Can you use propensity score matching in diff?
The -diff- command also allows to use propensity score matching to create a matched sample before applying the diff-in-diff approach. You may consider this as well if it is not beyond the scope of your thesis (there is also an ongoing debate about whether using matched samples is actually a good idea).
Why do we use control group in DIFF-in-diff?
In diff-in-diff, we use data from the control group to impute untreated outcomes in the treated group. This is the “secret sauce” of diff-in-diff. Using the control group helps us learn something about the unobservable counterfactual outcomes of the treated group.
What do you call the identification of DIFF in diff?
This process is called “identification”. For diff-in-diff, identification begins with the ATT, applies the Counterfactual Assumption (1) and the Consistency Assumption, and ends with the familiar diff-in-diff estimator.
How to control for differences in control and treatment groups?
You could also consider to use additional covariates to control for differences in the control and treatment group (see the -cov- option of the -diff- command). The -diff- command also allows to use propensity score matching to create a matched sample before applying the diff-in-diff approach.
How are covariates used to reduce degrees of freedom?
They are an effective means to reduce many covariates into a single score that can be used to adjust an effect of interest for a set of variables. In doing so, you save degrees of freedom by adjusting for a single propensity score rather than multiple covariates.
Is the covariate adjustment of propensity score biased?
One popular method, covariate adjustment of the propensity score in a regression model, has been empirically shown to be biased in non-linear models. However, no compelling underlying theoretical reason has been presented.
Why do you use a single propensity score?
They are an effective means to reduce many covariates into a single score that can be used to adjust an effect of interest for a set of variables. In doing so, you save degrees of freedom by adjusting for a single propensity score rather than multiple covariates. This presents a statistical advantage, certainly, but nothing more.