Browse IFS
Publication types
Programme Evaluation for Policy Analysis
Research
Article
Microeconometric methods in policy evaluation
Part of: Programme evaluation for policy analysis
Date started: 15 November 2012

The relationship between different approaches to policy evaluation often leaves the user bewildered as to which approach is the most reliable. However, the idea that there is one ideal approach for all policy evaluations is misleading. This project has two main objectives. The first is to establish the key relationships between alternative methods for policy evaluation and advance methods where better identification strategies can be devised. We propose to use substantive applications to training, education, tax and welfare policies to illustrate how to make best use of each method and how to interpret the results of their application to the measurement of policy impact. Second, we will pick up the question of research synthesis and examine how best to combine the results from different studies.

  • What is the link between control functions and structural or behavioural models?
  • Can we weaken the control function approach to estimate bounds on treatment effect?
  • How are lessons from multiple evaluations best synthesised?
Related publications
Publications by type

01 January 2013
Journal Articles
Article

Matching methods for treatment evaluation based on a conditional independence assumption do not balance selective unobserved differences between treated and non-treated. We derive a simple correction term if there is an instrument that shifts the treatment probability to zero in special cases. Policies with eligibility restrictions, where treatment is impossible if some variable exceeds a certain value, provide a natural application. In an empirical analysis, we exploit the age eligibility restriction in the Swedish Youth Practice subsidized work program for young unemployed, where compliance is imperfect among the young. Adjusting the matching estimator for selectivity changes the results towards making subsidized work detrimental in moving individuals into employment.

23 October 2012
cemmap Working Papers
Article
In this paper the authors study a random coefficient model for a binary outcome.
22 August 2012
cemmap Working Papers
Article
This paper studies simultaneous equations models for two or more discrete outcomes.
05 July 2012
Presentations
Article

We review popular evaluation methods in policy analysis, showing the relationship between social experiments (randomised control trials), matching methods, instrumental variables, and control functions.

This presentation was delivered as part of the PEPA contribution to the 2012 ESRC Research Methods Festival.

05 July 2012
Presentations
Article
This talk gives an overview of evaluation methods in microeconomic policy, in particular those based on randomized trials and IV methods.
13 January 2012
Presentations
Article
This presentation was given by Monica Costa Dias at the NCRM 2012 Annual Centre Meeting.
Pepa Partners

CEMMAP

Funders

ESRC National Centre for Research Methods