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: A Problem about Random Effects Negative Binomial Model (xtnbreg)

From   Kun-Feng Wu <>
Subject   st: A Problem about Random Effects Negative Binomial Model (xtnbreg)
Date   Tue, 1 Nov 2011 19:44:23 -0400


I'm running xtnbreg using both STATA10(MP) and 12(SE), and I'm
interested in the predicted number of events.

As I took exponential to the linear prediction (xb) to check the
predicted number of events generated by the postestimation function
(predict count, nu0). The thing I don't understand is that nu0 does
not equal to exp(xb). Moreover, in come cases, xb is greater than nu0.
For example,

count          xb
1.280443 1.851208
1.218648 1.801744
1.127919 1.724376
1.238915 1.818237
1.291304 1.859654
1.422111 1.956144

I'm wondering that did I do anything wrong? or anything else?
Any response would be appreciated. Thanks.


*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index