Posts by J. Brian Adams

With only three days left, Obama’s reelection chances have rebounded to 96%

Nov03
2012 4 Comments J. Brian Adams Written by J. Brian Adams

Despite the near tie in the latest polling of the nationwide popular vote, Obama appears poised to remain in the White House for four more years.

Running our simulation model with the last set of weekly polls before Tuesday’s election, President Obama once again has moved up to a near certain win for the electoral vote. As of November 2, our model predicts a 96% chance of reelection with Governor Romney’s chance of unseating the President falling back to 4%. While there is still buzz about the possibility of an electoral college tie – and the resulting President Romney and Vice-President Biden – that probability has also fallen to near zero.

At this point, Obama can claim 199 electoral votes as near certainties to Romney’s 159. When the likely wins are included Obama’s total rises to 226 and Romney’s to 173. If you include all of the states that are currently leaning for reelection, the President climbs well past the needed 270 to 332 electoral votes.

The challenge for Governor Romney is to retake several of the states that are leaning blue. The most likely of these is New Hampshire followed by Ohio but at a total of 22 electoral votes that only drops Obama to 310. If Romney can also win both Virginia and Florida he raises his total to 272 and a win – but even losing New Hampshire’s four votes from that mix turns his win back to a loss.

At this point our model is predicting an electoral college vote of 314 for President Obama and 224 for Governor Romney – a buffer of 45 votes. While this is the most likely outcome, the next most likely possibilities have even higher totals for the President. In fact the top fifty percent of the outcomes are all above 294 electoral votes.

A common saying by candidates is that the only poll that counts is the one on election day. And while an upset is still a possibility, that possibility currently appears to be quite unlikely.

Posted in Polling - Tagged , ,

With A Week To Go, October Reelection Slide Reverses

Oct29
2012 3 Comments J. Brian Adams Written by J. Brian Adams

There have been volumes written on how the presidential debates might impact the election. With their conclusion last week the polls have shown a significant impact.

Our simulation model which uses the latest state wide polls has been run each week since the beginning of summer. Its estimate of the probability of the President winning reelection peaked at 99.9% on September 28 when the electoral college math showed there was no likely way that Governor Romney could garner the necessary 270 electoral votes.

But the campaigns continued, the Benghazi attack was still making headlines, the stock market dropped, and the debates began.

With the first debate came performance critiques of the two candidates and new state polls. By the end of that week the race had tightened. Our model predicted that Governor Romney had gained in several key states primarily Florida, Virginia, and North Carolina. With this surge his probability of winning also rose – moving from 0% the week before to 11% on October 5.

The following week provided an opportunity for the Vice Presidential candidates to debate. As the debate was late in the week they could not have had significant impact on that week’s polls. Instead the new polls were more likely a continuation of the results of the first debate. On Octaber 12 our model showed a continued decline for the President with his probability of reelection dropping to 82%. At the same time Governor Romney’s probability of winning rose to 16% and for the first time in several months the probability of an electoral college tie reached significance at 2%.

The effects of the Vice Presidential debate and the third Presidential debate could be seen in the following week’s polls. As of October 19, Governor Romney’s chances continued to rise reaching a probabilty of 25%. Similarly President Obama’s probability of winning continued its slide dropping to 73%. The probability of a tie held at just under 2%.

Now the debates have been concluded and the candidates are back to the criss-crossing the country giving stump speeches in the battleground states. But with this return to the traditional campaign has also come a return to President Obama’s reelection hopes. As of last week our model shows the chance of reelection reversing, climbing from the previous week’s low back up above 92%. Similarly Romney’s chances have declined to about 7% with the probability of tie again dropping below 1%.

Why the reversal? A noticeable change has occurred in Florida. Romney had taken significant leads in the Sunshine State over the past several weeks. While still leading Florida has again tightened. Similarly Romney’s Virgninia lead has dropped to a tie. And in Ohio, a key for a Republican victory, the polls show that while Obama had been able to retain a slight lead throughout most of October, his lead has increased over the last week.

While the model does not indicate that reelection is a certainty, it does indicate good news for the President. Our model currently predicts an electoral college vote of 301 for President Obama and 237 for Governor Romney – a buffer of only 31 votes – a slim margin in electoral college math. But with only a week to go, and early voting and absentee voting already in progress, our model indcates the GOP may have a significant challenge to get those 31.

Posted in Polling - Tagged , , ,

While the campaigns move into the fall, polls show that little has changed

Sep23
2012 Leave a Comment J. Brian Adams Written by J. Brian Adams

The party conventions have passed and the fall campaign season is in full swing. As the campaigns prepare for the October debates the question continues to be asked; “is the current presidential race too close to call, or has one candidate already taken what is possibly an insurmountable lead?”

Polls tend to lag public opinion by about a week so any current events may not be reflected, but using the available polls and our simulation model, President Obama’s probability of reelection has dropped – but by only a small amount. He currently has near a 97% chance of winning with Governor Romney’s probability up slightly to about 3%. The chance of an electoral college tie – a serious possibility several months ago – has dropped to near zero.

The first plot shows the trend in the probabilities while the second shows the range of expected electoral votes for each of the candidates. With the exception of the Romney bounce that occurred following his selection of Paul Ryan for Vice-President in the middle of August, the trends have remained consistently strong in favor of the President.

The slight rise in Romney’s chance appears to be the result of favorable polling in Florida. While Florida has been considered a tossup throughout the campaign, the latest polls indicate a switch from leaning blue to now leaning red. This change gives Romney about a 58% of winning Florida and its 29 electoral votes.

With the possible loss of Florida, our model now gives Obama 247 likely or certain electors to Romney’s 151. That leaves only 23 votes to clinch reelection – with 46 of the remaining 140 electoral votes currently leaning in the President’s favor.

A common discussion point for polls is the margin of error. This is a measure of the uncertainty in the polling. The argument goes that if one candidate is polling within the margin of error – no matter how far from the center – then that candidate still has a chance.

The margin of error in our model is shown in the blue and red bands for each of the candidates. To be a tie these bands would have to have a significant level of overlap – more so than what even occurred in the middle of June. While they do currently overlap – explaining why the current probabilities are not at the certainty level – the overlap is so small that it is a statistical leap to argue that Romney’s true vote count is actually higher than Obama’s, and that the reason for the difference is due to the random error that occurs in all polls.

While world news, campaign announcements, and candidate debates are sure to move these lines, at the present it appears that the status quo is expected to stay.

Posted in Polling

Reelection probability rises to near certainty

Aug14
2012 1 Comment J. Brian Adams Written by J. Brian Adams

As the summer wanes and the presidential campaign continues, a recurring question relates to electoral mathematics – what states will either President Obama or Governor Romney need to win in November? There are several that are touted as battleground states that will determine the outcome of the election. Is this true?

As any follower of presidential elections already knows, it requires 270 electoral votes to win a presidential election.

Running the current statewide polling data through our simulation model, there are currently sixteen states – including Pennsylvania – in which Obama has a greater than 95% probability of winning. These sixteen contribute a total of 205 electoral votes to his total. Governor Romney also has sixteen states in his certain win column, but because of population differences they contribute only 141 electoral votes to his total.

A second level includes those states that while not certain wins for each of the candidates a win is considered likely. This level adds three more states to the Obama tally with an additional 58 electoral votes. Romney gains a single state and only three additional electors.

Including this level the President currently has 263 electoral votes requiring only seven additional electors. Governor Romney has 144 electoral votes and still needs 126 more.

To reach 270 it might be possible for Romney to win all four of the states that are leaning in his favor – Kansas, Kentucky, South Carolina, and South Dakota. This adds thirty-two electors to his total. If he also takes all three of the true tossup states – Colorado, Missouri, and Tennessee – he gains an additional thirty electors. But that only brings him to 203 – still 67 short. To make up these additional votes he will need to take all of the states that are polling close, but still leaning Obama.

At this point the probability of an Obama reelection is at 99.8% – as close to a certainty as one might expect. But it might be possible for Romney to change the result by swaying a few of the battlegrounds. But it will take more than a single win. For example Ohio is currently a likely Obama win. But if between now and November Romney can change that outcome and take Ohio his odds barely improve with Obama’s chance of winning dropping to just under 99%.

Instead, Romney will have to sweep all of the battlegrounds. Assume that he is able to win Florida, North Carolina, Ohio, and Virginia. His probability of winning puts him back into play at 46% to the President’s 52% with a 3% chance of tie. If you add Michigan or Pennsylvania into the Romney win column his chances rise to a likely – albeit not certain – electoral college win. Of course it is important to recognize that these are all states in which Obama is currently leading, some – such as Michigan and Pennsylvania – by significant margins.

This is not to imply that the election is over; far from it. This is simply a snapshot based on the current statewide opinion polls. It remains to be seen how Romney’s choice of Paul Ryan will play out in the polls or what impact the party conventions will have. As we enter the fall campaign season we are sure to see changes in the numbers. But based on the current polls, the odds are not on a photo finish, but instead a contender who is struggling to get out of the gate.
electoral_map_08102012

Posted in Polling - Tagged , , ,

President’s Reelection Chances Rebound with a Rise to Above 96%

Jul19
2012 1 Comment J. Brian Adams Written by J. Brian Adams

With last week’s release of eight new statewide polls the probability of President Obama being reelected has rebounded eight points to a new high of over 96%. Governor Romney’s probability of winning has similarly dropped eight points to 3%. These percentages represent the probability of each candidate receiving at least 270 electoral votes. The probability of a tie remains at less than 1%

These results are based upon a statistical model that uses currently available opinion polls for each of the fifty states and the District of Columbia. It analyzes these polls determining each possible outcome with its likelihood of occurring.

Of the eight states involved in the new polls, five – New Mexico, Virginia, Maine, North Carolina, Pennsylvania, and Wisconsin – have increased their support for the President. Two states – Florida and North Dakota – show increases for Governor Romney. Polls from Virginia and North Carolina indicate strong increases for Obama with both states moving from leaning Romney to now leaning Obama.

Florida which had been showing a fractional advantage towards Obama remains close but the slight advantage has now moved to Romney.

There are still three states, Iowa, New Hampshire, and Tennessee that are in the tossup category. Tossup states are the states in which there is not a statistically clear winner.

States that are leaning Obama are currently CO, MI, NV, NC, OH, and PA.
The states that are leaning Romney are FL, IN, KS, KY, SC, and SD.

The states that are likely wins for the President are ME, NM, OR, VA, and WI.
MO, and MT are likely wins for Governor Romney.

The final category are those states that would be considered statistically certain outcomes.

For President Obama these are CA, CT, DE, DC, HI, IL, MD, MA, MN, NJ, NY, RI, VT, and WA.
For Governor Romney the certain win states are AL, AK, AZ, AR, GA, ID, LA, MS, NE, ND, OK, TX, UT, WV, and WY.

The box plots show the distribution of predicted electoral votes for each candidate over the past seven weeks. The center rectangle includes the middle 50% of the outcomes while the whiskers cover the most likely 99.5% of outcomes. The green line marks the 270 electoral vote cutoff needed to win the election.

The time series plot tracks the trend in the probability of winning since the middle of May.

Box Whisker Plots for Possible Electoral Votes

Comparison of Predicted Electoral Vote Outcomes for President Obama and Governor Romney

Trend of Probabilities of Receiving 270 or More Electoral Votes

Posted in Polling - Tagged , , ,

Latest Polls Indicate Probability of Reelection Down But Still Strong

Jul09
2012 Leave a Comment J. Brian Adams Written by J. Brian Adams

With the release of the latest statewide polls President Obama has an 88% chance of winning reelection as compared to Gov. Romney’s 11% with a 1% chance of a tie.

These results are based upon an analysis of the combinations of possible results using Monte Carlo techniques. This simulation model combines the estimated percentage of votes that each candidate is expected to receive while further taking into account the percentage of the electorate that may still be undecided.

With each run a number of electoral votes is predicted for each of the fifty states and the District of Columbia. A simulated winner of the election is thus determined. By running the model millions of times, the technique estimates the percentage of the simulated elections that each candidate wins and thus the probability of winning the election.

The input data for the simulation model is collected from the most current public opinion polls that are available for each state. Since new polls are conducted almost daily, the probabilities frequently change.

Of course the polls only reflect the electoral vote outcome for a single state so while the results do vary, the magnitude a particular change is dependent upon the size of the state. For example, a change in the public polls for Florida with its twenty-nine electoral votes has a far larger impact on the outcome of the national election than does a change in Delaware with its three electoral votes.

The model has been run weekly since the middle of May. With the latest set of polls President Obama’s probability of winning has dropped slightly from 93% in the previous week to 88% this week. With this drop for the President, Governor Romney’s probability of winning the election has risen from 6% the previous week to just over 11%. The probability of a tie – both candidates receiving 269 electoral votes – has also risen to just under 1%.

As events unfold over the next five months the polls will reflect the opinions of the electorate to those events. With the changing polls the probability of a particular candidate winning the election can change as well. If a third party candidate enters the race and is included in the polls then that candidate’s impact can also be modeled.

While polls provide a snapshot of the opinion of the electorate, this statistical modeling technique can use these opinions to make quantitative predictions about the November outcome.

Comparison of Predicted Electoral Vote Outcomes

Trend of Probabilities for Winning the November Presidential Election

Posted in Polling - Tagged , ,

The Political Express
G. Terry Madonna, editor
Log In