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]

st: how to test DD assumption about the similar trend before treatment


From   "Li, Rui (CDC/ONDIEH/NCCDPHP)" <eok8@cdc.gov>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: how to test DD assumption about the similar trend before treatment
Date   Wed, 19 Oct 2011 20:13:02 +0000

Hi,

I am brand new to the group. I did check the FAQs. However If I ask questions being answered before, please forgive me.

I am using a DD model and testing whether the treatment group and control group have similar trend before the policy changed (repeated cross-sectional data). I have at least 5 years of pre-policy data. I tested by the following two ways:

1. Add a year trend and interaction between year and treatment group, then if the interaction terms was not significant, I concluded that the two groups had similar trend before the policy change (like a linear spline analysis with the year before policy change as the knot).
2. Run separate regressions for treatment group and control group using only pre-policy data, I coded the year variables as categorically data because the time trend might not be linear. Then I compared each coefficient for the year variables in the two regression analysis using ttest. 

Are these the right ways to test the assumption?

Thanks!

Rui



*
*   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