Gary King

Gary King is the David Florence Professor of Government in the Department of Government (in the Faculty of Arts and Sciences) at Harvard University. He also serves as Director of the Institute for Quantitative Social Science. King and his research group develop and apply statistical and other methods in many areas of social science research, focusing on innovations that span the range from statistical theory to practical application. For more information, see his short bio and curriculum vitae.

King's work can be found categorized by type (recent writings, published articles, books, and software, and public presentations) or alternatively by research areas:

Causal Inference: Methods for detecting and reducing model dependence (when minor model changes produce substantively different inferences) in inferring counterfactuals (such as predictions, what-if questions, and causal effects). Matching methods; a "politically robust" and cluster-randomized experimental designs; a causal bias decompositions; software; and applications.
Content Analysis: Automated methods of extracting information from text documents and for correcting for errors by human coders.
Data Sharing and Informatics: New standards, protocols, and software for citing, sharing, analyzing, archiving, preserving, distributing, cataloging, translating, disseminating, naming, verifying, and replicating quantitative data and associated analyses. Also includes proposals to improve the norms of data sharing and replication in science.
Ecological Inference (Inferring Individual Behavior from Group-Level Data): The original methods that incorporate both unit-level deterministic bounds and cross-unit statistical information, methods for 2x2 and larger tables, Bayesian model averaging, applications to elections, EI/EzI software.
Event Counts and Duration Models: Develops statistical models to explain how many events occur for each fixed time period, or the time between events. An application to cabinet dissolution in parliamentary democracies united two previously waring scholarly literatures. Other applications in international relations, and Supreme Court appointments.
Incumbency Advantage: Proof that previously used estimators of the electoral advantage of having served in office before were biased, and a new unbiased estimator. Also, the first systematic demonstration that constituency service by legislators increases the incumbency advantage.
International Conflict: Evidence that the causes of conflict, theorized to be important but often found to be small or ephemeral, are indeed tiny for the vast majority of dyads, but they are large, stable, and replicable wherever the ex ante probability of conflict is large. Also methods for coding, analyzing, and forecasting international conflict and state failure.
Legislative Redistricting: Defining partisan symmetry as a standard for fairness; measuring partisan bias and electoral responsiveness; discussion of U.S. Supreme Court rulings on this work. Evidence that U.S. redistricting reduces bias and increases responsiveness, and that the electoral college is fair; applications to legislatures, primaries, and multiparty systems; JudgeIt Software.
Missing Data: Statistical methods to accommodate missing information in data sets due to scattered nonresponse or to entire missing survey questions. Introduces the first fast and easy-to-use algorithm for multiple imputation, resulting in the widespread use of both. Applications to electoral, and other compositional data.
Mortality Studies: Methods for estimating cause-specific and overall mortality rates in areas without vital registration; forecasting mortality rates (hierarchically, for time series data cross-classified by age, sex, country, and cause); measuring inequality in risk of death.
Presidency Research, and Voting Behavior: Resolution of the paradox of why polls are so variable over time during presidential campaigns even though the vote outcome is easily predictable before it starts. Also, a resolution of a key controversy over absentee ballots during the 2000 presidential election; and the methodology of small-n research on executives.
Qualitative Research: How the same unified theory of inference underlies quantitative and qualitative research alike; scientific inference when quantification is difficult or impossible; research design; empirical research in legal scholarship.
Rare Events: How to save 99% of your data collection costs; bias corrections for logistic regression in estimating probabilities and causal effects in rare events data; estimating base probabilities or any quantity from case-control data; automated coding of events.
Survey Research: "Anchoring Vignette" Methods for when different respondents (perhaps from different cultures, countries, or ethnic groups) understand survey questions in different ways; an approach to developing theoretical definitions of complicated concepts apparently definable only by example (i.e., "you know it when you see it"); how surveys work.
Unifying Statistical Analysis: Development of a unified approach to statistical modeling, inference, interpretation, presentation, analysis, and software; integrated with most of the other projects listed here.

You may also find the following of interest:

U.S. Supreme Court responds to Amici Curiae Brief filed on partisan symmetry as a standard for evaluating partisan gerrymandering, see this paper for details, an outgrowth of related research
Social Science Statistics Blog
Workshop in Applied Statistics