Presentations

How the Chinese Government Fabricates Social Media Posts for Strategic Distraction, not Engaged Argument, at Northeastern University, Monday, September 26, 2016:

Slides

This talk is based on this paper, by me, Jennifer Pan, and Margaret Roberts, along with a brief summary of our previous work. Here's an abstract: The Chinese government has long been suspected of hiring as many as 2,000,000 people to surreptitiously insert huge numbers of pseudonymous and other deceptive writings into the stream of real social media posts, as if they were the genuine opinions of ordinary people. Many academics, and most journalists and activists, claim that...

Big Data is Not About the Data! , at Venice, Italy, Friday, September 23, 2016:

Slides

The spectacular progress the media describes as "big data" has little to do with the data. Data, after all, is becoming commoditized, less expensive, and an automatic byproduct of other changes in organizations and society. More data alone doesn't generate insights; it often merely makes data analysis harder. The real revolution isn't about the data, it is about the stunning progress in the statistical and other methods of extracting insights from the data. We illustrate these points with a wide range of examples from ...

Big Data is Not About the Data! The Power of Modern Analytics, at Civil Service College, Singapore, Friday, August 19, 2016:

Slides

How the Chinese Government Fabricates Social Media Posts for Strategic Distraction, not Engaged Argument, at DARPA, Monday, July 11, 2016:

Slides

This talk based on this paper, by me, Jennifer Pan, and Margaret Roberts, with this abstract: The Chinese government has long been suspected of hiring as many as 2,000,000 people to surreptitiously insert huge numbers of pseudonymous and other deceptive writings into the stream of real social media posts, as if they were the genuine opinions of ordinary people. Many academics, and most journalists and activists, claim that these so-called ``50c party'' posts vociferously argue for the government's...

Introduction to Perusall, at Webinar, Tuesday, April 5, 2016:

Slides (as presented)

Slides (for printing or handout)

Perusall is a new collaborative ebook platform that keeps students on track before class. Perusall ensures students learn more, get instant answers to their questions, come to class prepared (with >90% having done the reading), and enjoy the experience. It enables instructors to teach more effectively, understand student misconceptions, structure class discussion, and save time. Perusall is free. For publishers and authors, it is the ultimate solution to IP piracy, resales, and sell-through. Perusall is based on extensive patent-...

Simplifying Matching Methods for Causal Inference, at University of Pennsylvania, APPC, Friday, April 1, 2016:

Slides

In this talk, Gary King introduces methods of matching for causal inference that are simpler, more powerful, and easier to understand than prior approaches. Software is available to implement everything discussed. Copies of some of his papers on the subject are available at his web site GaryKing.org.

Discovering and Explaining Systematic Bias and Nontransparency in US Social Security Administration Forecasts, at University of Florida, Department of Political Science, Friday, March 18, 2016:

Slides

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 or anyone else. 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...

Big Data is Not About the Data!, at University of Florida, Informatics Symposium, Thursday, March 17, 2016:

Slides

In this talk, Gary King explains that the spectacular progress the media describes as "big data" has little to do with the data. Data, after all, is becoming commoditized, less expensive, and an automatic byproduct of other changes in organizations and society. More data alone doesn't generate insights; it often just makes data analysis harder. The real revolution isn't about the data, it is about the stunning progress in the statistical methods of extracting insights from the data. He will illustrate these points...

Why Propensity Scores Should Not Be Used For Matching, at Yale University, MacMillan-CSAP Workshop on Quantitative Research Methods, Thursday, March 10, 2016:

Slides

This talk summarizes a paper -- Gary King and Richard Nielsen. 2016. “Why Propensity Scores Should Not Be Used for Matching” -- with this abstract: Researchers use propensity score matching (PSM) as a data preprocessing step to selectively prune units prior to applying a model to estimate a causal effect. The goal of PSM is to reduce imbalance in the chosen pre-treatment covariates between the treated and control groups, thereby reducing the...

The Next Big [Social Science] Thing, at National Academy of Sciences, Friday, March 4, 2016:

Slides

"Dr. Gary King, NAS member and Professor at Harvard University, will talk about progress in and the future of the Social Sciences, illustrated with a wide range of examples from his research. These examples include forecasting the solvency of Social Security; reverse engineering Chinese censorship; estimating causes of death in developing countries; automated text analysis of billions of social media posts; dataverse, software and protocols his team developed to run the largest archive of...

Presentations

Pages

c05432e852e7f3fbb2c56fc04411b732