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

st: Content-Transfer-Encoding: 8bit

From   "Drakos, Kostas" <[email protected]>
To   <[email protected]>
Subject   st: Content-Transfer-Encoding: 8bit
Date   Wed, 4 Aug 2004 10:44:41 +0100

I am estimating a dynamic panel using the GMM Arellano-Bond routine.
It's proved impossible so far to find an instrument set that will
satisfy the Sargan test. How crucial is the significance of the Sargan

Kostas Drakos

-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of David Airey
Sent: 04 August 2004 04:40
To: [email protected]
Subject: re: st: Re: xtlogit and logistic-cluster (REVISED)

Joseph Coveney wrote:

> -logit, cluster()- produces the same results as -xtgee,
> family(binomial)
> link(logit) corr(independent) robust- (this came up on the list last 
> month in
> the context of -mlogit, cluster()-, so I would recommend avoiding that

> approach
> in circumstances in which population-averaged GEE would not be ideal.

> There
> are those who would say that GEE is never ideal, but even among its 
> adherents,
> most would caution that, with only 50 physicians, GEE would be a 
> little dicey.
> -xtlogit, fe- would help see the influence of patient characteristics
> upon a
> physician's inclination to refer, while, in a sense, controlling for 
> physician
> characteristics.  (Where the predictor variables for patient 
> characteristics do
> not vary within a physician, the entire physician's caseload would be 
> dropped.)
>  As you mention, because physician's characteristics do not vary 
> within a
> physician, -xtlogit, fe- doesn't seem to be the way to go to explore 
> both
> patient and physician characteristics together.
> -xtlogit, re- would seem to be the remaining alternative available in
> Stata,
> unless I'm overlooking something.  Cautions would be similar to the 
> case with
> GEE.  The number of physicians is limited.  If there is a substantial
> correlation between the fixed effects (physician covariates) and the 
> random
> effect, then the parameters are liable not to be consistently 
> estimated.

But when stuck with a small data set, why not run a model designed for 
that data structure, as opposed to running a model not designed for the 
data structure? When does ignoring the clustering become more favorable 
to acknowledging the presence of fewer than an optimal number clusters? 
Why is it not the case that a good model on a small data set is not 
always better than a bad model on the same small data set? I hope I'm 


*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index