Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: regression methodology


From   "Vasilis.Sarafidis" <vs242@cam.ac.uk>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: regression methodology
Date   21 Oct 2005 16:41:44 +0100

I assume you are dealing with a panel where all regressors are strictly exogenous.

Including a dummy for a subgroup is not equivalent to running separate regressions for each subgroup. If you want to allow for subgroup-specific heterogeneity across all the parameters then you need to add multiplicative dummies for each regressor plus dummies for subgroup-specific constants.

Then the two methods will produce the same values for the parameters so there is no issue of sample size. However, pooling the whole data set will restrict the variance error to be the same across all subgroups, so if you don't want to do so an adjustment is necessary.

See a usefull discussion in

http://www.stata.com/support/faqs/stat/awreg.html

Pooling the whole data set and adding multiplicative dummies will allow you to test in a straightforward way whether these dummies are statistically insignificant or not. So this approach is more efficient in the sense that you could allow a limited only set of regressors being subgroup-specific at the end.

Hope this helps

Vasilis


On Oct 21 2005, Dirk Nachbar wrote:


Dear all

there are two ways to deal with heterogeneity in your data set

1. you include a dummy for a sub-group
2. you run several regressions for each sub-group

Now I was thinking when do we choose one or the other . It seems that if we do not want the same explanatory variables for each sub-group we should use approach 2, but then maybe our sample becomes too small. Approach 1 seems more neat and is quicker.

What do you think? Which approach is better and how should we determine when to use which approach?

Dirk Nachbar Assistant Economist Pensim2 Department for Work and Pensions Level 4, The Adelphi 1-11 John Adam St WC2N 6HT London 020 796 28531 ********************************************************************** This document is strictly confidential and is intended only for use by the addressee. If you are not the intended recipient, any disclosure, copying, distribution or other action taken in reliance of the information contained in this e-mail is strictly prohibited. Any views expressed by the sender of this message are not necessarily those of the Department for Work and Pensions. If you have received this transmission in error, please use the reply function to tell us and then permanently delete what you have received. Please note: Incoming and outgoing e-mail messages are routinely monitored for compliance with our policy on the use of electronic communications. **********************************************************************



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
--
If I could get my membership fee back, I'd resign from the human race.
Fred Allen (1894 - 1956)



*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index