Citation:
Du, Z., & Escanciano, J. C. (2014). A Nonparametric Distribution-Free Test for Serial Independence of Errors. Econometric Reviews, 34(6-10), pp. 1011-1034.
xmlui.dri2xhtml.METS-1.0.item-contributor-funder:
Ministerio de Educación y Ciencia (España)
Sponsor:
Research of first author funded by Ministry of Education of China, 11XJC790002 and the National Natural Science Foundation of China, 71401140. Research of second author has been funded by the Spanish Plan Nacional de I+ D+ I, reference number SEJ2007-62908.
Project:
Gobierno de España. SEJ2007-62908
Keywords:
Empirical processes
,
Generalized spectral test
,
Location-scale model
,
Parameter estimation uncertainty
,
Serial dependence
,
Unobservable errors
In this article, we propose a test for the serial independence of unobservable errors in location-scale models. We consider a Hoeffding-Blum-Kiefer-Rosenblat type empirical process applied to residuals, and show that under certain conditions it converges weaklIn this article, we propose a test for the serial independence of unobservable errors in location-scale models. We consider a Hoeffding-Blum-Kiefer-Rosenblat type empirical process applied to residuals, and show that under certain conditions it converges weakly to the same limit as the process based on true errors. We then consider a generalized spectral test applied to estimated residuals, and get a test that is asymptotically distribution-free and powerful against any type of pairwise dependence at all lags. Some Monte Carlo simulations validate our theoretical findings.[+][-]