Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: Direction of the effect of the cluster command on the standard error depends on the inclusion of a control variable


From   DE SOUZA Eric <eric.de_souza@coleurope.eu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Direction of the effect of the cluster command on the standard error depends on the inclusion of a control variable
Date   Thu, 6 Jan 2011 12:36:18 +0100

You can find a good presentation of cluster sampling issues (Lecture 7) --  and, indeed, an excellent course in recent development in econometrics -- here:
http://www.cemmap.ac.uk/resources/resources25.php
You have both the slides and the lecture notes.
The level supposes a good basis in econometrics.

Eric


Eric de Souza
College of Europe
Brugge (Bruges), Belgium
http://www.coleurope.eu



-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Jacob Felson
Sent: 06 January 2011 01:30
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: Direction of the effect of the cluster command on the standard error depends on the inclusion of a control variable

Justina,

Thank you for your input.  Is it improper to use the cluster command with only 4 nations?  I will attempt #2.

Jacob Felson

On Wed, Jan 5, 2011 at 7:20 PM, Justina Fischer <JFischer@diw.de> wrote:
> Hi,
>
> just two caveats
>
> 1) Using cluster-option, you should have a decent number of clusters 
> to profit from its beneficial characteristics (Kit can probably 
> highlight on this). I guess 4 clusters is far from large....
>
> 2) in cross-sectional micro data, I would use cluster-option when my 
> variable of interest varies only across countries, as standard errors 
> are then corrected for this. For example, this could be an 
> institution, like democracy
>
>
> to your question: is z a vector of country-characteristics in your 
> micro model? That could possibly explain your finding...
>
> Justina
>
>
> -----owner-statalist@hsphsun2.harvard.edu schrieb: -----
>
> An: statalist@hsphsun2.harvard.edu
> Von: Jacob Felson <felsonj@gmail.com>
> Gesendet von: owner-statalist@hsphsun2.harvard.edu
> Datum: 06.01.2011 01:01AM
> Thema: st: Direction of the effect of the cluster command on the 
> standard error depends on the inclusion of a control variable
>
> I wonder if anyone might be able to provide an explanation for the 
> following scenario.  I'm wondering why the direction of the change in 
> a standard error affected by the use of the cluster command depends on 
> the whether another control variable is included.  My inquiry is more 
> theoretical than practical, as I'm not wondering "what I should do"
> but rather, simply "why is this happening?"   Let me elaborate below.
>
> Consider the following variables:
>
> y, the dependent variable
> x, the independent variable of greatest interest, which is moderately 
> correlated with y and with z z, another independent variable, which is 
> correlated with y at about 0.5.
>
> nation - the data was collected in 4 different nations by different 
> organizations.
>
>
> I am examining the standard errors (SE) for the coefficient of 
> variable x from the following four models:
>
> 1. Regress y on x, without clustering on nation.
> 2. Regress y on x, with clustering on nation.
>
> 3. Regress y on x and z without clustering on nation.
> 4. Regress y on x and z with clustering on nation.
>
>
> The SE of the coefficient for x is LARGER in model 2 than in model 1.
> This suggests there is a positive intercluster correlation.  That is, 
> the residuals are more similar to each other within nations than we 
> would expect by chance alone.  I suppose there is a preponderance of 
> positive residuals in some nations and a preponderance of negative 
> residuals in other nations.
>
> The SE of the coefficient for x is SMALLER in model 4 than in model 3.
> This suggests there is a negative intercluster correlation.  That is, 
> the residuals are less similar to each other within nations than we 
> would expect by chance.
>
>
> So the effect that clustering on nation has on the SE of x depends on 
> whether a third variable, z, is controlled.  Why is this?
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
>
>

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index