Bookmark and Share

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

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

Re: st: Best way to export a simple Stata model

From   Maarten Buis <>
Subject   Re: st: Best way to export a simple Stata model
Date   Sat, 11 Feb 2012 15:01:36 +0100

Most post-estimation commands do not know or care whether you changed
the data after estimating the model but before using the
post-estimation command. This can be useful for what-if analyses. You
estimate the model, change the variable you want to change in your
data (possibly precede it with -preserve-) so it corresponds to your
scenario, and use for example -predict- to see what happens.
Alternatively, I guess you can implement many scenarios with clever
use of -margins- without changing the data.

Hope this helps,

On Fri, Feb 10, 2012 at 4:21 PM, Dimitriy V. Masterov wrote:
> I have a simple regression model that I would like to pass on to a
> colleague. She will mostly use it to conduct what-if analyses where
> she changes some of the independent variables. I would like to build
> in some controls. For example, if the range of x_1 is integers from 1
> to 5, I need to make sure that she can't enter a 10.2. There are also
> dummy variables that need to be handled appropriately, so that being
> make and female simultaneously is not possible.
> Is the best way of doing this in Excel by hand, or is there something
> better? I have a feeling I will wind up tweaking this a lot so a more
> automate solution would be preferable.
> *
> *   For searches and help try:
> *
> *
> *

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

*   For searches and help try:

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