Hi All
I have two sets of data with values 0 and 1. The number of observations for dataset of value 0 is 14,000 and number of observations for dataset of value 1 is only 3,000. Thus, I am now hoping to match these two datasets through propensity score matching and then run my regression analysis. I wish to match in a way that treated and control sample firms are similar in size, industry etc.
I tried psmatch2 and it does not give a good match as number of observations in treated and control group are still very different.
I think I have to use some loop code.
I did help psmatch2 in stata and that showed me following loop code:
g att = .
egen g = group(groupvars)
levels g, local(gr)
qui foreach j of local gr {
psmatch2 treatvar varlist if g==`j', out(outvar)
replace att = r(att) if g==`j'
}
sum att
However, I am not sure how to use it for the kind of match I need (based on firm size, industry, etc.)
Can someone please advise what code should I use to do this match? or if someone has done similar match in the past.
Thank you heaps for the help!
Related Posts with Propensity Score Matching
regressionsHello, I have daily stock returns for the market and for companies. I want to run this model (reg r…
Fama FrenchA new day a new question. I have now done a rolling window regression according to CAPM model and th…
spell-type data/survival time analysesDear stata list, I am running survival time analyses and my goal is to create a survival time varia…
Using -atjoint- in -margins- targeting only one at() condition when multiple at() are specifiedI am working on a logit model containing one interaction between a continuous and a dummy variable. …
replacing missing valuesHello, I have two variables, one is a code identifier for companies (permno), and another is return…
Subscribe to:
Post Comments (Atom)
0 Response to Propensity Score Matching
Post a Comment