Re: st: how to write model equation for probit with cluster

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Sat, 12/2/11, Laura R. wrote:
> I estimated a probit equation in stata with the option
> -cluster-, like this:
> 
> probit depvar indepvar1 indepvar2 ..., cluster(clustervar)
> 
> Usually, you can write the formula for probit models in the
> paper something like this:
> 
> Pr(Y=1|observed var)= "cdf sign" (bX1+bX2+e)
> 
> However, I am wondering how to insert the option for
> cluster into this formula.

You should not include the e (I assume error term) in these
models. The error terms is already included in the probability.

Compare this with linear regression, either you say:

y = bx1 + bx2 + e

or:

E(y) = bx1 + bx2

but not:

E(y) = bx1 + bx2 + e

Other than that, you can use the same formula for model with
clustered standard errors, as this formula only represents
the relationship between the mean/probabilty and the explanatory
variables.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/