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]

st: update margdistfit

From   Maarten Buis <>
Subject   st: update margdistfit
Date   Thu, 22 Dec 2011 17:03:54 +0100

Thanks to Kit Baum a new version of -margdistfit- is now available
from SSC. -margdistfit- is a post-estimation command that can be used
after -regress- or -betafit- (available from SSC) to check the
distributional assumptions of these models. It does so by comparing
the marginal distribution of the dependent variable implied by the
model with the observed distribution of the dependent variable using a
qq-plot, pp-plot, a plot of the two cumulative distributions or a
hanging rootogram. To give an indication of how much deviation from
the theoretical distribution is legitimate, the graph will also show
the distribution of several (by default 20) simulated variables under
the assumption that the regression model is true. Examples are given
here: <>

The new version contains the following improvements:

o One can now compare the theoretical and empirical distribution using
a hanging rootogram.

o The simulated variables now also include uncertainty due to the fact
that the parameters are estimated. This is done by first drawing the
parameters from their sampling distribution and than drawing a
simulated dependent variable from that distribution.

o I improved the algorithm used for approximating the quartile
function and the cumulative distribution function.

If you have already installed -margdistfit- you can update it by
typing in Stata -ssc install margdistfit, replace- or -adoupdate,
update-. If you haven't installed it yet and you want to get it, you
can do so by typing in Stata -ssc install margdistfit-.

I hope some of you will find it useful,

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