Testing Serial Correlation in Semiparametric Time Series Models
In this paper, we propose two test statistics for testing serial correlation in semiparametric time series model that could allow lagged dependent variables as explanatory variables. The first one is testing for zero first-order serial correlation and the second is for testing higher-order serial correlation. The test statistics are shown to have asymptotic normal or chi^2 distributions under the assumption of a martingale difference error process. Our results generalize some of the test statistics of Li and Hsiao (1998), that were developed for the case of panel data with a large N and a fixed T, to the case of a large T with N either small or large. Copyright 2003 Blackwell Publishing Ltd.
If you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
As the access to this document is restricted, you may want to look for a different version under "Related research" (further below) or search for a different version of it.
Volume (Year): 24 (2003)
Issue (Month): 3 (May)
|Contact details of provider:|| Web page: http://www.blackwellpublishing.com/journal.asp?ref=0143-9782|
|Order Information:||Web: http://www.blackwellpublishing.com/subs.asp?ref=0143-9782|