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 at the end of May, and its replacement, statalist.org is already up and running.


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

RE: st: Predictions and psuedo Rsq in zoib


From   Cameron McIntosh <cnm100@hotmail.com>
To   STATA LIST <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Predictions and psuedo Rsq in zoib
Date   Sat, 24 Sep 2011 22:00:05 -0400

Prerna,

Perhaps you might consider some of the likelihood-based pseudo-explained variance measures instead. See for example:
DeMaris, A. (2002). Explained Variance in Logistic Regression: A Monte Carlo Study of Proposed Measures. Sociological Methods & Research, 31(1), 27-74.http://gabarrot.psychologie-sociale.org/documents/DM2002.pdf
Cam

> From: maruiprerna@gmail.com
> Date: Sat, 24 Sep 2011 07:38:35 -0400
> Subject: st: Predictions and psuedo Rsq in zoib
> To: statalist@hsphsun2.harvard.edu
> 
> Hello Statalisters,
> 
> I have estimated the following equation:
> 
> zoib y1 x1 x2, zeroinflate (x1 x2) cluster (z) nolog
> zoib y2 x1 x2 zeroinflate (x1 x2) cluster (z) nolog
> 
> where yi = income from various sources and z = geographical location
> (city dummies).
> 
> I would like to calculate the pseudo-R squares.
> 
> Thus I specified the following:
> 
> predict y1_pred
> 
> Stata responded with:
> 
> (option pr assumed)
> 
> I think I am okay with this because I just want to get a sense of the
> global measure of explained variance as Ferrari and Cribari-Neto (
> 2004) suggest for beta regression. I'm assuming that a similar method
> on zoib is not so bad.
> 
> However, on running a correlation, I get a correlation of -0.5. Why
> would the correlation be negative!?! I used the command below.
> 
> correlate y1 y1_pred
> 
> On the other hand,
> 
> correlate y2 y2_pred
> 
> gives me a positive correlation.
> 
> Am I misinterpreting the result or is this an incorrect way to
> ascertain Rsquares for an inflated beta regression?
> 
> I am using Stata 11.2. I installed zoib from ssc.
> 
> Ferrai, S., & Cribari-Neto, F. (2004). Beta Regression for Modelling
> Rates and Proportions. Jl. of Applied Statistics. Vol. 31, No. 7,
> 799-815.
> 
> Thanks.
> 
> Prerna
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

 		 	   		  
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index