6 Potential Outcomes, Causal Inference, and Randomized Trials

Readings

Mastering Metrics, Chapter 1

Lecture

Slides from Lecture 6

Optional Lab

This lab makes use of the data set E1-CohenEtAl-data.dta, a subset of the data used in the paper Price Subsidies, Diagnostic Tests, and Targeting of Malaria Treatment: Evidence from a Randomized Controlled Trial by Jessica Cohen, Pascaline Dupas, and Simone Schaner, published in the American Economic Review in 2015. The authors examine behavioral responses to various discounts (“subsidies”) for malaria treatment, called “artemisinin combination therapy” or “ACT.” An overview of the randomized evalaution is available here.

To complete the lab, write a script that does the following:

1. Downloads the data.
2. Runs a regression of the outcome of interest, c_act, on the treatment dummy act_any.
3. Identifies the baseline covariates (beginning with b_) that predict c_act in the control group.
4. Compares the R-squared Question 2 to the R-squared from a regression that also includes the baseline covariates that predict c_act in the control group.
5. Defines a low_education variable equal to 1 if the household head had 0 or 1 years of education, and then tests for treatment effect heterogeneity along this dimension of baseline variation.