Skip to content

Field Experiments Design, Analysis and Interpretation

Best in textbook rentals since 2012!

ISBN-10: 0393979954

ISBN-13: 9780393979954

Edition: 2012

Authors: Alan S. Gerber, Donald P. Green

Shipping box This item qualifies for FREE shipping.
Blue ribbon 30 day, 100% satisfaction guarantee!
what's this?
Rush Rewards U
Members Receive:
Carrot Coin icon
XP icon
You have reached 400 XP and carrot coins. That is the daily max!

Description:

Written by two leading experts on experimental methods, this concise text covers the major aspects of experiment design, analysis, and interpretation in clear language. Students learn how to design randomized experiments, analyze the data, and interpret the findings. Beyond the authoritative coverage of the basic methodology, the authors include numerous features to help students achieve a deeper understanding of field experimentation, including rich examples from the social science literature, problem sets and discussions, data sets, and further readings.
Customers also bought

Book details

Copyright year: 2012
Publisher: W. W. Norton & Company, Incorporated
Publication date: 5/29/2012
Binding: Paperback
Pages: 512
Size: 6.06" wide x 9.25" long x 0.98" tall
Weight: 1.804
Language: English

Preface
Introduction
Drawing Inferences from Intuitions, Anecdotes, and Correlations
Experiments as a Solution to the Problem of Unobserved Confounders
Experiments as Fair Tests
Field Experiments
Advantages and Disadvantages of Experimenting in Real-World Settings
Naturally Occurring Experiments and Quasi-Experiments
Plan of the Book
Suggested Readings
Exercises
Causal Inference and Experimentation
Potential Outcomes
Average Treatment Effects
Random Sampling and Expectations
Random Assignment and Unbiased Inference
The Mechanics of Random Assignment
The Threat of Selection Bias When Random Assignment Is Not Used
Two Core Assumptions about Potential Outcomes
Excludability
Non-interference
Summary
Suggested Readings
Exercises
Sampling Distributions, Statistical Inference, and Hypothesis Testing
Sampling Distributions
The Standard Error as a Measure of Uncertainty
Estimating Sampling Variability 59 3.4- Hypothesis Testing
Confidence Intervals
Sampling Distributions for Experiments That Use Block or Cluster Random Assignment
Block Random Assignment
Matched Pair Design
Summary of the Advantages and Disadvantages of Blocking
Cluster Random Assignment
Summary
Suggested Readings
Exercises
Power
Using Covariates in Experimental Design and Analysis
Using Covariates to Rescale Outcomes
Adjusting for Covariates Using Regression
Covariate Imbalance and the Detection of Administrative Errors
Blocked Randomization and Covariate Adjustment
Analysis of Block Randomized Experiments with Treatment Probabilities That Vary by Block
Summary
Suggested Readings
Exercises
One-Sided Noncompliance
New Definitions and Assumptions
Denning Causal Effects for the Case of One-Sided Noncompliance 13
The Non-interference Assumption for Experiments That Encounter Noncompliance
The Excludability Assumption for One-Sided Noncompliance
Average Treatment Effects, Intent-to-Treat Effects, and Complier Average Causal Effects
Identification of the CACE
Estimation
Avoiding Common Mistakes
Evaluating the Assumptions Required to Identify the CACE 15
Non-interference Assumption
Exclusion Restriction
Statistical Inference
Designing Experiments in Anticipation of Noncompliance
Estimating Treatment Effects When Some Subjects Receive "Partial Treatment"
Summary
Suggested Readings
Exercises
Two-Sided Noncompliance
Two-Sided Noncompliance: New Definitions and Assumptions
ITT, ITT<sub>D</sub>, and CACE under Two-Sided Noncompliance
A Numerical Illustration of the Role of Monotonicity
Estimation of the CACE: An Example
Discussion of Assumptions
Monotonicity
Exclusion Restriction
Random Assignment
Design Suggestions
Downstream Experimentation
Summary
Suggested Readings
Exercises
Attrition
Conditions Under Which Attrition Leads to Bias
Special Forms of Attrition
Redefining the Estimand When Attrition Is Not a Function of Treatment Assignment
Placing Bounds on the Average Treatment Effect
Addressing Attrition: An Empirical Example
Addressing Attrition with Additional Data Collection
Two Frequently Asked Questions
Summary
Suggested Readings
Exercises
Optimal Sample Allocation for Second-Round Sampling
Interference between Experimental Units
Identifying Causal Effects in the Presence of Localized Spillover
Spatial Spillover
Using Nonexperimental Units to Investigate Spillovers
An Example of Spatial Spillovers in Two Dimensions
Within-Subjects Design and Time-Series Experiments
Waitlist Designs (Also Known as Stepped-Wedge Designs)
Summary
Suggested Readings
Exercises
Heterogeneous Treatment Effects
Limits to What Experimental Data Tell Us about Treatment Effect Heterogeneity
Bounding Var (�) and Testing for Heterogeneity
Two Approaches to the Exploration of Heterogeneity: Covariates and Design
Assessmg Treatment-by-Covariate Interactions
Caution Is Required When Interpreting Treatment-by-Covariate Interactions
Assessing Treatment-by-Treatment Interactions
Using Regression to Model Treatment Effect Heterogeneity
Automating the Search for Interactions
Summary
Suggested Readings
Exercises
Mediation
Regression-Based Approaches to Mediation
Mediation Analysis from a Potential Outcomes Perspective
Why Experimental Analysis of Mediators Is Challenging
Ruling Out Mediators?
What about Experiments That Manipulate the Mediator?
Implicit Mediation Analysis
Summary
Suggested Readings
Exercises
Treatment Postcards Mailed to Michigan Households
Integration of Research Findings
Estimation of Population Average Treatment Effects
A Bayesian Framework for Interpreting Research Findings
Replication and Integration of Experimental Findings: An Example
Treatments That Vary in Intensity: Extrapolation and Statistical Modeling
Summary
Suggested Readings
Exercises
Instructive Examples of Experimental Design
Using Experimental Design to Distinguish between Competing Theories
Oversampling Subjects Based on Their Anticipated Response to Treatment
Comprehensive Measurement of Outcomes
Factorial Design and Special Cases of Non-interference
Design and Analysis of Experiments In Which Treatments Vary with Subjects' Characteristics
Design and Analysis of Experiments In Which Failure to Receive Treatment Has a Causal Effect
Addressing Complications Posed by Missing Data
Summary
Suggested Readings
Exercises
Writing a Proposal, Research Report, and Journal Article
Writing the Proposal
Writing the Research Report
Writing the Journal Article
Archiving Data
Summary
Suggested Readings
Exercises
Protection of Human Subjects
Regulatory Guidelines
Guidelines for Keeping Field Experiments within Regulatory Boundaries
Suggested Field Experiments for Class Projects
Crafting Your Own Experiment
Suggested Experimental Topics for Practicum Exercises
References
Index