Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/23171 
Year of Publication: 
2003
Series/Report no.: 
Working Paper No. 2003-14
Publisher: 
Rutgers University, Department of Economics, New Brunswick, NJ
Abstract: 
This paper introduces a conditional Kolmogorov test, in the spirit of Andrews (1997), that allows for comparison of multiple misspecifed conditional distribution models, for the case of dependent observations. A conditional confidence interval version of the test is also discussed. Model accuracy is measured using a distributional analog of mean square error, in which the squared (approximation) error associated with a given model, say model i; is measured in terms of the average over U of E((Fi(ut,Theta-t-plus)-Fo(u ,Theta-o))) ; where U is a possibly unbounded set on the real line, Zt is the conditioning information set, Fi is the distribution function of a particular candidate model, and F0 is the true (unkown) distribution function. When comparing more than two models, a ?benchmark? model is specified, and the test is constructed along the lines of the ?reality check? of White (2000). Valid asymptotic critical values are obtained via a version of the block bootstrap which properly captures the effect of parameter estimation error. The results of a small Monte Carlo experiment indicate that the conditional confidence interval version of the test has reasonable finite sample properties even for samples with as few as 60 observations.
Subjects: 
block bootstrap
conditional Kolmogorov test
data snooping
misspecified conditional distribution
JEL: 
C22
C52
Document Type: 
Working Paper

Files in This Item:
File
Size
330.21 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.