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: nlogit

From   Chiara Mussida <>
To   statalist <>
Subject   st: nlogit
Date   Sun, 26 May 2013 11:56:58 +0200

Dear All,
I run a nlogit with a degenerate branch: the commands typed are:

nlogitgen noemp=dataset(no:1, yes: 2|3|4)
constraint 1 [no_tau]_cons=1
nlogit mode EE || noemp:  classe1 classe2  classe4 || dataset:,
noconstant case(id)  constraint(1)

details: noemp is a variable for individuals leaving the state of
employment for: a different job (working time, sector, employer, job
position), for unemployment, and for inactivity (yes:2,3,4). the
degenerate branch is for individual not leaving employment/not
changing their empl conditions (no:1).

I then fix my constraint as required for the degenerate branch.
The problem is in the model specification, precisely for the first
equation (mode is the dependent variable, correctly specified): i'm
not able to find an alternative specific variable with a within case
variability. I tried with the stock at the beginning of the period of
the individuals not leaving employment (EE above), firmsize, age,
gender but without success. Do you have suggestions?

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index