콘텐츠 바로가기
로그인
컨텐츠

Category Open

Resources

tutorial

Collection of research papers and materials on development issues

home

Resources
Official Aid Others

Print

Sampling and power calculations for randomized evaluations

Related Document
Frame of Image and Type II errors – Power calculations • A Simple Example of Calculating Power
What Is Sampling and Why Do We Do It?
• In randomized evaluations we will always be comparing:
– Mean in treatment group – Mean in control group
• Population census data covering the entire treatment and comparison groups are rarely available • So we will need to estimate the group means using the averages in samples of the population
Why Does Randomized Assignment Produce an Excellent Estimate of the Counterfactual?
• Want the survey to be an accurate representation of the population as a whole • Randomness ensures that the sample reflects the population and removes bias
Why Does Sample Size Matter?
Source: Impact Evaluation in Practice, Gertler, Martinez, Premand, Rawlings, Vermeesch, World Bank 2010
Can We Detect an Impact of the Program in This Scenario?
What about in This Scenario?
Higher Standard Deviation Implies the Need for Larger Sample Sizes
Setting a Bound Around Your Estimate: Confidence Intervals
• Each sample will give a slightly different answer. So how do we use our sample to make statements about the overall population?
• A 95% confidence interval for an effect size tells us that, for 95% of all samples that we could have drawn from the same population, the effect size would fall within this estimated interval.
Comparing Average Outcomes for Treatment and Control Groups: Hypothesis Testing
We want to test: Ho: impact = 0
(The null hypothesis is that the program does not have an i


Full Text
Title Sampling and power calculations for randomized evaluations
Similar Titles
Material Type Proceedings
Author(English)

Prateek Tandon

Publisher

[Washington, DC]:The World Bank

Date 2012
Event

The Regional Impact Evaluation Workshop

Pages 27
Language English
File Type Documents
Original Format pdf
Subject Official Aid < Others
Holding KDI; KDI School

User Note

Based on slides by Deon Filmer, Jed Friedman, and Esther Duflo/JPal