| |
| |
| Preface | |
| |
| |
| |
| The Challenge for Educational Research | |
| |
| |
| The Long Quest | |
| |
| |
| The Quest Is Worldwide | |
| |
| |
| What This Book Is About | |
| |
| |
| What to Read Next | |
| |
| |
| |
| The Importance of Theory | |
| |
| |
| What Is Theory? | |
| |
| |
| Theory in Education | |
| |
| |
| Voucher Theory | |
| |
| |
| What Kind of Theories? | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Designing Research to Address Causal Questions | |
| |
| |
| Conditions to Strive for in All Research | |
| |
| |
| Making Causal Inferences | |
| |
| |
| Past Approaches to Answering Causal Questions in Education | |
| |
| |
| The Key Challenge of Causal Research | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Investigator-Designed Randomized Experiments | |
| |
| |
| Conducting Randomized Experiments | |
| |
| |
| The Potential Outcomes Framework | |
| |
| |
| An Example of a Two-Group Experiment | |
| |
| |
| Analyzing Data from Randomized Experiments | |
| |
| |
| The Better Your Research Design, the Simpler Your Data Analysis | |
| |
| |
| Bias and Precision in the Estimation of Experimental Effects | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Challenges in Designing, Implementing, and Learning from Randomized Experiments | |
| |
| |
| Critical Decisions in the Design of Experiments | |
| |
| |
| Defining the Treatment | |
| |
| |
| Defining the Population from Which Participants Will Be Sampled | |
| |
| |
| Deciding Which Outcomes to Measure | |
| |
| |
| Deciding How Long to Track Participants | |
| |
| |
| Threats to the Validity of Randomized Experiments | |
| |
| |
| Contamination of the Treatment-Control Contrast | |
| |
| |
| Cross-overs | |
| |
| |
| Attrition from the Sample | |
| |
| |
| Participation in an Experiment Itself Affects Participants' Behavior | |
| |
| |
| Gaining Support for Conducting Randomized Experiments: Examples from India | |
| |
| |
| Evaluating an Innovative Input Approach | |
| |
| |
| Evaluating an Innovative Incentive Policy | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Statistical Power and Sample Size | |
| |
| |
| Statistical Power | |
| |
| |
| Reviewing the Process of Statistical Inference | |
| |
| |
| Defining Statistical Power | |
| |
| |
| Factors Affecting Statistical Power | |
| |
| |
| The Strengths and Limitations of Parametric Tests | |
| |
| |
| The Benefits of Covariates | |
| |
| |
| The Reliability of the Outcome Measure Matters | |
| |
| |
| The Choice Between One-Tailed and Two-Tailed Tests | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Experimental Research When Participants Are Clustered Within Intact Groups | |
| |
| |
| Random-Intercepts Multilevel Model to Estimate Effect Size When Intact Groups Are Randomized to Experimental Conditions | |
| |
| |
| Statistical Power When Intact Groups of Participants Are Randomized to Experimental Conditions | |
| |
| |
| Statistical Power of the Cluster-Randomized Design and Intraclass Correlation | |
| |
| |
| Fixed-Effects Multilevel Models to Estimate Effects Size When Intact Groups of Participants Are Randomized to Experimental Conditions | |
| |
| |
| Specifying a Fixed-Effects Multilevel Model | |
| |
| |
| Choosing Between Random-and Fixed-Effects Specifications | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Using Natural Experiments to Provide "Arguably Exogenous" Treatment Variability | |
| |
| |
| Natural- and Investigator-Designed Experiments: Similarities and Differences | |
| |
| |
| Two Examples of Natural Experiments | |
| |
| |
| The Vietnam-Era Draft Lottery | |
| |
| |
| The Impact of an Offer of Financial Aid for College | |
| |
| |
| Sources of Natural Experiments | |
| |
| |
| Choosing the Width of the Analytic Window | |
| |
| |
| Threats to Validity in Natural Experiments with a Discontinuity Design | |
| |
| |
| Accounting for the Relationship Between the Outcome and the Forcing Variable in a Discontinuity Design | |
| |
| |
| Actions by Participants Can Undermine Exogenous Assignment to Experimental Conditions in a Natural Experiment with a Discontinuity Design | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Estimating Causal Effects Using a Regression-Discontinuity Approach | |
| |
| |
| Maimonides' Rule and the Impact of Class Size on Student Achievement | |
| |
| |
| A Simple First-Differences Analysis | |
| |
| |
| A Difference-in-Differences Analysis | |
| |
| |
| A Basic Regression-Discontinuity Analysis | |
| |
| |
| Choosing an Appropriate Bandwidth | |
| |
| |
| Generalizing the Relationship Between the Outcome and the Forcing Variable | |
| |
| |
| Specification Checks Using Pseudo-Outcomes and Pseudo-Cut-Offs | |
| |
| |
| Regression-Discontinuity Designs and Statistical Power | |
| |
| |
| Additional Threats to Validity in a Regression-Discontinuity Design | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Introducing Instrumental-Variables Estimation | |
| |
| |
| Introducing Instrumental-Variables Estimation | |
| |
| |
| Bias in the OLS Estimate of the Causal Effect of Education on Civic Engagement | |
| |
| |
| Instrumental-Variable Estimation | |
| |
| |
| Two Critical Assumptions That Underpin Instrumental-Variables Estimation | |
| |
| |
| Alternative Ways of Obtaining the Instrumental-Variables Estimate | |
| |
| |
| Obtaining an Instrumental-Variables Estimate by the Two-Stage Least-Squares Method | |
| |
| |
| Obtaining an Instrumental-Variables Estimate by Simultaneous-Equations Estimation | |
| |
| |
| Extensions of the Basic Instrumental-Variable Estimation Approach | |
| |
| |
| Incorporating Exogenous Covariates into Instrumental-Variable Estimation | |
| |
| |
| Incorporating Multiple Instruments into the First-Stage Model | |
| |
| |
| Examining the Impact of Interactions Between the Endogenous Question Predictor and Exogenous Covariates in the Second-Stage Model | |
| |
| |
| Choosing Appropriate Functional Forms for Outcome/Predictor Relationships in First- and Second-Stage Models | |
| |
| |
| Finding and Defending Instruments | |
| |
| |
| Proximity of Educational Institutions | |
| |
| |
| Institutional Rules and Personal Characteristics | |
| |
| |
| Deviations from Cohort Trends | |
| |
| |
| The Search Continues | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Using IVE to Recover the Treatment Effect in a Quasi-Experiment | |
| |
| |
| The Notion of a "Quasi-Experiment" | |
| |
| |
| Using IVE to Estimate the Causal Impact of a Treatment in a Quasi-Experiment | |
| |
| |
| Further Insight into the IVE (LATE) Estimate, in the Context of Quasi-Experimental Data | |
| |
| |
| Using IVE to Resolve "Fuzziness" in a Regression-Discontinuity Design | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Dealing with Bias in Treatment Effects Estimated from Nonexperimental Data | |
| |
| |
| Reducing Observed Bias by the Method of Stratification | |
| |
| |
| Stratifying on a Single Covariate | |
| |
| |
| Stratifying on Covariates | |
| |
| |
| Reducing Observed Bias by Direct Control for Covariates Using Regression Analysis | |
| |
| |
| Reducing Observed Bias Using a Propensity-Score Approach | |
| |
| |
| Estimation of the Treatment Effect by Stratifying on Propensity Scores | |
| |
| |
| Estimation of the Treatment Effect by Matching on Propensity Scores | |
| |
| |
| Estimation of the Treatment Effect by Weighting by the Inverse of the Propensity Scores | |
| |
| |
| A Return to the Substantive Question | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Methodological Lessons from the Long Quest | |
| |
| |
| Be Clear About Your Theory of Action | |
| |
| |
| Learn About Culture, Rules, and Institutions in the Research Setting | |
| |
| |
| Understand the Counterfactual | |
| |
| |
| Always Worry About Selection Bias | |
| |
| |
| Use Multiple Outcome Measures | |
| |
| |
| Be on the Lookout for Longer-Term Effects | |
| |
| |
| Develop a Plan for Examining Impacts on Subgroups | |
| |
| |
| Interpret Your Research Results Correctly | |
| |
| |
| Pay Attention to Anomalous Results | |
| |
| |
| Recognize That Good Research Always Raises New Questions | |
| |
| |
| What to Read Next | |
| |
| |
| |
| Substantive Lessons and New Questions | |
| |
| |
| |
| Lower the Cost of School Enrollment | |
| |
| |
| Reduce Commuting Time | |
| |
| |
| Reduce Out-of-Pocket Educational Costs | |
| |
| |
| Reduce Opportunity Costs | |
| |
| |
| |
| Change Children's Daily Experiences in School | |
| |
| |
| More Books? | |
| |
| |
| Smaller Classes? | |
| |
| |
| Better Teaching? | |
| |
| |
| |
| Improve Incentives | |
| |
| |
| Improve Incentives for Teachers | |
| |
| |
| Improve Incentives for Students | |
| |
| |
| |
| Create More Schooling Options for Poor Children | |
| |
| |
| New Private-School Options | |
| |
| |
| New Public-School Options | |
| |
| |
| Summing Up | |
| |
| |
| Final Words | |
| |
| |
| References | |
| |
| |
| Index | |