Overview
The aim of the course is to introduce participants to recent methodological developments in the evaluation of public policies. These developments have shown that it is possible to circumvent most conceptual problems related to the evaluation of public policies under relatively innocuous assumptions. The importance of these developments has been underlined by the award of the Nobel Prize in Economics in 2000 to James Heckman and Daniel McFadden, the two main contributors to the field.
Course Outline
The course will take place over three days. Each daily session is divided into two parts. The first part takes place in the morning and focuses on theoretical notions. Conceptual and methodological problems are presented and solutions that have been proposed to overcome them are discussed in details. The second part takes place in the afternoon and provides hands-on experience with computer software (Stata or R) and survey data. Afternoon sessions focus on the theoretical models presented in the morning sessions.
Course Materials are availabe here for course participants only. Participants must login to access the page.
Day I
-
The Fundamental Problem:
- Determination of the control group
- Selection bias
- Attrition bias
- Social experimentation as a solution
- Empirical examples
-
Proposed solutions
- Before-After estimators
- Difference-in-differences estimator
- Cross-sectional estimators
- Two-step Heckman estimator
- Instrumental variables estimators
- Lab work
Day II
-
Propensity score matching estimators
- Difference-in-differences matching
- Multiple treatments
- Dose-Response models
- Lab work
Day III
-
Regression Discontinuity
- What it's all about....
- Fuzzy Design versus Sharp Design
- Examples
-
Ex Ante Evaluation (time allowing)
- Detailed presentation
- Examples from health economcis
- Lab work
Pre-Requisites
Knowledge of Stata or R required
APPLICATION
In order to apply for this course, AGRODEP members must complete the following by September 14, 2015:
If you would like to practice using Stata before taking the proficiency test, please review the modules below. Information included covers Stata use for beginners, linear regressions, bivariate regressions, and panel data. You will need to know this information to successfully complete the test.