN journal
03044076
Volume
71
Issue
1-2
Year of publication
1996
Pages
265 - 283
Database
ISI
SICI code
0304-4076(1996)71:1-2<265:AIAFNQ>2.0.ZU;2-G
Abstract
A new algorithm for computing quantile regression estimates for proble ms in which the response function is nonlinear in parameters is descri bed. The nonlinear I, estimation problem is a special (median) case. T he algorithm is closely related to recent developments on interior poi nt methods for solving linear programs. Performance of the algorithm o n a variety of test problems including the censored linear quantile re gression problem of Powell (1986) is reported.