Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

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

Re: st: Manual calculation of scale factors after tobit and/or truncreg [econometrics help]

From   Maarten Buis <>
Subject   Re: st: Manual calculation of scale factors after tobit and/or truncreg [econometrics help]
Date   Fri, 12 Oct 2012 09:11:20 +0200

On Thu, Oct 11, 2012 at 8:34 PM, Clara Mukuria wrote:
> Hi,
> I am trying to work out how to calculate the scale factor used to adjust
> results after a tobit and/or a truncreg regression.

I assume you mean what in "normal" linear regression would be the
standard deviation of the residual/root mean squared error/standard
error of the estimate. This parameter is returned in the vector of
parameters e(b). One way you can access it is through
[sigma]_b[_cons], for example -display [sigma]_b[_cons]-.

> I know there are several post estimation options, I am using the 'predict y,
> ystar(ll, ul)' option to assess how well the the model predicts. However,
> the aim is to provide generate a mapping function that can be used in other
> datasets to predict the single generic measure so I need to work out the
> scale factor.

You can just estimate your model in one dataset, open another dataset
and than use -predict-. You need to make sure that the
independent/explanatory/right-hand-side/x variables in both datasets
have the same name (how else would Stata know which parameter to apply
to which variable?), but otherwise there are no restrictions.

Hope this helps,

Maarten L. Buis
Reichpietschufer 50
10785 Berlin
*   For searches and help try:

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