Those of you interested in political psychology and data science might enjoy my latest post on the Ranker Data Blog entitled Mitt Romney Should Have Advertised on the X-Files. In it, I explore correlations between liking Mitt Romney and liking various TV Shows on lists on Ranker.com, replicating analyses which the Obama campaign purportedly conducted in the last campaign season, and finding that the X-Files and Mitt Romney have a surprising correlation. From the post:
As you can see, the X-Files appears to be the highest correlated show, by a fair margin. I don’t watch the X-Files, so I wasn’t sure why this correlation exists, but I did a bit of research, and found this article exploring how the X-Files supported a number of conservative themes, such as the persistence of evil, objective truth, and distrust of government (also see here). The article points out that in one episode, right wing militiamen are depicted as being heroic, which never would happen in a more liberal leaning plot. Perhaps if you are a conservative politician seeking to motivate your base, you should consider running ads on reruns of the X-Files, or if you run a television station that shows X-Files reruns, consider contacting your local conservative politicians leveraging this data.
- Ravi Iyer
Losing an election is tough and I have immense empathy for those who have a heartfelt vision for their country that was not fulfilled on election day. Most people who care deeply about the election, Democrats and Republicans, do so out of a real desire for the country to do better and it's unfortunate that the results have to disappoint so many well-meaning people.
That being said, there are some conservatives who have implied that those who vote for Obama simply want free stuff, while some liberals imply that billionaires who support Romney do so out of self-interest. Consider this quote from Sarah Palin:
We're not explaining to the rest of America, who thinks that they're going to get a bunch of free stuff from Obama, that you have a choice. You either get free stuff or you get freedom. You cannot have both, and you need to make a choice.
Or consider this quote from Paul Krugman:
billionaires have always loved the doctrines in question, which offer a rationale for policies that serve their interests....And now the same people effectively own a whole political party.
And in reaction to the election results, Bill O'Reilly opined that the reason that Obama gets support is that...
There are 50% of the voting public who want stuff. They want things. And who is going to give them things? President Obama.
What these three quotes have in common is that they all make a common mistake about how we view the motivations of others. Chip and Dan Heath call this "getting out of Maslow's basement", which refers to Maslow's hierarchy of needs depicted below.
Maslow's idea was that motivation can be grouped from lower level needs such as wanting "stuff" to higher order needs like caring about others, fulfilling values, etc. The implication of O'Reilly, Palin, Krugman, and many partisans, is that the other side is motivated by these lower level needs. It is a common mistake, made in many domains to believe that others are motivated by lower level needs. Chip and Dan Heath have shown that we all assume that other people are motivated by lower level needs, but that we ourselves are motivated by higher order needs. The truth is that most everyone is actually motivated by higher order needs. In the below video, they explain one of many studies showing this.
It is easy to let partisanship help you impugn the motives of others. And there is no doubt that some amount of self-interest helps shape our values. However, most people who care enough to vote do so out of higher order considerations. Indeed, nobody stands in an 8 hour line to vote out of self-interest. They really do want to help the poor or promote economic growth and freedom. And if we ever want to fulfill the bipartisanship we desire in the world, we would do well to understand the sincere motivations of others.
- Ravi Iyer
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.
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
Like this if you are registered to vote, share it if you want to see which of your friends are registered.
The title of this post is a blatant attempt to go viral, though hopefully for a good cause. A new study recently published in Nature estimates that a similar viral message touting voting behavior, led to 340,000 more votes in the 2010 election. Human beings are naturally social creatures and if we see our close friends doing something, we're more likely to do that too. It's actually an old, well researched topic in social science, so it's not so surprising that social influence works, but what is great is that in the new modern connected world, we can actually consciously create benevolent social influence and measure it's actual impact. You've always seen it in fundraisers where people ask their friends to help them run a race for charity or in telethons, but Facebook opens up entirely new possibilities, including using social influence to get your friends to register to vote (and hopefully vote, though I'm pretty sure Facebook will have that covered again this time). Such is the purpose of this blog post or feel free to create your own version as there is nothing magical about this post. Any post with a similar title will work. Or you can make up your own title for some other pro-social cause, harnessing the power of social influence for good.
So like this post if you are registered to vote, and share it with your friends if you want to see which of them are registered! And if you don't know who to vote for, check out or Obama vs. Romney quiz at VoteHelp.org.
- Ravi Iyer
The Republican National Convention is going to take place this week and one of the stated goals of many republicans is to "humanize" Mitt Romney. It reminded me of this graph that I pulled from our yourmorals.org database which looks at systemizing vs. empathizing scores. Based on work by Simon Baron-Cohen, the measure concerns how much one likes to analyze and construct systems as a way of understanding the world (e.g. being fascinated by how machines work) versus trying to understand social situations and empathize with others (e.g. I am quick to spot when someone in a group is feeling awkward and uncomfortable.). Men (in general) tend to systemize, while women tend to empathize and this difference tracks rates of autism (Baron-Cohen's main line of research), which strikes 4 males for every 1 female. Men also tend to support Romney vs. Obama.
This graph shows the correlation between favorability ratings of potential 2008 presidential candidates and the difference between systemizing and empathizing scores for those candidates' supporters.
Based on our libertarians research, we would have expected Ron Paul supporters to have the highest systemizing vs. empathizing scores and certainly his supporters do have a positive, and relatively high correlation. It is similarly unsurprising that Hillary Clinton's supporters in 2008 tended to be empathizers, or that Democrats generally tend to attract empathizers, rather than systemizers. What surprised me, however, was that Mitt Romney's supporters appear to have the highest systemizing vs. empathizing difference. Does this reflect something intrinsic about Mitt Romney, or at least his image? After watching some of the Sunday shows today, I think so.
Consider this quote from ABC's This Week, by George Will, a conservative who observed that "with most politicians, the problem is their inauthenticity. His (Romney's) problem is that he is authentically what he is...he has a low emotional metabolism. That's who he is. He can't turn to the country and say I feel your pain because the pain isn't his. It's other people's. What he can say is that I can fix your pain and that should be good enough for most people, unless we are electing a talk show host".
Mike Huckabee said something similar on Fox News Sunday about likability being less important than technical skill. These are perhaps inherent admissions by some of Mitt Romney's supporters that his strength is in appealing to systemizers, and therefore, they would like frame the debate in those terms. It will be interesting to see whether Mitt Romney aims his Republican National Convention nomination acceptance speech at empathizers or at systemizers.
When the NY Times or Gallup reports that Obama or Romney has a lead in the polls, how do they know this? Typically, they pay people to randomly call people and they extrapolate from this sample, using established statistical methods, to make generalizations to the population. Some groups won't respond, especially young adults who often have cellphones and screen their calls. Many people I know are like this.
Polling guru, Nate Silver, has written about this issue extensively, and Pew has researched it as well. Cell phone users tend to be younger and more liberal. Pollsters are used to correcting for such selective non-response (e.g. men selectively non-respond more than women) by weighting their answers. However, this critically relies on having a variable that you can use to do this weighting. If cellphone users simply differ on demographic dimensions, weighting should work, but if they differ on other dimensions such as Big 5 personality traits or values, then pollsters will be unable to weight their data.
Do cell phone users differ from landline users on psychological dimensions? The answer is fairly common sense as this is an issue that we all have lots of anecdotal data on. Of course they do. The below chart compares cellphone users to landline users based on visitors to yourmorals.org who answered a question about their phone usage, with traits related to landline use at the top and traits predicting cellphone use at the bottom.
Cellphone users value stimulation, achievement, and hedonism more. They value tradition, conformity, and security less. They are less conscientious, more liberal (especially on social issues), and are younger. Some of these variables are things that pollsters can address by weighting their results (e.g. youth and liberalism), but other variables are things that pollsters do not measure and therefore cannot directly weight for.
Since some of these things vary by ideology, gender and age as well, we can statistically control for these factors and see if we get fewer significant predictors of cellphone usage. Valuing stimulation and achievement are the remaining significant predictors with valuing tradition and being socially conservative as marginally significant predictors. Other psychological variables such as being conscientiousness and valuing hedonism are accounted for by controlling for factors that pollsters likely can weight for. As such, perhaps these psychological variables are less problematic. It is worth noting that valuing stimulation remains by far the best predictor of cellphone usage (after age) in regression analyses controlling for demographic variables (beta = .13, p<.001).
The yourmorals.org sample is not a representative sample, but I think that might be better in this case. Trying to measure characteristics of people who use cellphones, which I would assume correlates with screening calls and generally being less responsive to surveys, might be better done using non-phone means so that your measurement interacts less with what you are measuring. The educated, internet savvy users who tend to answer yourmorals surveys are exactly the kind of people you might want to examine and be unlikely to poll via phone. Further, we aren't interested in whether the overall population has differences between cellphone users and landline users. That could be a function of youth (the biggest predictor here). Rather, we are interested in whether people who have the exact same demographic characteristics and vary only in terms of their cell phone usage may differ in meaningful ways as it is this variance that would confound pollsters. Using a particular non-representative sample can actually be better for answering questions about the relationship between variables, as certain differences are naturally controlled for with the whole sample being generally internet savvy, educated, and white. But certainly these findings (like all social science) need to be replicated by others in other datasets to have more confidence.
The take home message? As noted by Pew and Nate Silver, polls will have to have cellphone samples in order to avoid bias that likely skews against liberal candidates. Second, if my intuition that heavy cell phone users are unlikely to respond regardless is correct, then even pollsters that poll cellphones may have to start thinking about weighting for non-traditional variables that are a proxy for these psychological variables that predict non-response. Silver suggests "urban/rural status, technology usage, or perhaps even media consumption habits". Third, the psychological profile of cellphone users (seeking novelty, being socially liberal and not valuing tradition) suggests that polls might exhibit more bias on social issues such as gay marriage, and other issues which could reasonably be said to correlate with being a novelty seeker. These effects aren't big, but in a world where a few percentage points is big news, they are worth considering when digesting poll results.
- Ravi Iyer