Skip to content

This code pulls data from 538's raw polling data and pollster grades, calculates actual errors across all elections, and for 2016 presidential race, and shows that 538's grades are weakly correlated with success across various measures. https://github.com/fivethirtyeight/data/tree/master/pollster-ratings

Notifications You must be signed in to change notification settings

jtrothwell/538_pollster_criticism

Repository files navigation

538_pollster_criticism

This code analyzes 538's raw polling data and pollster grades, calculates errors across all elections, adjusted for election-specific effects, and for the 2016 presidential race, and shows that 538's grades are weakly correlated with success across the two most important measures of error: point-estimate error and candidate margin error. https://github.com/fivethirtyeight/data/tree/master/pollster-ratings

About

This code pulls data from 538's raw polling data and pollster grades, calculates actual errors across all elections, and for 2016 presidential race, and shows that 538's grades are weakly correlated with success across various measures. https://github.com/fivethirtyeight/data/tree/master/pollster-ratings

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages