David Kirkpatrick

November 4, 2008

Election day 538 projection

Filed under: Politics — Tags: , , , , — David Kirkpatrick @ 6:49 am

Here’s the final FiveThirtyEight projection before the polls open here in a few hours.

Did much lighter blogging yesterday (read: none) because of a medical emergency, and possibly might not be able to do much today.

Update — Actually here’s the absolute final projection taking into account the straggler polls. Even worse news for McCain. And thanks to the gang at FiveThirtyEight for the incredible number crunching over this electoral season. They may have created a sea-change in political polling. An often seamy and slanted part of the game.

November 1, 2008

Could Obama win Georgia?

The guys at FiveThirtyEight think it’s a long shot, but absolutely possible. That would be unbelievable.

From the link:

What To Watch For

It’s entirely possible Georgia will give the Democratic Party its 60th Senate seat on Election Night, if Jim Martin beats Saxby Chambliss. All the House seats are pretty much safe, with incumbent Democrat Jim Marshall in central Georgia facing the toughest re-election in Georgia’s Republican-gerrymandered districts. Republicans are on defense all across the board again this cycle, so if Marshall survived in 2006, he should pull it off again in 2008. If the polls close in the eastern time zone and the nets can’t call Georgia for John McCain because it’s “too close to call,” we’ll all know who the next President-Elect will be.

And here’s the first November projection:

As always, If you’re finding this page later than today’s date hit this link for my latest update, or better yet head straight to 538 for their very latest projections.

October 31, 2008

538 four days out

Filed under: Politics — Tags: , , , , — David Kirkpatrick @ 2:19 pm

Holding steady for Obama.

And of course, If you’re finding this page later than today’s date hit this link for my latest update, or better yet head straight to 538 for their very latest projections.

October 29, 2008

Less than one week 538 projections

Filed under: Politics — Tags: , , , , — David Kirkpatrick @ 6:42 pm

Holding strong for Obama.

And of course, If you’re finding this page later than today’s date hit this link for my latest update, or better yet head straight to 538 for their very latest projections.

October 23, 2008

Final 12 days 538 projection

Filed under: Politics — Tags: , , , , , — David Kirkpatrick @ 8:33 pm

Obama’s highest numbers ever after a group of very strong battleground state polls.

Here’s the break down on the numbers behind this group of projections.

And of course, If you’re finding this page later than today’s date hit this link for my latest update, or better yet head straight to 538 for their very latest projections.

October 17, 2008

Six of nine presidential election forecasts predict Obama

I’ve been running polls and statistical projections. Now here’s the science.

The release:

October 16, 2008: 6 of 9 Presidential Election Forecasts Predict Obama Will Win 2008 Popular Vote APSA Press Release

For Immediate Release

6 of 9 Presidential Election Forecasts Predict Obama Will Win 2008 Popular Vote

WASHINGTON, D.C.—Most of nine forecast models developed by political scientists predict a victory for Senator Barack Obama over Senator John McCain in the two-party contest for the popular vote in the 2008 presidential election. Obama is predicted to win an average of 52% of the vote with an 80% probability that he will gain more than half the total two-party popular vote.

Six out of the nine presidential election forecasts predict an Obama victory with popular vote totals ranging from 50.1% to 58.2%, while two predict a race too close to call and one predicts a narrow McCain victory.  All of the predictions appear in an election-themed symposium in the October issue of PS: Political Science and Politics, a journal of the American Political Science Association (APSA).  The forecasts, published in advance of presidential and mid-term elections, are available online at: https://www.apsanet.org/content_58382.cfm.

The forecasts are based on different combinations of statistical and historical data and differ in their complexity and how far in advance their predictions were made.  The earliest forecast was made 294 days in advance while the latest was made 60 days before the election; however, all were made before the Wall Street financial crisis of the past few weeks.  Together these forecasts use a range of approaches and indicators that are critical to understanding national electoral processes and the dynamics at work in U.S. presidential elections.  Brief summaries of each are provided below:

·         In the earliest completed forecast made in January 2008, Helmut Norpoth’s (Stony Brook University) “Primary Model” uses candidate support in presidential primaries to predict the general election two-party popular vote outcome. Norpoth’s forecast makes Senator Obama the favorite by a razor-thin margin, predicting a 50.1% to 49.9% Obama victory, but also indicates only a 50% chance that Obama will gain a majority.

·         Using data from the second quarter of 2008, Brad Lockerbie (University of Georgia) employs two variables that are decided well in advance of the presidential conventions to forecast the presidential election: the amount of time a party has controlled the White House, and voters’ expectations concerning their financial well-being over the course of the next year. Lockerbie predicts an impressive victory by Barack Obama, with John McCain gaining only 41.8% of the two-party popular vote en route to a loss in the 2008 presidential election.

·         Alan I. Abramowitz’s (Emory University) “Time-for-Change” forecast model, completed in August 2008, is based on the assumption that a presidential election is fundamentally a referendum on the performance of the incumbent president. Abramowitz’s model employs three variables: the growth rate of the economy during the second quarter of the election year, the incumbent president’s approval rating at mid-year, and the length of time the incumbent president’s party has controlled the White House. Abramowitz predicts Senator Barack Obama will receive 54.3% of the two-party popular vote in the 2008 presidential election.

·         Robert S. Erikson (Columbia University) and Christopher Wlezien’s (Temple University) forecast model analyzes a combination of leading economic indicators and trial-heat polls from August 2008 to predict the election’s final outcome. Their model predicts that Senator Obama will win 52.2% of the two-party popular vote, compared with 47.8% for Senator McCain.

·         Michael Lewis-Beck (University of Iowa) and Charles Tien (Hunter College and the Graduate Center, CUNY) “Jobs Model” weighs the sitting president’s popularity and the actual number of jobs created or lost during his term with the powers of incumbency and economic growth. Unadjusted, it predicts that Senator Obama will win 56.57% of the two-party popular vote in what will amount to “the greatest incumbent popular vote loss on record from 1948.” However, with refinements to factor in the impact of race, the Jobs Model predicts a final outcome where Senator Obama will win by a smaller margin, garnering 50.1% of the two-party vote and with a 50% chance that Obama will gain a majority. The forecast was made in August 2008.

·         Thomas M. Holbrook’s (University of Wisconsin-Milwaukee) forecast model emphasizes presidential approval and the average level of satisfaction with personal finances in the summer before the presidential election.  Completed in August 2008, his model predicts Barack Obama will garner 55.7% of the two-party presidential popular vote compared to John McCain’s 44.3%.

·         Symposium editor James E. Campbell’s (University at Buffalo, SUNY) “Trial Heat” forecast model integrates the incumbent’s trial-heat Labor Day Gallup numbers and the real growth in the GDP in the second quarter of the election year. Completed in early September 2008, the Campbell model breaks with the other forecasts to predict that Senator McCain should be expected to receive 52.7% of the two-party popular vote.

·         Alfred G. Cuzan and Charles M. Bundrick (University of West Florida) use the “Fiscal Model” forecast and emphasize the relationship between the ratio of federal outlays to GDP and the share of the two-party vote going to incumbents.  Completed in August 2008, their forecast predicts the Democratic candidate, Senator Barack Obama, will emerge victorious by a 52%-48% margin.

·         Carl Klarner (Indiana State University) employs a forecast model that focuses on broad range of state and district-level factors. Completed in late July 2008, his forecast predicts Senator Obama will obtain 53.0% of the popular vote and 346 electoral votes.

The 2008 presidential election is taking place in an extraordinary environment.  The open-seat nature of the contest, the implications of President Bush’s low approval ratings, Senator Obama’s decision to forego public financing of his campaign, the effect of race on a contest featuring the first black candidate of a major party in U.S. history, the relative levels of party unity, and the impact of the Wall Street meltdown after these forecasts were produced all combine to make the outcome of the 2008 election unusually difficult to predict.  Nevertheless, more of the forecasts predict an Obama victory than not, as the “median of these nine forecasts indicates that Senator McCain will receive 48% of the two-party popular vote,” concludes symposium editor James Campbell.

# # #

The American Political Science Association (est. 1903) is the leading professional organization for the study of politics and has over 14,000 members in 80 countries. For more news and information about political science research visit the APSA media website, www.politicalsciencenews.org.

October 16, 2008

538 projections in the homestretch

Filed under: Politics — Tags: , , , , , — David Kirkpatrick @ 2:17 pm

The debates are done and the homestretch portion of this election has officially begun. The numbers are not pretty for McCain in any of the polls, etc.

Not surprisingly this holds doubly true with the current FiveThirtyEight projection:

Here’s a little context on these figures from the site itself:

Again, when you look at the pie chart on the upper left of the page (note from dk — that’s the chart above), you see a decimal point to one place on the electoral vote projection. That number comes from the 10,000 daily simulations the model runs. Essentially, it’s the final outcome simulated 10,000 times and then divided by 10,000. This monthly snapshot says, if we give 100% of the electoral votes for each state we project into one candidate’s column, the final tally would be:

Senator Barack Obama, Democratic Party: 364 electoral votes
Senator John McCain, Republican Party: 169 electoral votes
Undetermined: 5 electoral votes.

And of course, If you’re finding this page later than today’s date hit this link for my latest update, or better yet head straight to 538 for their very latest projections.

October 9, 2008

Obama’s 538 projection now over 90%

Filed under: et.al. — Tags: , , , , , — David Kirkpatrick @ 4:56 pm

Crazy numbers. And I hope everyone caught Nate Silver on The Colbert Report this week.

If you’re finding this page later than today’s date hit this link for my latest update, or better yet head straight to 538 for their very latest projections.

September 20, 2008

538 projections showing McCain’s bounce is over

Filed under: Politics — Tags: , , , , — David Kirkpatrick @ 7:58 pm

Obama regains his customary position in a comfortable lead according to the presedential projections at FiveThirtyEight.

If you’re finding this page later than today’s date hit this link for my latest update, or better yet head straight to 538 for their very latest projections.

September 11, 2008

McCain takes lead in 538’s “win percentage” projection

Filed under: Politics — Tags: , , , , , — David Kirkpatrick @ 12:31 am

This is a first as far as I know. If this is the extent of the bounce it’ll be very interesting to see how the numbers shake out over the next two weeks or so.

Also interesting to see how each campaign reacts to the changing situation, although internal polling may show something radically different than the FiveThirtyEight polling data.

The latest projections:

If you’re finding this page later than today’s date hit this link for my latest update, or better yet head straight to 538 for their very latest projections.