Princeton Election Consortium

A first draft of electoral history. Since 2004

Entries Tagged as 'Meta-analysis'

Spacetime rift delays update until noon

October 7th, 2008, 11:42am by Sam Wang

Andrew says there was “a routing problem this morning between the University and quite a few outside websites — a split in the internet, if you will.” For the next EV estimator update, check back at noon…

[Read more →]

Tags: 2008 Election · Meta-analysis · Site News

VP debate: big audience but race unchanged

October 5th, 2008, 3:00pm by Sam Wang

Biden v. Palin drew 70 million viewers, one-third more than Obama v. McCain. VP debates usually don’t matter, but I wondered…

[Read more →]

Tags: 2008 Election · Meta-analysis

For locals: a talk on the Meta-Analysis

October 2nd, 2008, 9:00am by Sam Wang

Tomorrow (Friday) at noon, I’ll give a talk in Kosuke Imai and Dustin Tingley’s political methodology seminar. If you’re nearby, you’re welcome to attend. Of course, the math will all be included. The blurb is here (PDF). Update: Here’s another local event, happening next Tuesday: a panel on the reliability of state polls featuring both [...]

[Read more →]

Tags: 2008 Election · Meta-analysis · Princeton

New rules

September 30th, 2008, 9:26pm by Sam Wang

As we head into the last five weeks of the campaign, polls are coming more frequently. In response, we are making two changes to the Meta-Analysis: (a) the averaging rule and (b) the update schedule.

[Read more →]

Tags: 2008 Election · Meta-analysis · Site News

Turning back

September 23rd, 2008, 2:35pm by Sam Wang

Today’s data puts the EV estimator back on track. This supports the double-outlier idea. Okay, back to our regularly scheduled Meta-Analysis.

[Read more →]

Tags: 2008 Election · Meta-analysis

An unexpected turn

September 22nd, 2008, 10:36am by Sam Wang

Although national polls have shown steady movement in Obama’s direction, this weekend the Meta-Analysis made a clear move toward McCain. What’s going on?

[Read more →]

Tags: 2008 Election · Meta-analysis

A change to the polling database

September 14th, 2008, 2:48pm by Sam Wang

Until now the Meta-Analysis has used all polls in the Pollster.com database. However, a source of many outliers is Zogby Interactive, which uses Internet-based polling. Recently we dropped them. The EV estimator will be calculated without their data.

[Read more →]

Tags: Meta-analysis

Dialing it back…

September 10th, 2008, 8:34pm by Sam Wang

Reader PC thinks I need to be careful not to cross the line, so we can focus on the credibility of the work at hand. It’s a good point. The offending post is gone. Instead, here’s something more substantive: a video on the earmark queen. Which leads us to the funny bit:

[Read more →]

Tags: 2008 Election · Meta-analysis · Site News

Taking feedback

September 2nd, 2008, 8:12am by Sam Wang

This morning on FiveThirtyEight, a correction meant to counteract the effect of post-convention bounces was removed. Evidently reader feedback was negative. This is a useful lesson…

[Read more →]

Tags: Meta-analysis

Technical note: Correlated change among states (revisited)

August 28th, 2008, 2:51pm by Sam Wang

The next week and a half will be stormy, not only in the Gulf but also for polls. Seeing where political events take the median EV history will be clearer once we have polls taken after the Republican convention. In the meantime, let’s return to an topic that is obscure, but loved by some hardcore [...]

[Read more →]

Tags: Meta-analysis