[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: two step procedure

From   Maarten buis <>
Subject   Re: st: two step procedure
Date   Sun, 16 Sep 2007 17:04:25 +0100 (BST)

--- "Xu, Xin" <> wrote:
> Does anybody know how to calculate Murphy-Topel variance estimator? I
> am aware of Hardin(2002) paper and Hole et al. (2006) paper. However,
> in my case, I have two steps coming from two different data sets
> which I append them together. Therefore, it is hard for me to
> calculate C and R matrix as shown in their paper.

You should give full references, even if articles appear in the Stata

The only command I know of that explicitly deals with combining
estimates from multiple samples is the -suest- command. However, quite
offten people think they have multiple samples when they don't, e.g.
they think that men and women are different samples while almost
everything can be solved when adding a dummie for female and the
appropriate interaction terms.  

Hope this helps,

Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands

visiting address:
Buitenveldertselaan 3 (Metropolitan), room Z434

+31 20 5986715

Want ideas for reducing your carbon footprint? Visit Yahoo! For Good
*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index