2012 October | Data Science & Psychology

26Oct/12

Likely Voter Models Should Be Applied to Polls Probabilistically

One of the many great points I took from Nate Silver's recent book, The Signal and the Noise, is that people are generally bad at dealing with uncertainty. We want the weather forecaster to tell us if it's going to rain tomorrow, not that there is a 30% chance, even though that's the right answer. Nevertheless, weather forecasters have failed enough, in part because they get feedback every day, that they insist on giving us probabilities. Perhaps pollsters haven't failed enough, as they still continue to insist that they can categorically predict who is going to vote and who isn't. Since voting records are largely public (whether you voted, not whom you voted for), a recent study by Todd Rogers and Masa Aida was able to actually look at how effective it is to ask a respondent whether they plan on voting. Below is a chart showing what % of people who reported each intention actually voted.

Percentage Who Actually Vote x Reported Intention in 2008 (from Rogers & Aida)

Pollsters can predict who votes and who doesn't above chance, but in the same way that poker players probabilistically predict the likelihood of winning a hand, accepting the inherent uncertainty, pollster predictions on who votes are also likely to be wrong much of the time. Pollsters should realistically adopt the same tactics as poker players who multiply the expected outcome (the size of the pot vs. what they have to put in the pot) by the likelihood of the outcome (the odds of the right cards coming to win the hand) in order to determine their decisions. Similarly, polling would be vastly improved if pollsters weighted votes by voting intention rather than categorically deciding that a person is or is not a likely voter. What would be the result?

Right now (October 26, 2012) Romney is leading Obama in Gallup's survey 51-46 among 2700 likely voters, but they are tied 48-48 among 3,050 registered voters. If one does the math, Obama leads Romney approximately 63-25 among unlikely voters. If the pattern from the above paper remains this year (percentages are very different in non-general elections, btw), then we could apply a weight of .87 to likely voters (since 13% don't vote) and a weight of .55 to unlikely voters (since 55% do vote), which would predict that Romney would get 51% of the overall vote and Obama would get 49%, a result which pushes Gallup's result far closer to the average of other polls, where Romney has a slight lead nationally, and is slightly behind in the battleground states.

- Ravi Iyer

Tagged as: obama, registered voters, romney, uncertainty, voting records Comments Off

19Oct/12

Be the Bipartisanship you want to see in the World by Supporting our next President

The point of politics is to make people’s lives better. Liberals and conservatives may disagree about how to do that, but despite the heated rhetoric, there are a number of broad goals that most anyone would agree upon. Consider a survey we recently conducted concerning liberal and conservative preferences about the kind of place they would like to live. While there are differences in terms of priorities, the top 5 desirable attributes are largely the same. Everyone wants a strong economy, safety, clean air and water, and good medical care.

Top 5 Desirable attributes in a city by ideology:

Unfortunately, roughly half of the country is going to be disappointed by the results of the next presidential election. Both history and psychology tell us that this disappointment will likely lead to some amount of demonization of whomever wins, reflexive opposition, and incivility. This may lead to outcomes that nobody wants, such as what occurred during the debt ceiling negotiations.

Thoughtful liberals, conservatives, and both presidential candidates have talked about the need to transcend partisanship in order to attempt to create better policy and a better country. The results of the next election are likely to disappoint some of these thoughtful people, yet it also represents an opportunity for them to be the change they wish to see in the world, by consciously resisting the impulse toward demonization and reflexive opposition. It represents an opportunity to back up words of bipartisanship with action, at a powerful moment when everybody will expect the opposite.

Supporting our next president does not mean that you need to support their policies. We can disagree without being disagreeable. But supporting our next president does mean that we hope they succeed at goals that we all share such as creating a safer, cleaner, healthier, and more prosperous world. It means hoping that the unemployment rate goes down, not up. It means hoping that the poor receive the help they need, whether by charity or government, and that terrorism is stopped, whether by military or diplomatic means. Whomever wins, let’s support them by truly hoping they succeed at our shared goals.

If this resonates with you, consider joining our facebook group and pass this message on to your friends. Positive change always starts with small groups of people who believe in something.

Tagged as: bipartisanship, debt ceiling, demonization, incivility, liberals and conservatives, next presidential election, partisanship Comments Off

3Oct/12

In Defense of Akin: Moral Coherence is common.

Recently, some of my collaborators (Brittany Liu and Pete Ditto) published a paper on moral coherence, which is when people fit their factual beliefs to their moral beliefs. It is a phenomenon very similar to what I've called moral confabulation (I like their term better, so have adopted it). It is a specific example of every person's general desire for coherence and avoidance of cognitive dissonance.

Conservatives are often skeptical of social science (which incidentally, I think is healthy for improving social science), so I was intrigued that a blogger at the prominent conservative blog, Red State, echoed the point that Liu & Ditto make: moral coherence is relatively common. In the blog post titled Everyone Knows Something that Isn't True, the blogger defends Todd Aikin's infamous comments about pregnancy and rape.

I don’t know when I learned that everyone has false beliefs. But I see it all the time, both in myself and in others. I’d hate to have my fate decided by some fact I got wrong. Wouldn’t you?

For instance, I never questioned a belief I had held for years: that the hijackers that flew planes into the World Trade Center on 9/11 came through Canada. On twitter I said that to do anything about 9/11, President Bush would have had to fix security in Canada.

It was then that I learned the hijackers all came through from US airports.

I had no reason, up to that embarrassing moment, to challenge my belief. It’s not that I had a particular bond to my false recollection, it’s that it just never occurred to me that there was anything to challenge. Afterward I realized that the hijackers would have complicated their mission greatly by choosing a foreign country as their takeoff point.

It’s difficult to challenge our own beliefs. That’s why we believe them.

While I don't share the politics of this blogger, the social scientist in me has to admit that the blogger is right. Most of us have factual beliefs that are wrong, often because they conform to/cohere with what we want to believe. Consider how factual beliefs about whether the Packers or Seahawks should have won their latest football game conform to fan sympathies. I won't and can't defend the contents of Akin's comments. But most of us are capable of making comments as ignorant as Akin's. We just usually make them about subjects that are less controversial and in ways that are less public.

Want more examples of moral coherence? Like our moral coherence facebook fan page where we post occasional examples of moral coherence that pop up in the news, where both liberals and conservatives make such errors.

- Ravi Iyer

Tagged as: coherence, conservatives, liberals, moral coherence Comments Off