Monday, August 13, 2012

Breaking: Romney Errs in VP Pick

Today campaign insiders admitted to reporters that Mitt Romney, the presumptive Republican president candidate, meant to ask Ron Paul to be his running mate but accidentally dialed Paul Ryan.

The 65-year old presidential candidate released a statement saying "I used to have contacts sorted 'Last, Name' on my Rolodex but on this iPhone thing it's 'First, Last.'" Inquiries about whether the candidate planned to dump Paul Ryan from the campaign and nominate Ron Paul were met with stonewalling.

Political analysts say it doesn't really matter who gets the nomination as the Ron Paul Revolution crowd will vote for anyone who throws them a few libertarian bones about lowers or a nugget of a conspiracy theory. Insiders have even suggest Paul Ryan may have more appeal to the Birthers, 9/11 truthers, and other conspiracy theorists because of his ties to a government conspiracy to defraud investors.

Friday, August 10, 2012

Scott Brown is more of a dick than I thought

I didn't know much about Scott Brown until his reelection campaign heated up.

Evidently he is demanding that Elizabeth Warren pay to mail voter registration forms to people getting government assistance. They were supposed to have been given the forms when they applied for the benefits, just like how you get them when move and get a new license, but Brown thinks this is a conspiracy to get votes for Warren.

What a dick.

More details here.

Thursday, August 9, 2012

Clinical psych is hard: Kids edition

A clinicial pyshologist writes in the New York Times that she has found that,
[t]he happiest, most successful children have parents who do not do for them what they are capable of doing, or almost capable of doing . . .
The central task of growing up is to develop a sense of self that is autonomous, confident and generally in accord with reality.
The research I've seen says that having a better sense of reality is correlated with depression. Having a small reality distortion field that allows you spin things in a positive light is a key part of being satisfied with your life.

Likewise I don't understand how the author sees no trade-off between being happy and successful. There could, of course, be a positive correlation, and the research on flow suggests that people who succeed doing things they like are happy and likewise it makes sense that people who enjoy what they do will be more motivated. So maybe happiness and success should be correlated.

But mostly you would expect a tradeoff. The way people become exceptional--remember we are talking about "most successful"--is by doing a ton of directed practice. And directed practice is hard work, exhausting, and it sucks. Working 80+ hours a week sucks, even when you generally like your work, when it inevitably cannibalizes your social or family life.

I know from experience that most of the most successful kids, a few years down the road when they are at MIT and Harvard, are not particularly happy.

Wednesday, August 8, 2012

Statistics is hard: Type 1 error edition

Matt Yglesias notes that data dredging is a major potential downside to "Big Data:"

Given a nice big dataset and a good computer, you can come up with any number of correlations that hold up at a 95 percent confidence interval, about 1 in 20 of which will be completely spurious.
But that isn't really right at all. The number of spurious correlations is probably far higher.

Let's start with where the 5% spurious figure comes from. If we test a true hypothesis that there is no linear correlation between two variables at the 5% level, then we will find a significant correlation between the two uncorrelated variables about 5% of the time. If we test a bunch of true null hypotheses that pairs of variables are uncorrelated about 5% of those pairs will show up in our list of significant correlated pairs.

But what percentage of the correlations on the list are spurious?

100% by assumption!

The key parameter for estimating how many of the correlations are spurious is the percentage of pairs that are uncorrelated, call it p. The other parameters that matters which is how often true correlations are detected, the power function of the test, and a distribution of correlation coefficients for the variables are are correlated.

Let's assume for simplicity that all false null hypotheses are rejected 100% of the time. Then we can use Bayes rule to figure out the percentage of spurious correlations:

P(spurious | null rejected) = P(null rejected | spurious)P(spurious)/P(null rejected)
From earlier P(spurious) = p and P(null reject | spurious) = 0.05
P(null rejected) = correct rejections on the 1-p false nulls and 0.05p incorrect rejections = 1-p+0.05p

P(spurious | null rejected) = 0.05p/(1-p+0.05p)

If p > 20/39 then more than 1 in 20 of the correlations we find is going to be spurious. p being close to 1 seems most plausible since we can imagine testing all sorts of bizarre correlations like the relation of the number of vowels in your last name to cheddar consumption on a given day--for each day of the year. That gives us 365 hypotheses to test. We could add 365 more for each type of cheese and that is just the tip of the iceberg. How many of those hypotheses have a genuine relationship?

Obama: "I didn't pass that"

Today President Obama has reversed his position on "you didn't build that" explaining that the conventional wisdom was right and he "was wrong." He went on to say that he bears no responsibility for Obamacare because "I didn't pass that, the congress did." When asked if the political pressure he exerted on party members and the input his administration had on crafting the bill counted for anything he said "about as much [credit] as the police should get for preventing theft thus protecting profits--absolutely zero percent."

Democratic House Majority Leader Nancy Pelosi  said she did not agree with the president because "most Americans are too dumb to understand proof by contradiction or his point here." She reiterated that "most Americans are so fucking stupid they think small business owners invented the Internet." 2000 election popular vote winner Al Gore declined to comment on the origins of the Internet was asked.

The president was not the only candidate backtracking today. When informed of the president's comments, Republic nominee Mitt Romney exclaimed "that's right . . . I passed a pretty much identical bill in Massachusetts! Give credit where credit is due, Mr. President" to roaring applause but quickly backtracking and asking an advisor, "how do I twist this so I am not responsible for Romneycare but he is responsible for Obamacare?"

Recent polls show that 65% of Americans believe small business owners built America's roads. When asked if a business that started paying taxes after a road was built could take credit for building that particularly road, a plurality responded "whatever choice will make Obama sound bad."

Monday, August 6, 2012

Economics is dangerous: CCP "Justice" Edition

China has a long standing tradition of accepting body doubles to stand in and take the punishment of crimes committed by the rich. The response of CCP officials is a textbook example of how learning a little bit of economics can be dangerous:
Some imperial Chinese officials who admitted to the use of substitute criminals justified its effectiveness. After all, the real criminal was punished by paying out the market value of his crime, while the stand-in’s punishment intimidated other criminals, keeping the overall crime rate low. In other words, a “cap-and-trade” policy for crime.
That, of course, is nonsense. You could get the result in a simple model where every agent is identical. When everyone is identical it is easy to talk about the right tax level to internalize the externalities of your crime because everyone faces identical constraints with identical preferences. But one of the obviously important facts is that a stand in and the criminal perceive the cost of the punishment differently (or the benefit or the money exchange) hence the "trading" of places.

How much do you think Li Gang's son  would have to had to pay for the college girl to accept being murdered? That is the real "market price" of his crime, not the amount the lowest bidder is willing to pay to be executed.

And hasn't the CCP ever heard of public goods? Do you think Li Gang's son has enough money to compensate the hundreds of millions calling for his head, each of whom would gladly pay a few yuan to watch him die? I think in CCP logic he should be executed to ensure the "Pareto efficient" outcome.*

* - Yes, that is sarcastic. Pareto efficient means all parties are better off or at least as well worse after the trade. Surely Li Gang's son would not agree to die even for that enormous "market price" any more than the woman he killed would have agreed to die for the CCP dubbed "market price" of her life.

Saturday, August 4, 2012

Math is good: Jared Diamond edition

Diamond, who is an excellent scholar, writes this nonsense in a discussion of health and economic growth:

 Tropical diseases cause a skilled worker, who completes professional training by age thirty, to look forward to, on the average, just ten years of economic productivity in Zambia before dying at an average life span of around forty, but to be economically productive for thirty-five years until retiring at age sixty-five in the US, Europe, and Japan (average life span around eighty).
This isn't right because there is a difference between average life expectancy and conditional life expectancy. It is easy, maybe even natural, to assume that if life expectancy is 40 and you are 30 you can expect to live 10 more years. But that isn't right, if you are 45 do you expect to live -5 years?

It turns out that this isn't an innocuous mistake. The low life expectancy in Zambia is driven by high child/infant mortality and a high AIDS prevalence. If you survived your childhood and don't have AIDS, then you will live into your 70s, on average, and probably die from cancer or heart disease like most Americans. A priest in Sierra Leone told me that they having a saying to that effect (paraphrased): "If you live to 18, you will live to 80."