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: New packages -meresc- and -r2_mz- on SSC

From   Dirk Enzmann <>
Subject   st: New packages -meresc- and -r2_mz- on SSC
Date   Sat, 21 Jan 2012 19:18:36 +0100

Thanks to Kit Baum and Ulrich Kohler, two new packages are on SSC.

-meresc- rescales the results of mixed nonlinear probability models such as xtmelogit, xtlogit, or xtprobit to the same scale as the intercept-only model. This allows to compare regression coefficients or variance components across hierarchically nested models. The technique applied is described in chapter 6.5 of Hox (2010: 133--139).

Reference: Hox, J. J. (2010), Multilevel Analysis: Techniques and Applications. New York (2nd ed.): Routledge.

r2_mz is a post-estimation command that computes McKelvey & Zavoina's Pseudo R2 for multilevel logistic regression, random effects, and fixed effects logit and probit models. At least for fixed effects models, according to Windmeijer (1995) "... it seems to be the best measure to use" (p. 114). r2_mz works after the following: xtmelogit, xtlogit, xtprobit, logit, logistic, probit.

Reference: Windmeijer, F. A. G. (1995). Goodness-of-fit measures in binary choice models. Econometric Reviews, 14, 101-116.
[ ]

Dr. Dirk Enzmann
Institute of Criminal Sciences
Dept. of Criminology
Rothenbaumchaussee 33
D-20148 Hamburg

phone: +49-(0)40-42838.7498 (office)
       +49-(0)40-42838.4591 (Mrs Billon)
fax:   +49-(0)40-42838.2344
*   For searches and help try:

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