Slashdot Mirror
Political Affiliation Can Be Differentiated By Appearance
quaith writes "It's not the way they dress, but the appearance of their face. A study published in PLoS One by Nicholas O. Rule and Nalini Ambady of Tufts University used closely cropped greyscale photos of people's faces, standardized for size. Undergrads were asked to categorize each person as either a Democrat or Republican. In the first study, students were able to differentiate Republican from Democrat senate candidates. In the second, students were able to differentiate the political affiliation of other college students. Accuracy in both studies was about 60% — not perfect, but way better than chance."
Of course, if you RTFA, the photos of other students were all Caucasian.
So if you always said a "black guy" was a Democrat, it wouldn't have any effect on the results at all.
Statistical significance can't be pinned down to a number like .8% in the general case - statistical significance is hugely dependent upon the sample size. However, the parent poster is correct in that the article was referring to statistical significance, not necessarily to a huge correlation. Generally speaking, a study like this makes an assumption that there is no connection between appearance and political affiliation (i.e. the average accuracy of these guesses should be something like 50% - could be higher or lower depending on how the study was executed - if there were 3 possible parties to choose from instead of two for example, or if it was well known that 90% of the participants all belonged to a given party). They then execute an experiment which provides evidence for or against that hypothesis. Whatever they were expecting (let's say it was 50% correct answers if it was totally random), they found 60% correct answers - and because of the number of people participating in the study, they determined that the chances that they would find 60% correct answers if the guesses really were random (i.e. there was no hint from appearance) would have been astronomically small. In this way, 60% correct can give incredibly convincing evidence that appearance is linked to political affiliation, even if that link is relatively subdued (after all, 60% is not that much more than 50%).
Next time, click both links before you post.
I've lost all my marbles except one & It's fun to test angular & centripetal acceleration in my skull
Somehow I think you and I have a different understanding of the term "Irish Republican"
60% versus 50%? How is that WAY better?
With a large enough sample size a result like this can be highly statistically significant, but still useless as a predictor.
For example, if I have 2000 marbles, half white and half black, and pull them out randomly and ask you to predict what colour each one is, if you guessed correctly 60% of the time (you got 600 white marbles correct and 600 black marbles correct) you'd be bumping up against three sigma (over 99%) odds of your results NOT being due to chance, but some incredible marble-colour-guessing gene that evolution or possibly archeobacteria had slipped you. Up the number to 20,000 marbles with 60% accuracy and you'd be a proven phenomenon, even though you utility as a marble-colour picker would be pretty much useless unless it also happened to work on a roulette wheel.
This is something that it can be hard for people outside the machine learning community to understand: an enormously significant result, statistically, can still make for a practically useless classifier.
Blasphemy is a human right. Blasphemophobia kills.
Indeed. Or my take on it: there's a difference between statistically significant and actually significant.
I live in constant fear of the Coming of the Red Spiders.
The latter is a subset of the former.
Give me Classic Slashdot or give me death!
A cursory look at TFA indicates that both types of misclassification rates in this study are found to be in the range 40%-50% (approximately in each study). That is piss-poor. For comparison, a typical Bayesian spam filter has both misclassification rates in the 1% range, and people still complain about that.
The correct conclusion should really be that looking only at peoples' faces is a really bad way to gauge political affiliation. Slow news day, eh?
The quote refers to the old Liberal party, not the Lib Dems. The Liberals were the traditionally party of business interests (and so favoured the Commons) and the urban/suburban middle class. They supported free trade, and had the support of several protestant churches.
For comparison, the Conservatives were the party of old money (and so favoured the Lords), the rural middle and upper class, the aristocracy, and those associated with them. They were protectionist, imperialist, and were closer to the High Church. Labour were the party of the industrial working class, and were generally socialist
1) Banks are taken over by the government every year since the inception of the FDIC. The FDIC promptly sells them off (to some other bank). The ownership by the FDIC is for an extremely short period of time and the sale is usually worked out before they even take control of the failing bank.
2) What are all these other private businesses he's taking over?
3) Capitalism is merely ownership of private property (look it up if you don't believe me). Nothing more. Free markets and everything else is shit that's added on to the concept. You may be thinking of " laissez-faire" capitalism but that's not required to be a "capitalist" nation. In any event, there have never ever been truly free markets. It's not possible to have in the real world, only on paper. I can explain why but think it through and I'm sure you can figure it out.
4) The government telling businesses what they can and can't do has occurred since the inception of the country. It has always been and always will be and has occurred in every country that has existed in all of human history. This will never change. The only difference is to the degree that it occurs. Now, you may think that him telling companies like Goldman Sachs that they are in for new regulations is inappropriate but I don't. They fucked over the country and they are being rewarded for doing it. In other words, they are asking for it.
All the regulations that exist on the books exist for one of two reasons: 1) A lobbying group successfully managed buy enough senators/congressmen to get their way, or 2) a business or particular industry fucked over enough people that congress had to do something about it to keep their jobs.
Finally, neither party gives a flying shit about capitalism, they only care about getting re-elected. The Republicans talk a good game but did you think it was a free market, capitalist idea for Bush to require Medicare by law to NOT negotiate and to pay for drugs at the maximum price while simultaneously massively increasing national debt? Bush also had no problem with oil subsidies. Parties are playing a game and that game is to keep you so confused, you don't know which way is up and they are good at it. In the end, they are in it for themselves. And trust me, they need each other. Neither party could survive a year without the other to blame for everything.
Are agnostics skeptical of unicorns too?