Date: Wed, 9 Jan 2008 19:29:25 -0500
Reply-To: Lisa Stickney <Lts1@ptd.net>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Lisa Stickney <Lts1@ptd.net>
Subject: Heteroscedasasticity questions
Content-Type: text/plain; charset="iso-8859-1"
I have two questions about heteroscedasticity. I have two data sets -- one larger (1002 cases), and one smaller (104 case subset of the larger one).
My first question is can I run the Koenker version of Breush-Pagan on the smaller data set or do I need to run something else? If so, what? Based on the Gwilym Pryce paper (that's posted on Raynald's web site), I'm leaning towards White's test. Is there anything else about it that I should know?
And second, does anyone have code for the heteroscedasticity correction using White's Standard Errors. I believe I'll need the ones for samples larger than 500 and for samples smaller than 250.
Thanks and advance.
Lisa T. Stickney
Fox School of Business
====================To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
For a list of commands to manage subscriptions, send the command