The House Always Wins: House Effects in Polling
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.

The House Always Wins: House Effects in Polling


In 2007--2008, I collected some data to estimate house 'effects', and to explain them. For instance, some variation across polling houses likely stems from the whether or not a 'don't know' option is provided, the length of the polling period, whether or not the polling house uses a likely or registered voter screen, the question text, etc.

This repository includes some of the data I collected, and may over time include some of the analyses I conducted.

Rasmussen Vs. the Rest

G. W. Bush Approval

rasmussen vs. rest bush approval

2008 Election Cycle, McCain Support

rasmussen vs. rest election


Preliminary Release


Preliminary Release

Contribute to the project

If you see an inconsistency in the data, or have a suggestion, or some data that you would like to contribute to the project, please create a pull request or open an issue.


Released under CC BY 2.0.