What is Impact Evaluation?
Impact evaluation(IEs) are studies performed to isolate effects of a program/intervention from other external factors or potential selection bias so that observed outcomes can be attributed to the intervention itself. The sole purpose of Impact evaluation is to quantify/answer cause-and-effect questions about an intervention.
Impact evaluations are divided into two categories: Quasi-experimental and experimental(Randomized Controlled Studies).Both categories rely on the same concept - of using the counterfactual to estimate the changes caused by the intervention.
A Counterfactual scenario is what would have happened in the absence of the intervention.
Key challenge for an impact evaluation is how to identify a valid comparison group- which is a group of subjects that closely resemble the characteristics of the group that received the intervention, but that did not receive the intervention.This comparison group should have on average, the same characteristics as the treatment group at baseline.
In sequel, there exist several methods of developing comparison groups. including.
Randomized controlled trials (RCTs)/randomized experiments/randomized evaluations-selection of individuals into the control and treatment groups are chosen purely at random from a group of eligible participants.
Quasi-experimental designs employs statistical
methods to create a comparison group, which has the same characteristics
as the treatment group, apart from treatment.This method is often used
when it is not possible to randomize individuals or groups
to treatment and control groups *
I shall explore each of the following methods of constructing a
comparison group and demonstrate how it is implemented in
R.*
Propensity score matching (PSM)
Difference-in-Differences(DID)
Regression Discontinuity design (RDD)