I’m looking for a research assistant at Princeton to work on a gerrymandering project at a scholarly level, i.e. for academic research. It will also have practical implications. There’s a posting at the Student Employment office – look for posting #35677! For now, students only please.
February 28th, 2015, 6:30am by Sam Wang
January 20th, 2015, 11:50am by Sam Wang
In a recent CBS poll, Republican voters were asked who they wanted to see run for President. In terms of the net yes-minus-no percentage, leading the pack were Mitt Romney and Jeb Bush. Trailing, but still with net positives were Mike Huckabee, Scott Walker, Marco Rubio, and Ben Carson. In negative territory were Ted Cruz, Rand Paul, Rick Santorum, and Rick Perry. Bringing up the rear? Chris Christie and Sarah Palin.
Palin is an interesting “control experiment” since her political career is basically over. Using her to define a maximum lack of enthusiasm (1 Palin unit, or 100 centiPalins), and Mitt Romney to set the high-enthusiasm end (0 centiPalins), Governor Christie is at 77 centiPalins. Whatever GOP voters want seems not to come from New Jersey.
January 2nd, 2015, 1:13pm by Sam Wang
Since mid-December, President Obama’s net approve/disapprove numbers have shot up. This graph shows the median of the last 21 days of polling. The current level, a net disapproval of only 2%, reflects six pollsters (Gallup, Rasmussen, CNN, ARG, YouGov/Economist, and ABC/Post). These are his highest numbers since early 2013. What is going on?
First, a caveat. A jump of this size and suddenness is surprising. Reasons should be offered with care. For example, I still don’t have a good explanation for the dive in Obama’s numbers in June – and that was a drop of similar size. Still, this recent jump occurred with multiple pollsters, suggesting that it’s a real phenomenon and not some artifact of changing methods.
To identify possible causes, we should look to events prior to the jump. The obvious event is the President’s newfound liberation from the pressures of the election cycle. Since the November election, the President has done the opposite of what many people expected: he showed strong assertiveness to Congress (shortly after November 4), acted boldly on immigration (November 20), made frank public statements on race (December 17), and normalized relations with Cuba (December 17). Could it be that voters like a strong leader?
It could be asked whether, from an electoral standpoint, these actions would have been welcome before the election. However, that is a mixed bag. Consider an alternative scenario, in which Obama had acted like this earlier. That might have been worse for his policies since loss of the Senate was still likely, as well as retained GOP control of the House. Those defeats would then cast a shadow on Obama’s actions and lead to pressure to reverse them. In the current situation, the President has little reason to change course.
I’ll get out on a limb with a speculation: If this “real Obama” uptick lasts, it might demonstrate a benefit to Democrats if they act, with vigor, like Democrats. With a newly invigorated President and a Congress in full opposition, the coming year will be worth watching.
Postscript: The most plausible trigger seems to be normalization with Cuba, which was huge news and reminded people of the unique power of the Presidency. This is a time when crosstabs would be helpful. Is the uptick concentrated among Hispanics? Democrats? Independents? For now, I leave that to readers and other analysts…
November 10th, 2014, 9:26am by Sam Wang
At The American Prospect: Tweet
In the home stretch, I wrote that midterm polling is far less accurate than in Presidential years. Today, in The American Prospect, I detail how this year’s polling errors are correlated with voter turnout, which was the lowest since 1942, as based on Michael McDonald’s tabulation so far. In 2014, Democrats underperformed expectations by over 5 percentage points on average, the largest such error in over 20 years. State by state, underperformance was correlated with low turnout. This suggests that voter apathy on the Democratic side was a significant factor in the 2014 election. Here’s the article.
From a polling standpoint, estimating turnout is likely to be a major source of systematic error. Here are some details of this year’s GOP “bonus.” [Read more →]
November 5th, 2014, 11:41am by Sam Wang
Pre-election PEC Senate aggregate: 52 Republican seats.
Outcome: 52 or more Republican seats (Alaska is not called, and Louisiana goes to a runoff).
As I wrote in The New Republic, last night’s performance by the GOP was remarkable. In close Senate races, Republicans outperformed polls by an average of 5.3 percentage points. Prime examples of that effect could be seen with Republican wins in Kansas and North Carolina, two races that went against pre-election polls.
In gubernatorial races, Republicans outperformed polls nearly 2 percentage points on average. This was enough to put Paul LePage of Maine (tied), Rick Scott of Florida (tied), and Bruce Rauner of Illinois (Quinn +2.0%) over the top. All in all, Republicans had an excellent night.
Historically, midterm polling is much more prone to large biases than in Presidential years. In 2010, Democrats benefited; in 2014, it was Republicans. In six Senate races that were polling within less than three percentage points, two were won by the lagging candidate. That is entirely in line with past results. Added to the median poll-based snapshot of 52 Republicans, 48 Democrats+Independents, the result could be as large as a convincing 54-46 majority.
Before the election, I pointed out the possibility that polling bias could go in either direction. It is likely that pollsters face a tough challenge in identifying likely voters in an off-year.
With control the Senate so closely fought, even a small bias put into question who would control the chamber. And, as I wrote, it also opened the possibility of a GOP blowout. I said we didn’t know what would happen. Maybe we can call that my Peggy Noonan moment.
Over the weekend I suggested Brier scores as a way to compare predictions. Aggregators and analysts did worse than in 2012, when polls did not miss any races (PEC Brier score, 0.01; scores close to zero are considered good).
I used final probabilities as listed at The Upshot to calculate Brier scores. The lowest (and therefore best) score came from Drew Linzer (DailyKos Elections), who took a Bayesian polls-only approach and ended up with a Brier score of 0.10. Coming in second was The Washington Post with a mostly-polls approach, at 0.12. Next came HuffPost, FiveThirtyEight, and Betfair got 0.14, followed by The Upshot at 0.15. And finally we have PEC, with 0.18. Although the number of “misses” (i.e. being on the wrong side of 50% probability) was no worse than the other sites, we were done in by an across-the-board lack of certainty, which we predicated on the unreliability of midterm polls. Congratulations to Drew Linzer!
Postscript: as pointed out by commenter Paul, Drew Linzer shines even more if his calculation’s performance in the several months prior to the election is included.
P.P.S.: Doug Rivers at YouGov has evaluated his own organization’s miss of actual-voter behavior, as well as that of other polling organizations. The findings seem consistent with what I’ve reported here.
November 4th, 2014, 9:23pm by Sam Wang
See below the fold for older commentary. The most recent comment will appear up top.
12:10am: Tonight’s performance by the GOP has been quite remarkable. In close Senate races, Republicans seem to be outperforming polls by around 5 percentage points. That goes a long way toward explaining what is happening in Virginia. In close gubernatorial races, Republicans are outperforming polls by about 3 percentage points.
I did say that historically, midterm polling can be off in either direction by a median of 3 percentage points – far worse than Presidential years. Tonight is certainly consistent with that.
11:30pm: Ernst will win Iowa. Other than New Hampshire, it’s looking like a sweep of close races by Republicans. Counting CO, GA, IA, KS, and NC gets to 52. Alaska and Louisiana are still outstanding, but that’s icing on the cake for the GOP.
November 4th, 2014, 7:09pm by Sam Wang
See below the fold for older commentary. The most recent comment will appear up top.
8:40pm: The Upshot has projected counts. For now, use those for your Geek’s Guide. Shaheen (D-NH) around +5% and McConnell (R-KY) around +13%, both ahead of their pre-election polls. Ambiguous for estimating Delta.
8:27pm: Reader Forrest asked me how The Upshot estimates vote share from partial returns. I can’t say what they are doing, but look at Jay Boice’s HuffPollster calculation. Basically take the prior history of the state, county by county (or whatever level of granularity you have available). Then slide over all the counts in past comparable elections, and see how each county would have to break in order to reach a 50-50 tie. Use that as an over/under, i.e. calculate whether a candidate is over/underperforming that expectation. Then do a weighted average across counties. That is an estimator of the margin between candidates. [Read more →]
November 4th, 2014, 2:00pm by Sam Wang
From 2004 to 2012, only thirteen Senate races have had margins of less than three percentage points in the week before the election. Of these, four were won by the trailing candidate. One more, the Florida 2004 race, was tied in the polls, and was eventually won by the Republican, Mel Martinez, by 2 percentage points. Scoring that one as half correct, the overall rate of wins by a front-runner is 65%, a bit better than chance.
In light of that, the probability that all six close Senate races (AK, CO, IA, KS, NH, and NC) will be won by the candidate in the lead is only 7%. A wrong call is almost inevitable. We should not be surprised to see one to three races to be won by the candidate who trails this morning. This allows us to hazard a guess as to the most probable path to Democratic retention of the Senate (which PEC currently has at 35%). [Read more →]
November 4th, 2014, 12:00pm by Sam Wang
Download it! It includes instructions for estimating Delta. Liveblogging will start around 8:00pm.