Transcript Document
Daniel Stein (DIME) Using Randomized Evaluations to Improve Policy Development Impact Evaluation Initiative innovations & solutions in infrastructure, agriculture & environment naivasha, april 23-27, 2011 in collaboration with Africa region, SD network, GAFSP and AGRA 1 What we will learn... Impact Evaluation looks to asses the causal impact of a project To assess causality of a project, we must gather data from a control group Randomly selecting people into a treatment and control group is the “gold standard” for causal inference Opportunities for randomization abound, even in large infrastructure projects! Randomization? That’s Not For Me There are opportunities for randomization in almost every project Maybe you can’t randomize the placement of water connections, but you might be able randomize: Access price Maintenance Contracts Monitoring Etc Randomization allows clear answers to YOUR questions! Overview of the Presentation Control groups and Causality Selection Bias and Randomization Opportunities for Randomization Sampling Room for improvement: before-after comparison Historically, many projects measure “impact” by looking at project indicators before and after the project implementation This is not good enough! Many things change over time naturally Impact evaluation seeks to improve on this strategy Using monitoring For impact Before-After Comparison Treatment Group 14 Is this the impact of the program? 12 10 8 6 4 2 0 Before After 6 Weather Shock!! What if there is a drought? Is this the project’s fault? 9 8 7 6 Farm 5 Income 4 3 2 1 0 Is this the impact of the program? Before After Before-After Comparison In most cases, comparing populations before and after a project is not a good measure of impact! Lots of things can affect indicators over time that have nothing to do with the project General economic growth/recession Weather World prices of commodities Need a measurement of the counterfactual: what would have happened in the absence of the project, with everything else the same Impact Evaluation and Causality Impact evaluation seeks to understand the causal effect of a program Separate the impact of the program from other factors Need to find out what would have happened without the program, or with an alternative strategy 9 What is Impact Evaluation? • Counterfactual analysis Compare same individual with & without subsidy, information etc. at the same point in time to measure the difference This is impossible! • The solution: Use a control group Need to identify people that represent what the treatment group would have been like if there was no project The Value of a Control Group Control Group Treatment Group 14 (+) Impact of the program 12 10 (+) Impact of other (external) factors 8 6 4 2 0 Before After 11 Differences in Differences Instead of comparing before after, compare the difference in before-after between the treatment and control groups Treatment Control Difference Before 8 8 0 After 14 10 4 Difference 6 2 4 Before-After Comparison Diff-inDiff Difference-in-Difference Control Group Treatment Group 14 (+) Difference-inDifference 12 10 Before-after comparison 8 6 4 2 0 Before After 13 Diff-in-Diff Major assumption for diff-in-diff: In the absence of the project, treatment and control would have to be the same. So you need a treatment and control group that are as similar as possible from the outset! Control Group Quality Control Group has to be good! Projects started at specific times and places for particular reasons What is a good control group? By design treatment and comparison have the same characteristics (observed and unobserved), on average Only difference is treatment Control group represents what would have happened to the treatment population if the project has not occurred 15 Selection Bias Can we just compare people who received the project to anyone who didn’t receive the project? Danger of Selection Bias What was the reason that some people received it and others didn’t? Selection bias a major issue for impact evaluation Projects started at specific times and places for particular reasons Participants may select into programs (eligibility criteria) First farmers to adopt a new technology are likely to be very different from the average farmer, looking at their yields will give you a misleading impression of the benefits of a new technology Danger of Selection Bias 1) Village Electrification Higher Income OR Home Electrification 2) Village is Politically Influential Higher Income from Other Sources How to create Control Group? Need to find a group of non-treated people who can proxy for people who received treatment This is hard: there is normally some reason why some people received treatment and others not, meaning any differences might not be due to the project Unless… Randomized Experimental Design Randomization is the best way to create a good control group Randomly assign potential beneficiaries to be in the treatment or comparison group By design treatment and comparison have the same characteristics (observed and unobserved), on average Only difference is treatment With large sample, all characteristics average out 19 Can we Randomize? Randomization does not mean denying people the benefits of the project Usually there are constraints within project implementation that allow randomization Opportunities for Randomization Budget constraints prevent full coverage Limited implementation capacity Randomized phase-in gives all the same chance to go first No evidence on which alternative is best Random assignment (lottery) is fair and transparent Random variation in treatment with equal ex ante chance of success Take up of existing program is not complete Encouragement design: Randomly provide information or incentive for some to sign up 21 Example: Irrigation Canal Project The government of Umbastan wants to undertake a project creating irrigation canals to farming communities It has identified 100 villages where the project is feasible and the community would likely benefit What types of randomized designs might be possible? Example: Irrigation Canal Project Possible Constraint: The government only has money to fund 50 villages Opportunity for Randomized Assignment: 50 villages to receive project could be randomly selected from 100 eligible This is a fair way to select beneficiaries Other 50 serve as control group Example: Irrigation Canal Project Possible Constraint: The government can fund 100 villages eventually, but only has time to build the canals the first year in 50 villages Opportunity for Randomized Phase-In: 50 villages to receive project in the first year This is a fair way to select who gets project in first year Other 50 serve as control group for first year Drawback is that it would be difficult to measure long term effects Example: Irrigation Canal Project Possible Constraint: There are worries that there will not be equitable distribution of water within a village Opportunity for randomized Variation in Treatment: 50 villages could receive water meters, and 50 could be organized into water user groups If the best system is unknown ex-ante, randomization can provide evidence for which is best Example: Irrigation Canal Project Possible Constraint: Worried people will not connect their fields to main canal Opportunity for Encouragement Design: Within villages that receive a canal, farmers are randomly given a course on how to use and benefit from irrigation This show the effect of the training session Also allows us to identify the effect of the irrigation project Steps to Randomizaion Choose sample for impact evaluation 1. These are people who are eligible for project and can be in treatment or control Selection of sample affects external validity only Randomize into treatment and control group 2. This step affects internal validity, allowing you to assess the impact of your project Start with sample of all possible program beneficiaries Choose who will be part of impact evaluation IE Sample: Could be part of treatment of control group Out of IE sample: Ineligible for program, or must be treated Randomize IE sample into treatment and control IE Sample: Randomly selected treatment AND control group Out of IE sample: Ineligible for program, or must be treated Actual Randomization Example: Coin Flip Village A B Treatment Group Control Group Thank you