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]

st: update propcnsreg available

From   Maarten Buis <>
Subject   st: update propcnsreg available
Date   Fri, 28 Sep 2012 17:39:43 +0200

Thanks to Kit Baum a new version of -propcnsreg- is now available from
SSC. To install it use the -ssc- or -adoupdate- commands in Stata.

-propcnsreg- fits a model with proportionality constraints. Consider a
model where one wants to explain the respondent's education (ed) with
the eduction of the father (fed) and the mother (med), and that one is
interested in testing whether the relative contribution of the
mother's education has increased over time. propcnsreg will estimate
this model under the null hypothesis that the relative contributions
of fed and med have remained constant over time. Notice that the
effects of fed and med are allowed to change over time, but the
effects of fed and med are constrained to change by the same
proportion over time. So if the effect of fed drops by 10% over a
decade, than so does the effect of med. An alternative interpretation
of this model is that fed and med "add up" to a latent variable
(parental education), whereby the weights assigned to each parent
remained constant over time. This is a model known as a model with
parametrically weighted covariates. It is also possible to add an
error term to this latent variable. A more complete description is
given here: <>.

In this update I added the possibility to estimate a proportionality
constraint in a Poisson model, and I extended the possibility to use
-predict- after -propcnsreg-. I also fixed a bug when using weights
and the constraint that the standard deviation of the latent variable
is one to identify the scale of the latent variable. In that case
-propcnsreg- used the unweighted variance of the latent variable
instead of the weighted variance.

I hope some of you will find it useful,

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