Victory probability mapObama lead over time

Friday, June 25, 2004

Current Standings

Were the election held today, Kerry would have a 40.4% chance of winning, with 264.5 expected electoral votes. Kerry has a 43.1% chance of winning on Election Day, with 261.8 expected electoral votes.

Cartogram showing, for each electoral vote, the chances that the leading candidate would win if the election were today:
for each electoral vote, the chances that the leading candidate would win today

Cartogram showing, for each electoral vote, the chances that the leading candidate will win on Election Day:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

List showing where each state would stand if the election were held today:

Extremely Safe (99%+ chance of winning)

Kerry 94: Connecticut, District of Columbia, Illinois, Maine (at large and 1st), Massachusetts, New York, Rhode Island, Vermont, Washington.

Bush 127: Alabama, Florida, Indiana, Kentucky, Louisiana, Montana, Oklahoma, South Dakota, Tennessee, Texas, Utah.

Very Safe (90-99%)

Kerry 99: California, Maine (2nd), New Jersey, Oregon, Pennsylvania.

Bush 66: Alaska, Arizona, Georgia, Idaho, Kansas, Nebraska (3rd), North Carolina, South Carolina, Wyoming.

Safe (80-90%)

Kerry 32: Iowa, Maryland, Minnesota, New Mexico.

Bush 40: Colorado, Nebraska (at-large and 1st), Nevada, North Dakota, Ohio.

Very Probable (70-80%)

Kerry 21: Delaware, Hawaii, New Hampshire, Wisconsin.

Bush 18: Mississippi, Missouri, Nebraska (2nd).

Probable (60-70%)

Kerry 0.

Bush 13: Virginia.

Tossup (55-60%)

Kerry 0.

Bush 6: Arkansas.

Close Tossup (50-55%)

Kerry 0.

Bush 22: Michigan, West Virginia.

Total

Kerry 246.

Bush 292.

A number of states have changed slightly because I altered a significant parameter (really, the only parameter) in my calculations. Specifically, I had cause to raise the daily added variance in my estimates.


Read more (maybe)!

Thursday, June 24, 2004

Current Standings; Ohio

Were the election held today, Kerry would have a 39.3% chance of winning, with 268.0 expected electoral votes. Kerry has a 48.2% chance of winning on Election Day, with 269.2 expected electoral votes.

Cartogram showing, for each electoral vote, the chances that the leading candidate would win if the election were today:
for each electoral vote, the chances that the leading candidate would win today

Cartogram showing, for each electoral vote, the chances that the leading candidate will win on Election Day:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

Ohio (20) changed from Very Safe Bush to Safe Bush because of a new ARG poll.


Read more (maybe)!

Wednesday, June 23, 2004

Current Standings

Following the latest Zogby polls, Bush has a clear lead. Were the election held today, Kerry would have a 32.0% chance of winning, with 265.2 expected electoral votes. Kerry has a 41.5% chance of winning on Election Day, with 265.6 expected electoral votes.

Cartogram showing, for each electoral vote, the chances that the leading candidate would win if the election were today:
for each electoral vote, the chances that the leading candidate would win today

Cartogram showing, for each electoral vote, the chances that the leading candidate will win on Election Day:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

List showing where each state would stand if the election were held today:

Extremely Safe (99%+ chance of winning)

Kerry 172: California, Connecticut, District of Columbia, Illinois, Maine (at large and 1st), Maryland, Massachusetts, New Jersey, New York, Rhode Island, Washington.

Bush 171: Alabama, Alaska, Arizona, Georgia, Idaho, Indiana, Kansas, Kentucky, Louisiana, Montana, Nebraska (at large, 1st, and 3rd), North Carolina, North Dakota, Oklahoma, South Carolina, South Dakota, Tennessee, Texas, Utah, Wyoming.

Very Safe (90-99%)

Kerry 56: Delaware, Hawaii, Iowa, Maine (2nd), Minnesota, Oregon, Pennsylvania, Vermont.

Bush 79: Colorado, Florida, Mississippi, Missouri, Nebraska (2nd), Nevada, Ohio.

Safe (80-90%)

Kerry 22: Michigan, New Mexico.

Bush 6: Arkansas.

Very Probable (70-80%)

Kerry 14: New Hampshire, Wisconsin.

Bush 13: Virginia.

Probable (60-70%)

Kerry 0.

Bush 5: West Virginia.

Tossup (55-60%)

Kerry 0.

Bush 0.

Close Tossup (50-55%)

Kerry 0.

Bush 0.

Total

Kerry 264.

Bush 274.


Read more (maybe)!

Current Standings

Fixed a typo in my records that had given 21 electoral votes to Ohio (20).

Were the election held today, Kerry would have a 49.5% chance of winning, with 273.0 expected electoral votes. Kerry has a 53.1% chance of winning on Election Day, with 272.0 expected electoral votes. Bush has 50.4% of the popular vote.


Read more (maybe)!

Monday, June 21, 2004

Current Standings; Arizona

I have access to Maple again, and corrected a typo in my new spreadsheet which had given Bush a high chance of winning Vermont. Were the election held today, Kerry would have roughly a 49.5% chance of winning and an expected 273.1 electoral votes. I predict Kerry to have a 53.5% chance of winning on Election Day, with an expected 272.2 electoral votes.

These facts may seem paradoxical for two reasons: First, Bush would be more likely than Kerry to win if the election were held today, even though Kerry has more than 270 expected electoral votes. Second, Kerry becomes more likely to win between now and election day, while losing almost one expected electoral vote.

The first paradox comes from the probability distribution of Kerry's electoral votes being skewed right (meaning that the right tail is heavier than the left tail). Every state that Bush takes with a probability that's neither too much nor too little probability contributes some significant right skew, and every state that Kerry takes with neither too much nor too little probability contributes some significant left skew. Because Florida, Ohio, and Virginia are large states that would currently go to Bush with probabilities between 72 and 87%, they contribute a substantial right skew to the overall distribution of Kerry's electoral votes.

So why is the likelihood of Kerry winning on Election Day so much better than it would be today? Mostly because Florida and Ohio are states with low sampling error (the error that determines predictions for today) but high passage-of-time error (the error that partially determines predictions for Election Day) compared with the projected margins of Bush's victories there. Even though the two-party vote is extraordinarily close in these states (Bush gets an expected 50.5-50.9% of the two-party vote in these states), I have enough data on those two states to be fairly confident (72% chance for Florida and 87% for Ohio) that they would go to Bush if the election were today. However, the passage of several months adds enough variance to these states' predictions that they become much less certain. If Bush had even 52% or so of the two-party vote in these states, the extra variance wouldn't matter nearly as much, as is the case in Kerry's Michigan and Pennsylvania.

I am not sure what causes Kerry to lose an expected electoral vote between now and Election Day. It is possible that the passage-of-time error affects Extremely Likely Kerry states such as Minnesota or Maine slightly more than Extremely Likely Bush states such as Alaska or Texas because of Bush's ridiculously large projected margins of victory in many western states.

Cartogram showing, for each electoral vote, the chances that the leading candidate would win if the election were today:
for each electoral vote, the chances that the leading candidate would win today

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

Arizona changed from Very Safe Bush to Extremely Safe Bush because of a new Market Solutions Group poll.


Read more (maybe)!

Friday, June 18, 2004

Bush leads; Florida, New Hampshire, West Virginia

Were the election held today, Kerry would have roughly a 45% chance of winning and an expected 268.1 electoral votes. Note that 45 < 50, and then go give Kerry some money. I say "roughly" because my office computer, which is over 1000 miles away and contains my only functional and usually-Internet-accessible mathematical software, is not responding. Luckily, that doesn't affect my state-by-state predictions (spreadsheet on my laptop) or map-making (free drawing program on my laptop). But grrrr. I blame the recent electrical work in that building. Anyone wishing to donate me a licensed copy of Maple for OS X is welcome to do so; I would love to Command the Brilliance of a Thousand Mathematicians without having to use SSH.

Cartogram showing, for each electoral vote, the chances that the leading candidate would win if the election were today:
for each electoral vote, the chances that the leading candidate would win today

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

The pro-Bush swing is mostly because of a Survey USA poll from Florida (27) that changes Florida from Tossup Kerry to Very Probable Bush. West Virginia (5) changes from Close Tossup Kerry to Probable Kerry because of an ARG poll, and New Hampshire (5) changes from Safe Kerry to Very Probable Kerry because of aging data.


Read more (maybe)!

Monday, June 14, 2004

New and Improved Current Standings; Nevada, Ohio, West Virginia, etc.

I've made some changes to how I predict each state, in particular to how I weight old polls. This new system allows me to make predictions with greater confidence, and also theoretically allows me to state confidence estimates for Election Day predictions instead of just for if-the-election-were-today predictions, although I don't have much faith yet in Election Day predictions. (If you're curious, I give Kerry a 62.9% chance of winning, with an expected 277.3 electoral votes.) When I get back from San Francisco on Friday, I'll post more details on all this in a comment to the bookmarked "Methodology" post.

Were the election held today, Kerry would have an 70.1% chance of winning and an expected 281.7 electoral votes. Assuming all Very Probable, Safe, Very Safe, and Extremely Safe states went the predicted way, Florida would decide the winner. Bush has 50.09% of the popular vote.

Cartogram showing, for each electoral vote, the chances that the leading candidate would win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

Extremely Safe (99%+ chance of winning)

Kerry 182: California, Connecticut, District of Columbia, Illinois, Maine (at large and 1st), Maryland, Massachusetts, Minnesota, New Jersey, New York, Rhode Island, Washington.

Bush 161: Alabama, Alaska, Georgia, Idaho, Indiana, Kansas, Kentucky, Louisiana, Montana, Nebraska (at large, 1st, and 3rd), North Carolina, North Dakota, Oklahoma, South Carolina, South Dakota, Tennessee, Texas, Utah, Wyoming.

Very Safe (90-99%)

Kerry 56: Delaware, Hawaii, Iowa, Maine (2nd), Michigan, Pennsylvania, Vermont.

Bush 43: Arizona, Arkansas, Colorado, Mississippi, Missouri, Nebraska (2nd).

Safe (80-90%)

Kerry 21: New Hampshire, Oregon, Wisconsin.

Bush 25: Nevada, Ohio.

Very Probable (70-80%)

Kerry 0.

Bush 13: Virginia.

Probable (60-70%)

Kerry 0.

Bush 0.

Tossup (55-60%)

Kerry 27: Florida.

Bush 0.

Close Tossup (50-55%)

Kerry 5: West Virginia.

Bush 5: New Mexico.

Total

Kerry 291.

Bush 247.

Many states shifted slightly. The notable shifts are Ohio (20, from Close Tossup Bush to Safe Bush, Nevada (5, from Tossup Kerry to Safe Bush), and West Virginia (5, from Very Probable Kerry to Close Tossup Kerry). These three shifts were the cause of my decreased optimism.


Read more (maybe)!

Sunday, June 13, 2004

Filler; Florida

No posts this weekend. No polls came out, so I didn't find it urgent to post, and an urgent personal problem came up. I did revise my disorganized spreadsheets (which I'm sure excites you all), and I did do some research on some methodological improvements, which will be announced tomorrow. For now, let's just say that I hope Florida, led by Jeb Bush appointee Glenda Hood, has its shit together this year.


Read more (maybe)!

Thursday, June 10, 2004

Current Standings; Florida, Missouri, Ohio, Wisconsin

Kerry has an 87.7% chance of winning and an expected 295.7 electoral votes. Kerry could win with just Florida among his Tossup states. Bush has 50.06% of the two-party popular vote.

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

Florida (27) moved from Probable to Tossup Kerry because of aging data. Missouri (11) moved from Probable to Very Safe Bush, Ohio (20) from Very Safe to Close Tossup Bush, and Wisconsin (10) from Very Safe to Safe Kerry because of new data from the LA Times. I also got new data for Kentucky from Survey USA and for New Hampshire from American Research Group.


Read more (maybe)!

Wednesday, June 09, 2004

Current Standings; Florida, Michigan, Missouri, Nevada, New Mexico, New Jersey

Kerry has an 84.2% chance of winning and an expected 290.7 electoral votes. Kerry could win without a tossup state. Bush has 50.08% of the two-party popular vote.

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

Florida (27, Kerry) and Missouri (11, Bush) moved from Tossup to Probable, Michigan (17) moved from Extremely Safe Kerry to Very Safe Kerry, and New Mexico (5) moved from Tossup Bush to Close Tossup Bush because of corrected data; Nevada (5) moved from Probable Kerry to Tossup Kerry and New Jersey (15) moved from Extremely Safe Kerry to Very Safe Kerry because of aging data.


Read more (maybe)!

Tuesday, June 08, 2004

Zogby

Zogby's interactive poll seems to interview some of the same people from fortnight to fortnight. (I myself have taken his poll twice now.) Therefore, I am only going to use Zogby's most recent poll in my calculations. At this point, this change helps Bush overall by a slight margin and in New Mexico (where there is a dearth of data) substantially, enough to take it from Probable Kerry to Tossup Bush. Since I don't trust Zogby's online poll much anyhow, I'm not too sad about this.


Read more (maybe)!

Current Standings; Arkansas, Florida, Michigan, Minnesota, Missouri, Nevada, New Hampshire, New Mexico, Ohio, Tennessee, Washington, West Virginia

Kerry has an 86.1% chance of winning and an expected 292.1 electoral votes. Kerry could win by taking Florida (his only Tossup state) even while losing all of his Probables and Very Probables; he could also win by losing Florida provided that he kept his Probables and Very Probables and picked up one of Bush's Tossups. Bush has 50.06% of the two-party popular vote.

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

Extremely Safe (99%+ chance of winning)

Kerry 179: California, Connecticut, District of Columbia, Illinois, Maine (at large and 1st), Massachusetts, Michigan, New Jersey, New York, Rhode Island, Washington.

Bush 132: Alabama, Alaska, Georgia, Idaho, Indiana, Kentucky, Louisiana, Montana, Nebraska (at large, 1st, and 3rd), North Dakota, Oklahoma, South Dakota, Tennessee, Texas, Utah, Wyoming.

Very Safe (90-99%)

Kerry 59: Delaware, Hawaii, Iowa, Maine (2nd), Minnesota, Pennsylvania, Vermont, Wisconsin.

Bush 72: Arizona, Arkansas, Kansas, Mississippi, North Carolina, Nebraska (2nd), Ohio, South Carolina.

Safe (80-90%)

Kerry 10: Maryland.

Bush 9: Colorado.

Very Probable (70-80%)

Kerry 12: New Mexico, Oregon, West Virginia.

Bush 0.

Probable (60-70%)

Kerry 5: Nevada.

Bush 13: Virginia.

Tossup (55-60%)

Kerry 27: Florida.

Bush 16: Missouri, New Mexico.

Close Tossup (50-55%)

Kerry 0.

Bush 0.

Total

Kerry 296.

Bush 242.

Missouri (formerly Tossup Kerry) and New Mexico (formerly Very Probable Kerry) switched to Tossup Bush. My confidence in Kerry's lead strengthened in Florida (Close Tossup to Tossup), Michigan (Very Safe to Extremely Safe), Nevada (Tossup to Probable), Washington (Very Safe to Extremely Safe), and West Virginia (Close Tossup to Very Probable), but weakened in Minnesota (Extremely Safe to Very Safe) and New Hampshire (Very Safe to Very Probable). My confidence in Bush's lead strengthened in Arkansas (Very Safe to Extremely Safe), Ohio (Very Probable to Very Safe), and Tennessee (Safe to Extremely Safe).


Read more (maybe)!

Monday, June 07, 2004

Current Standings; Iowa, Maine, New Jersey, Virginia, West Virginia

Kerry has an 90.5% chance of winning and an expected 298.4 electoral votes. Kerry could win with just Missouri, Florida, or both Nevada and West Virginia out of his tossup states. Kerry has 50.09% of the two-party popular vote, his first lead since I started these predictions.

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the expected percentage (of Bush/Kerry votes only) for the leading candidate.
for each electoral vote, the leading candidate's expected percentage

Extremely Safe (99%+ chance of winning)

Kerry 161: California, Connecticut, District of Columbia, Illinois, Maine (at large and 1st), Massachusetts, Minnesota, New Jersey, New York, Rhode Island.

Bush 121: Alabama, Alaska, Georgia, Idaho, Indiana, Kentucky, Louisiana, Montana, Nebraska (at large, 1st, and 3rd), North Dakota, Oklahoma, South Dakota, Texas, Utah, Wyoming.

Very Safe (90-99%)

Kerry 81: Delaware, Hawaii, Iowa, Maine (2nd), Michigan, New Hampshire, Pennsylvania, Vermont, Washington, Wisconsin.

Bush 46: Arizona, Kansas, Mississippi, North Carolina, Nebraska (2nd), South Carolina.

Safe (80-90%)

Kerry 10: Maryland.

Bush 26: Arkansas, Colorado, Tennessee.

Very Probable (70-80%)

Kerry 12: New Mexico, Oregon.

Bush 20: Ohio.

Probable (60-70%)

Kerry 0.

Bush 13: Virginia.

Tossup (55-60%)

Kerry 16: Missouri, Nevada.

Bush 0.

Close Tossup (50-55%)

Kerry 32: Florida, West Virginia.

Bush 0.

Total

Kerry 312.

Bush 226.

Iowa changed from Very Probable to Very Safe Kerry; Maine (at large and 1st) changed from Safe to Extremely Safe Kerry; Maine (2nd) changed from Very Probable to Very Safe Kerry; New Jersey changed from Very Safe to Extremely Safe Kerry; Virginia changed from Very Probable to Probable Bush; West Virginia changed from Safe Bush to Close Tossup Kerry. All changes were because of new polling data. This is the first Virginia prediction based on 2004 data.


Read more (maybe)!

Thursday, June 03, 2004

Current Standings; Georgia, Missouri, Oregon

Kerry has an 85.7% chance of winning and an expected 293.2 electoral votes. Kerry could win with just Missouri or Florida out of his tossup states. Bush has 50.16% of the two-party popular vote.

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the leading candidate's lead.
for each electoral vote, the leading candidate's expected percentage

Georgia (15) changed from Safe Bush to Extremely Safe Bush, Missouri (11) changed from Probable Kerry to Tossup Kerry, and Oregon (7) changed from Safe Kerry to Very Probable Kerry, all because of new polls. This was the first poll I had for Georgia.

I will be camping in Wisconsin (10, Very Safe Kerry) this weekend, so no updates until Monday or Tuesday.


Read more (maybe)!

Wednesday, June 02, 2004

Methodology; Current Standings; Florida, Maryland, New Mexico, Tennessee, Vermont

I made a slight methodological change today: Instead of using the end date of each poll, I'm using the middle date. Recently, there have been some polls published with long time frames, including a bizarre Alabama poll with the dates "5/4-6,5/17-20." I also slightly updated (more like corrected) the formula I use for estimating sample size from published margin of errors. In practice, neither of these changes does much, since most polls publish sample size and have short time frames.

Kerry has an 87.6% chance of winning and an expected 295.3 electoral votes. Kerry could win without any of his tossup states, while Bush would need at least 36 electoral votes from Kerry's side. Bush has 50.27% of the Bush/Kerry popular vote.

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win

Cartogram showing, for each electoral vote, the leading candidate's lead.
for each electoral vote, the leading candidate's expected percentage

Florida (27) changed from Tossup Kerry to Close Tossup Kerry; Maryland (10) changed from Very Safe Kerry to Safe Kerry; New Mexico (5) changed from Safe Kerry to Very Probable Kerry because of aging data; Tennessee (11) changed from Very Safe Bush to Safe Bush; Vermont (3) changed from Extremely Safe Kerry to Very Safe Kerry. These happened because of methodological changes, except as noted.


Read more (maybe)!

Tuesday, June 01, 2004

Current Standings

In the absence of new polling data, the "Confidence" map, the list of states, the odds of a Kerry victory, and the expected electoral vote tally can change, but the "Percentages" map cannot. When I post the Current Standings, I'll only post the elements that have changed, however slightly (today's only change is that Tennessee got one notch lighter).

Cartogram showing, for each electoral vote, the chances that the leading candidate will win:
for each electoral vote, the chances that the leading candidate will win


Read more (maybe)!