Hi,
I am trying to compare the equality of two regression coefficients from regressions that use the same variables, but the catch is that the two equations are at different levels of analyses. One looks at data at the state-level, while the other looks at it at the LMA-level. Both of these datasets are created from a master dataset that contains data at the county-level (by computing means of the variables and collapsing the data).
From what I've read about the Chow test, I can't find any mention of it being applicable when different levels of analyses are used. Everything seems to indicate that Chow tests or Z-tests can be used only between subgroups at the same level of analysis. Is it possible to do such an equality test? If so, how would I go about it?
Any advice on how to proceed would be much appreciated.
Thank you.
-Atul
*
* 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/
