Gary King is the Weatherhead University Professor at Harvard University. He also serves as Director of the Institute for Quantitative Social Science. He and his research group develop and apply empirical methods in many areas of social science research. Full bio and CV

Research Areas

    • Evaluating Social Security Forecasts
      The accuracy of U.S. Social Security Administration (SSA) demographic and financial forecasts is crucial for the solvency of its Trust Funds, government programs comprising greater than 50% of all federal government expenditures, industry decision making, and the evidence base of many scholarly articles. Forecasts are also essential for scoring policy proposals, put forward by both political parties. Because SSA makes public little replication information, and uses ad hoc, qualitative, and antiquated statistical forecasting methods, no one in or out of government has been able to produce fully independent alternative forecasts or policy scorings. Yet, no systematic evaluation of SSA forecasts has ever been published by SSA or anyone else. We show that SSA's forecasting errors were approximately unbiased until about 2000, but then began to grow quickly, with increasingly overconfident uncertainty intervals. Moreover, the errors all turn out to be in the same potentially dangerous direction, each making the Social Security Trust Funds look healthier than they actually are. We also discover the cause of these findings with evidence from a large number of interviews we conducted with participants at every level of the forecasting and policy processes. We show that SSA's forecasting procedures meet all the conditions the modern social-psychology and statistical literatures demonstrate make bias likely. When those conditions mixed with potent new political forces trying to change Social Security and influence the forecasts, SSA's actuaries hunkered down trying hard to insulate themselves from the intense political pressures. Unfortunately, this otherwise laudable resistance to undue influence, along with their ad hoc qualitative forecasting models, led them to also miss important changes in the input data such as retirees living longer lives, and drawing more benefits, than predicted by simple extrapolations. We explain that solving this problem involves using (a) removing human judgment where possible, by using formal statistical methods -- via the revolution in data science and big data; (b) instituting formal structural procedures when human judgment is required -- via the revolution in social psychological research; and (c) requiring transparency and data sharing to catch errors that slip through -- via the revolution in data sharing & replication.An article at Barron's about our work.
    • Incumbency Advantage
      Proof that previously used estimators of electoral incumbency advantage were biased, and a new unbiased estimator. Also, the first systematic demonstration that constituency service by legislators increases the incumbency advantage.
    • Information Control by Authoritarian Governments
      Reverse engineering Chinese information controls -- the most extensive effort to selectively control human expression in the history of the world. We show that this massive effort to slow the flow of information paradoxically also conveys a great deal about the intentions, goals, and actions of the leaders. We downloaded all Chinese social media posts before the government could read and censor them; wrote and posted comments randomly assigned to our categories on hundreds of websites across the country to see what would be censored; set up our own social media website in China; and discovered that the Chinese government fabricates and posts 450 million social media comments a year in the names of ordinary people and convinced those posting (and inadvertently even the government) to admit to their activities. We found that the goverment does not engage on controversial issues (they do not censor criticism or fabricate posts that argue with those who disagree with the government), but they respond on an emergency basis to stop collective action (with censorship, fabricating posts with giant bursts of cheerleading-type distractions, responding to citizen greviances, etc.). They don't care what you think of them or say about them; they only care what you can do.
    • Mexican Health Care Evaluation
      An evaluation of the Mexican Seguro Popular program (designed to extend health insurance and regular and preventive medical care, pharmaceuticals, and health facilities to 50 million uninsured Mexicans), one of the world's largest health policy reforms of the last two decades. Our evaluation features a new design for field experiments that is more robust to the political interventions and implementation errors that have ruined many similar previous efforts; new statistical methods that produce more reliable and efficient results using fewer resources, assumptions, and data; and an implementation of these methods in the largest randomized health policy experiment to date. (See the Harvard Gazette story on this project.)
    • Presidency Research; 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.
    • Informatics and Data Sharing
      Replication Standards New standards, protocols, and software for citing, sharing, analyzing, archiving, preserving, distributing, cataloging, translating, disseminating, naming, verifying, and replicating scholarly research data and analyses. Also includes proposals to improve the norms of data sharing and replication in science.
    • International Conflict
      Methods for coding, analyzing, and forecasting international conflict and state failure. 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 are large, stable, and replicable wherever the ex ante probability of conflict is large.
    • Legislative Redistricting
      The definition of partisan symmetry as a standard for fairness in redistricting; methods and software for measuring partisan bias and electoral responsiveness; discussion of U.S. Supreme Court rulings about 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.
    • Mortality Studies
      Methods for forecasting mortality rates (overall or for time series data cross-classified by age, sex, country, and cause); estimating mortality rates in areas without vital registration; measuring inequality in risk of death; applications to US mortality, the future of the Social Security, armed conflict, heart failure, and human security.
    • Teaching and Administration
      Publications and other projects designed to improve teaching, learning, and university administration, as well as broader writings on the future of the social sciences.
    • Automated Text Analysis
      Automated and computer-assisted methods of extracting, organizing, understanding, conceptualizing, and consuming knowledge from massive quantities of unstructured text.
    • Anchoring Vignettes (for interpersonal incomparability)
      Methods for interpersonal incomparability, when respondents (from different cultures, genders, countries, or ethnic groups) understand survey questions in different ways; for developing theoretical definitions of complicated concepts apparently definable only by example (i.e., "you know it when you see it").
    • Causal Inference
      Methods for detecting and reducing model dependence (i.e., when minor model changes produce substantively different inferences) in inferring causal effects and other counterfactuals. Matching methods; "politically robust" and cluster-randomized experimental designs; causal bias decompositions.
    • Event Counts and Durations
      Statistical models to explain or predict how many events occur for each fixed time period, or the time between events. An application to cabinet dissolution in parliamentary democracies which united two previously warring scholarly literature. Other applications to international relations and U.S. Supreme Court appointments.
    • Ecological Inference
      Inferring individual behavior from group-level data: The first approach to incorporate both unit-level deterministic bounds and cross-unit statistical information, methods for 2x2 and larger tables, Bayesian model averaging, applications to elections, software.
    • Missing Data & Measurement Error
      Statistical methods to accommodate missing information in data sets due to scattered unit nonresponse, missing variables, or values or variables measured with error. Easy-to-use algorithms and software for multiple imputation and multiple overimputation for surveys, time series, and time series cross-sectional data. Applications to electoral, and other compositional, data.
    • 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
      How surveys work and a variety of methods to use with surveys. Surveys for estimating death rates, why election polls are so variable when the vote is so predictable, and health inequality.
    • 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.

Recent Papers

How Not to Lie With Statistics: Avoiding Common Mistakes in Quantitative Political Science

How Not to Lie With Statistics: Avoiding Common Mistakes in Quantitative Political Science
Gary King. 1986. “How Not to Lie With Statistics: Avoiding Common Mistakes in Quantitative Political Science.” American Journal of Political Science, 30, Pp. 666–687.Abstract
This article identifies a set of serious theoretical mistakes appearing with troublingly high frequency throughout the quantitative political science literature. These mistakes are all based on faulty statistical theory or on erroneous statistical analysis. Through algebraic and interpretive proofs, some of the most commonly made mistakes are explicated and illustrated. The theoretical problem underlying each is highlighted, and suggested solutions are provided throughout. It is argued that closer attention to these problems and solutions will result in more reliable quantitative analyses and more useful theoretical contributions.
Read more

The Significance of Roll Calls in Voting Bodies: A Model and Statistical Estimation

The Significance of Roll Calls in Voting Bodies: A Model and Statistical Estimation
Gary King. 1986. “The Significance of Roll Calls in Voting Bodies: A Model and Statistical Estimation.” Social Science Research, 15, Pp. 135–152.Abstract
In the long history of legislative roll call analyses, there continues to exist a particularly troubling problem: There is no satisfactory method for measuring the relative importance or significance of individual roll calls. A measure of roll call significance would be interesting in and of itself, but many have realized that it could also substantially improve empirical research. The consequence of this situation is that hundreds of researchers risk heteroskedastic disturbances (resulting in inefficient estimates and biased standard errors and test statistics), are unable to appropriately choose the roll calls most suited to their theory (resulting in analyses that may not correctly test their theory), and often use methods that create more problems than they solve (resulting in selection bias, unrealistic weighting schemes, or relatively subjective measures). This article introduces a new method designed to meet these problems. Based on an application of Box-Tiao intervention analysis, the method extracts from observed voting participation scores the "revealed preferences" of legislators as a measure of roll call significance. Applying this method to roll calls from the U.S. Senate demonstrates the success of the method and suggests its utility in applied research.
Read more

Democratic Representation and Partisan Bias in Congressional Elections

Democratic Representation and Partisan Bias in Congressional Elections
Gary King and Robert X Browning. 1987. “Democratic Representation and Partisan Bias in Congressional Elections.” American Political Science Review, 81, Pp. 1252–1273.Abstract
The translation of citizen votes into legislative seats is of central importance in democratic electoral systems. It has been a longstanding concern among scholars in political science and in numerous other disciplines. Through this literature, two fundamental tenets of democratic theory, partisan bias and democratic representation, have often been confused. We develop a general statistical model of the relationship between votes and seats and separate these two important concepts theoretically and empirically. In so doing, we also solve several methodological problems with the study of seats, votes and the cube law. An application to U.S. congressional districts provides estimates of bias and representation for each state and deomonstrates the model’s utility. Results of this application show distinct types of representation coexisting in U.S. states. Although most states have small partisan biases, there are some with a substantial degree of bias.
Read more

Seats, Votes, and Gerrymandering: Measuring Bias and Representation in Legislative Redistricting

Seats, Votes, and Gerrymandering: Measuring Bias and Representation in Legislative Redistricting
Robert X Browning and Gary King. 1987. “Seats, Votes, and Gerrymandering: Measuring Bias and Representation in Legislative Redistricting.” Law and Policy, 9, Pp. 305–322.Abstract
The Davis v. Bandemer case focused much attention on the problem of using statistical evidence to demonstrate the existence of political gerrymandering. In this paper, we evaluate the uses and limitations of measures of the seat-votes relationship in the Bandemer case. We outline a statistical method we have developed that can be used to estimate bias and the form of representation in legislative redistricting. We apply this method to Indiana State House and Senate elections for the period 1972 to 1984 and demonstrate a maximum bias 6.2% toward the Republicans in the House and a 2.8% bias in the Senate.
Read more

Political Parties and Foreign Policy: A Structuralist Approach

Political Parties and Foreign Policy: A Structuralist Approach
Gary King. 1986. “Political Parties and Foreign Policy: A Structuralist Approach.” Political Psychology, 7, Pp. 83–101.Abstract
This article introduces the theory and approach of structural anthropology and applies it to a problem in American political science. Through this approach, the "bipartisan foreign policy hypothesis" and that "two presidencies hypothesis" are reformulated and reconsidered. Until now participants in the debate over each have only rarely built on, or even cited, the other’s research. An additional problem is that the widespread conventional wisdom in support of the two hypotheses is inconsistent with systematic scholarly analyses. This paper demonstrates that the two hypotheses are drawn from the same underlying structure. Each hypothesis and the theoretical model it implies is conceptually and empirically extended to take into account the differences between congressional leaders and members. Then, historical examples and statistical analyses of House roll call data are used to demonstrate that the hypotheses, while sometimes supported for the congressional members, are far more applicable to leadership decision making. Conclusions suggest that conventional wisdom be revised to take these differences into account.
Read more

The Development of Political Activists: A Model of Early Learning

The Development of Political Activists: A Model of Early Learning
Gary King and Richard Merelman. 1986. “The Development of Political Activists: A Model of Early Learning.” Social Science Quarterly, 67, Pp. 473–490.Abstract
An analysis of panel data reveals the unique importance of early learning to the development of political activism among Americans. A combination of two learning models– the frequently used crystallization model and the rarely analyzed sensitization model– is advanced as most appropriate for understanding political socialization and the development of political activism. The findings contribute to research on elite behavior and on the process of political socialization.
Read more
All writings

Presentations

Simplifying Matching Methods for Causal Inference, at Center for Virology and Vaccine Research, Beth Israel Deaconess Medical Center, Harvard Medical School, Friday, March 9, 2018:
We show how to use matching in causal inference to ameliorate model dependence -- where small, indefensible changes in model specification have large impacts on our conclusions. We introduce matching methods that are simpler, more powerful, and easier to understand than existing approaches. We also show that the most commonly used existing method, propensity score matching, should rarely be used in practice. Easy-to-use software is available to implement all methods discussed.
How the news media activate public expression and influence national agendas Friday, February 16, 2018:
This talk reports on the results of first large scale randomized news media experiment. We demonstrate that even small news media outlets can cause large numbers of Americans to take public stands on specific issues, join national policy conversations, and express themselves publicly—all key components of democratic politics—more often than they would otherwise. After recruiting 48 mostly small media outlets, and working with them over 5 years, we chose groups of these outlets to write and publish articles on subjects we approved, on dates we randomly assigned. We estimate the causal effect... Read more about How the news media activate public expression and influence national agendas
How to Measure Legislative District Compactness If You Only Know it When You See it, at Stony Brook University, Institute for Advanced Computational Science, Thursday, February 15, 2018:
To prevent gerrymandering and to encourage a form of democratic representation, many state constitutions and judicial opinions require US legislative districts be "compact." Yet, few precise definitions are offered other than "you know it when you see it," effectively assuming the existence of a common understanding of the concept. In contrast, academics have concluded that the concept has multiple theoretical dimensions requiring large numbers of conflicting empirical measures. This has proved extremely challenging for courts tasked with adjudicating compactness. We hypothesize that both are... Read more about How to Measure Legislative District Compactness If You Only Know it When You See it
Matching Methods for Causal Inference, at Microsoft, Cambridge, Friday, January 19, 2018:
This presentation shows how to use matching in causal inference to ameliorate model dependence -- where small, indefensible changes in model specification have large impacts on our conclusions. We introduce matching methods that are simpler, more powerful, and easier to understand. We also show that the most commonly used existing method, propensity score matching, should rarely be used. Easy-to-use software is available to implement all methods discussed.
All presentations

Books

  • «
  • 2 of 2
  •  
All writings

Gary King on Twitter

  • kinggary
    kinggary Many thanks to all my friends at Dartmouth for a great visit; it was a privilege getting to interact over the last few days.
  • thresher_io
    thresher_io Thanks for the recap Technically Media and the chance to demo at the DC Tech Meetup Selina McPherson and team. Glad our demo hit the mark. 'When Fair finished her presentation, the first question she got was: “Where can I get it?"' t.co/8m14r7hUfb
  • kinggary
    kinggary Looking forward to seeing everyone at Dartmouth tomorrow for my talks about an experiment where we randomized what 48 news media outlets published (12:45 Haldeman 41) and on matching methods for causal inference (4pm Silsby 119). Slides at t.co/Zi0QLQs669