Re:st: Propensity Score Matching with Multiple Categorical Variables with Multiple Categories...Dummy Variables?

["Ariel Linden, DrPH" <ariel.linden@gmail.com>]

Hi Pete,

Since estimation of the propensity score is nothing more than a logistic (or
probit) regression model, you could leave the categorical variables as-is
and use the "i." prefix to denote that they are categorical, such as i.race.
The regression output will show you that the levels of the categorical
variable have been dealt with accordingly (including if any of the levels
are dropped from the model). See for example:

sysuse auto
logit foreign i.rep78

On the other hand, you could certainly create dummy variables for the
categorical variable. However, if you have a large number of covariates,
your dataset will start looking ugly in a hurry. In any case, your results
will be identical:

tab rep78, gen(rep78_)
logit foreign rep78_1- rep78_5

I hope this helps

Ariel 

Date: Fri, 13 Jul 2012 10:06:14 +0700
From: TA Stat <tastat@gmail.com>
Subject: st: Propensity Score Matching with Multiple Categorical Variables
with Multiple Categories...Dummy Variables?

Dear All

In PS matching, I am wondering about how to handle multiple
categorical variables e.g. 15 variables.  Each variable has multiple
categories e.g. 3-5 categories.  Do I have to create dummy variables,
(n-1 for each variable), for all those categorical variables before
calculating propensity score?

Thanks
Pete

*
*   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/