Hi
I am currently running some analysis using gllamm. I have quite a big
dataset (160,000 cases), about 10 individual explanatory variables and
several area level explanatory variables.
What I am concerned about is the condition number. It says in the manual
that a large condition number might indicate a poorly fitting model (but on
the hand it might not). As soon as I add the level two explanatory
variables the condition number increases substantially, in some cases up to
about 500. Is this a serious problem? Does anyone know how I might overcome
it?
I have checked all the variables for collinearity, and those which are
collinear have not been entered into the same model, but instead have been
used separately. Is this large condition number something I should be
concerned about?
I would be grateful for any advice
Thanks
Liz
For the latest data on the economy and society
consult National Statistics at http://www.statistics.gov.uk
**********************************************************************
Please Note: Incoming and outgoing email messages
are routinely monitored for compliance with our policy
on the use of electronic communications
**********************************************************************
Legal Disclaimer : Any views expressed by
the sender of this message are not necessarily
those of the Office for National Statistics
**********************************************************************
The original of this email was scanned for viruses by the Government Secure Intranet (GSi) virus scanning service supplied exclusively by Energis in partnership with MessageLabs.
On leaving the GSi this email was certified virus-free
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
