Presented By O'Reilly and Cloudera
Make Data Work
September 26–27, 2016: Training
September 27–29, 2016: Tutorials & Conference
New York, NY

Statistics, machine learning, and the crazy 2016 election

Sam Wang (Princeton University)
10:25am–10:45am Thursday, 09/29/2016
Location: Javits North
Tags: politics
Average rating: ***..
(3.85, 13 ratings)

Get the free Ebook:
Data and Democracy.

Although 2016 is a highly unusual political year, elections and public opinion follow predictable statistical properties. Sam Wang explains how the presidential, Senate, and House races can be tracked and forecast from freely available polling data using tools from statistics and machine learning. These approaches offer a deeper understanding of the US political scene, even under extreme circumstances.

Photo of Sam Wang

Sam Wang

Princeton University

Sam Wang pioneered the science of data-based political prediction later popularized by Nate Silver. Like Nate, Sam has harnessed the power of big data to yield astonishingly accurate predictions of the last several American elections. In 2008 and 2012, Sam called 49 out of 50 states correctly; in 2004, he was 50 for 50. Sam’s project, the Princeton Election Consortium, analyzes polls across the US to create a single accurate snapshot of the nation at any moment. His methods have yielded highly accurate predictions of final results, high-resolution tracking of the race during the campaign, and key insights into where campaign money can be most valuably spent. The Princeton Election Consortium and its predecessor, the Meta-Analysis of State Polls, have attracted millions of hits and tens of thousands of visits per day during campaigns.

Sam’s statistical analysis in 2012 correctly predicted the presidential vote outcome in 49 of 50 states and even the two-candidate popular vote of 51.1% to 48.9%. That year, the Princeton Election Consortium also correctly called 10 out of 10 close Senate races and came within a few seats of the final House outcome. A highly recognized biophysicist and neuroscientist, Sam has also applied his statistical and probabilistic methods to complex experimental data with great success. He is the author of Welcome to Your Child’s Brain and Welcome to Your Brain, which have both been translated into over 20 languages worldwide. Sam was selected by the American Association for the Advancement of Science as a congressional science and engineering fellow. He also served on the staff of the US Senate Committee on Labor and Human Resources.