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: marginal effects of interaction variables after clogit

From   Ori Katz <[email protected]>
To   [email protected]
Subject   st: marginal effects of interaction variables after clogit
Date   Mon, 26 Mar 2012 16:51:05 +0200

I am involved in a research project regarding major choice by
university applicants. my data includes ethnic origin of the
applicants, majors, and income per major (not per person). I run a
clogit model for the majors chosen, where the explanatory variables
are: majors income (the variable name is "m_inc12_jman"), and
interaction between major income and ethnic origin (the variable name
for ethnic origin is "ethnic_origin_ussr"). this is the command
clogit choice1 c.m_inc12_jman i(1
3/8)bn.ethnic_origin_ussr#c.m_inc12_jman, or group(id)

you can see that I omit ethnic origin 2 (there are 8 categories).
after the regression I try to run marginal effects, by using the
margins, dydx(*) predict(xb)

I run into two problems in the results from the margins command:

1. the results table include m_inc12_jman and ethnic_origin_ussr, but
not the interaction between them. maybe when it writes
"ethnic_origin_ussr" it is actually the interaction, but I don't know
for sure. it is a bit similar to the problem described here:

2. Stata omits ethnic origin 1 and 2 from the results, but I want to
omit only 2.

Many thanks,
Ori Katz
*   For searches and help try:

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