Hi,
I want to compare the treatment effect on the patent quantity produced by treatment and control group. The dependent variable is patent and no other predictors. Without synthetic matching my equation looks like this:
reghdfe lnpatent treatment##post, a(assignee appyear) vce( cluster assignee)
Now for the synthetic matching, I want to match treatment and control firms based on Pre-Intervention Outcomes ONLY. As I have multiple treatment groups I have created one dummy variable called interact with the interaction of treatment and post. The code I'm using is:
synth_runner lnpatent lnpatent(1970) lnpatent(1972) lnpatent(1974), d(interact)
and its showing me the following error:
. synth_runner lnpatent lnpatent(1970) lnpatent(1972) lnpatent(1974), d(interact)
(9834 missing values generated)
Estimating the treatment effects
Error estimating treatment effect for unit 1045
Re-running last -synth- command with output/errors un-captured
------------------------------------------------------------------------------------------------------------------------
Synthetic Control Method for Comparative Case Studies
------------------------------------------------------------------------------------------------------------------------
First Step: Data Setup
------------------------------------------------------------------------------------------------------------------------
invalid numlist has too few elements
r(122);
Any help is appreciated.
Regards,
Syeda
Related Posts with Synthetic matching with Pre-Intervention Outcomes ONLY
Identify excluded observations from mixedI'm working with longitudinal panel data and running models using the mixed command. In prepping the…
xtgee how to create a linear graph with confidence interval for the adjusted modelI am running xtgee to assess the association between change in heart dimension (pch_rveda) and time …
Making marginsplots equal size with graph combineHi Statalist, I'm struggling with a graphing issue perhaps someone can help me with. I'm trying to …
Local macro in "forvalues" functionMy first post here, but have used this forum extensively in the past to trouble shoot. However, can'…
-mi estimate- used for analysis of imputed variables only?I have used multiple imputations on 2 variables, say a and b. Specifically, for some simplified mod…
Subscribe to:
Post Comments (Atom)
0 Response to Synthetic matching with Pre-Intervention Outcomes ONLY
Post a Comment