It's easy to lie with statistics...

...though as Richard Herrnstein once pointed out, it's a lot easier to lie without them. Thus The New York Times is able to pick apart Giuliani's misuse of numbers.

I cited a similar NYT story (about how Giuliani twists New York's abortion and adoption statistics) in this Spectator piece.

Do the pokie-pokie, stay out of the pokey?

Apologies for the title.

Lately, Slate has been writing about a very promising research design: When two variables tend to go together, and you want to see if one causes the other, check to see if they're linked in identical twins, too. Such twins share both DNA and a home environment.

In a new study, the connection between early sexual initiation and later delinquency was at issue. If sex in and of itself causes delinquency, when one twin has sex earlier, he should be more likely to get in trouble later on.

But that twin is actually less likely to become delinquent, according to the study. It seems there are genetic and/or environmental factors that contribute to both sex and delinquency, and once those factors are present, the kid's bound to act out in one way or another. If he chooses to act out via sex, sometimes it's apparently out of his system when it comes to delinquency.

Of course, the left is going crazy with this "sex-positive" finding, acting like we've uncovered a major benefit to teen sex. But the core message is still to create an environment that discourages all misbehavior -- presuming genetics don't completely determine one's actions, this will reduce the odds of both early sexual initiation and delinquency. This study doesn't change the fact that the two are linked in the population at large, meaning that eliminating the underlying factors will cut down on both problems.

I'd like to see similar studies looking at the impact of early sex on (say) emotional and psychological problems. All this one shows is that, if you have a child, early sexual encounters won't actually cause future delinquency, though they still predict it.

Puddle of Mudd review up at antiMusic

I remember seeing these guys tour with Korn after their first record, and it seems they're still around. Here's my take on Famous.

Main point:

A few years back, Puddle of Mudd pushed all the right buttons with Come Clean. Their early-'90s throwback sound netted them a few hits, and they toured with the best in the business.

At that point, they should have called it quits – or at least severely adjusted their extremely grunge-derivative sound. Instead, they kept trying to put out the next Nevermind. The new Famous is exactly what you'd expect from them, meaning it's always inoffensive, often catchy and never innovative.

Penetratoring Huckabee

Note to Adam Thierer: You cannot use Ted Nugentisms like "The Harder they Come, the Harder I Get" and "If You Can't Lick 'Em ... Lick 'Em" to make a serious point. Sorry.

P.S. You missed "Bridge Over Troubled Daughters," "My Baby Likes My Butter on her Grits" and "Sexpot."

Still more on IQ and race

Jim Manzi has a good point: Playing statistics games -- using clumsy regression analyses to try to disentangle genes from environment -- is over. Science has reached the point where we can identify the genes that determine IQ and figure out if they're more common in some races than in others.

However, I think he's a little too quick to go with complete agnosticism. As Half Sigma has been documenting, researchers have found some of those genes, and they're not evenly distributed by race. Also, as William Saletan's article pointed out, brain size itself varies by race, and we've identified those genes. There's still what I've called "wiggle room," but the preliminary evidence is pointing (or at least gesturing) in one direction.

Also, regarding that Saletan article series, Ross Douthat notes a correction in which Saletan apologized for citing J. Philippe Rushton. Saletan realized:

For the past five years, J. Philippe Rushton has been president of the Pioneer Fund, an organization dedicated to "the scientific study of heredity and human differences." During this time, the fund has awarded at least $70,000 to the New Century Foundation. To get a flavor of what New Century stands for, check out its publications on crime ("Everyone knows that blacks are dangerous") and heresy ("Unless whites shake off the teachings of racial orthodoxy they will cease to be a distinct people"). New Century publishes a magazine called American Renaissance, which preaches segregation. Rushton routinely speaks at its conferences.

Douthat's right -- it's hard to believe Saletan researched and wrote a whole IQ article without realizing Rushton was controversial. It's troubling that the Pioneer Fund supported such a fringe group and Rushton speaks at its conferences.

But I would like to point out that the fund has played a major role in mainstream studies:

Two of the Pioneer Fund's most notable recipients are the Minnesota Twin Family Study and the Texas Adoption Project, which studied the similarities and differences of identical twins and other children adopted into non-biological families.

Any psychology student has heard of those two, so let's not discount Pioneer entirely.

New immigration data

The immigration-restrictionist Center for Immigration Studies has a new analysis of Census data. There's nothing all that shocking in it, but it's a great update -- it shows once again how immigration is providing a disproportionate influx of low-skill, uneducated people:

Of adult immigrants, 31 percent have not completed high school, compared to 8 percent of natives. Since 2000, immigration increased the number of workers without a high school diploma by 14 percent, and all other workers by 3 percent.

One can make all sorts of economic arguments about immigration (it's probably about a wash for the native-born, who benefit from cheap labor but lose jobs and pay for immigrants' social services), but to me the best point is social. Intelligence and skills are distributed unevenly through the population, so some Americans have to work in low-skill occupations; bringing in other countries' poor people to compete with them is not in our nation's best interest.

It's true that technological progress has moved lots of Americans out of these low-level positions and into other fields -- in previous generations, even the very intelligent often worked on family farms. When good jobs will go unfilled otherwise , it's not a problem to bring in immigrants to replace the now-white-collar folks. But when American high school dropouts enter a who-can-work-cheapest contest with Third Worlders, immigration poses a threat in the forms of social instability, poverty, unemployment and racial tensions.

Hat tip: Borjas blog.

A pack of cigarettes costs $222!!!!

Not exactly, for those who've seen articles about the study. Basically, the researchers took a very subjective notion, the "value of a statistical life," and extrapolated it.

The idea behind VSL is that people value their lives at a certain dollar amount -- for example, if it would take $1 million for someone to risk 1:1 odds of dying, one could say he values his life at $2 million. Economists have calculated this figure (for example) based on people who take pay cuts to get safer jobs.

What annoys me the most is, the coverage doesn't make it clear that the costs aren't real. You won't actually spend $222; you'll lose time off your life that you'd have valued at $222.

Also, no one's been kind enough to post the full study online, so it's hard to critique the methodology. Some statements from what I've been able to find, like "smoking increases the mortality risk throughout a smoker's life, not just at the end of the smoker's expected lifetime," are ridiculous (show me a verifiable smoking death of a 30-year-old and I'll retract that).

Finally, "[a]t discount rates of 15 percent or more, the cost decreases to under $25 per pack." Not quite sure how that works.

If you don't want the strings, don't take the money

The above line is often given as a defense of government regulations that accompany subsidies. What typically happens is that the federal government steals your money, then refuses to give it back (not even to you, but to your state government) until you pass the laws it thinks you should. If you don't want your state to have stricter drunk-driving laws, well, then you should just refuse federal transportation money and get nothing from the federal tax you paid. That's fair!

It seems a DA in San Diego is using the same tactic with welfare recipients:

[The] D.A.'s office has been sending agents to conduct suspicionless, warrantless searches on the private homes of welfare applicants.

Yes, applicants were free to refuse the searches ... [but that] means forfeiting welfare benefits.

This is a little different from the tax example -- the welfare money didn't come from the welfare recipients the way that transportation money comes from the taxpayers it's being denied to. But it's the same bribe-them-to-give-up-their-core-rights principle, and it's sad the Supreme Court refused to hear the case. The government shouldn't use poverty relief as leverage against the Fourth Amendment.

Explaining state crime rates

Steve Sailer has an interesting discussion, so I'd like to re-post a similar analysis I once did. I edited the original post to match the selection below (I've learned a little more about statistics and was able to make it more accurate).

Being a complete nerd, I've been fascinated lately by my discovery of Gnumeric, a free spreadsheet program that does multivariate statistics.

I've been messing around with crime data. Using the FBI's list of violent crime rates per 100,000 by state as the dependent variable, I factored in race, diversity, income and toughness on crime:

*Race (four variables). Proportions of a given state that are black, Hispanic, Asian and Native American. If a state is 10 percent Hispanic, for example, that figure is .10.

*Diversity. The ELF for that state, or the odds that two randomly chosen people will be of different ethnicities. Calculated by squaring each race's proportion and adding them together, then subtracting that number from 1. A higher ELF means more diversity.

*Income. The average, adjusted for cost of living.

*Toughness on crime. Average time served in months for a violent offense.

The raw correlations are about what you'd expect -- states with higher proportions of whites, low diversity, high incomes and tough sentences tend to have low violent crime rates. But once you throw them all into one regression equation, the results are interesting.

A disclaimer: I'm pretty good at math but don't have much formal training in statistics. Numbers are on the spreadsheet. (One thing Gnumeric does not do well is export files that Google Spreadsheets can use, so I had to do it in html. E-mail me, and I'll send a .xls file as an attachment.)

Here are the coefficients:

% Black: 1902
% Hispanic: 1213
% Native American: 1941
% Asian/Pacific Islander: 175*
Diversity: -308*
Income: .000021*
Tough on crime: -1.14*

The starred results are statistically insignificant, with P values > .05 and/or t-stats between -1.96 and 1.96.

Two very weird things. One, income has no significant effect.

Second, once one takes into account where diversity is coming from, diversity in and of itself doesn't explain the crime rate either (if anything, higher diversity means lower crime). I think this says something for immigration -- the problem isn't that we're taking in people who are different than we are; the problem is that we're drawing from specific populations that commit crimes (or have kids who commit crimes).

This squares with an international analysis I did once failing to find a correlation between diversity and murder rate. (I also found, oddly enough, that diversity and incarceration rate were related -- having different people side by side makes them distrust each other and likely to throw each other in prison, but it doesn't make them kill each other, assuming my results are right and mean something.)

This can't be serious

From the American Prospect, about state ballot initiatives banning racial preferences:

In Colorado...affirmative action supporters sued to keep the "Civil Rights Initiative" off the ballot altogether, claiming its language was misleading. A 3-to-3 State Supreme Court decision in Colorado led to approval for Connerly's organizers to move forward there...

What was that "misleading" phrase that so divided a state supreme court? This:

It said state universities, colleges, and public employers should not "discriminate against, or grant preferential treatment to, any individual or group on the basis of race, sex, color, ethnicity, or national origin in the operation of public employment, public education, or public contracting."

Which of course, means exactly what it says. How do liberals want the initiative to read, "Vote NO on this measure. PLEASE."?

Arbitration nation

Mother Jones has a pretty good piece about mandatory arbitration. Basically, when you buy a car, the contract stipulates that any dispute you have with the company goes through an arbitration firm -- which the company picks. The evidence is pretty solid that these firms tend to find in favor of the company and lose business when they don't. The article speaks favorably of legislation to ban this.

Two quick points. The first is that, frustrating as this is, it's a market outcome. Car companies save money on lawsuits this way and use the difference to offer consumers lower prices. If people were willing to pay significantly more to get rid of the arbitration clause, car dealers would start offering that option. That doesn't seem to be happening.

But two is that "arbitration" has a specific meaning, and it's not "the car company automatically wins." Even if a contract defines "arbitrator" as one chosen by the company, the word still stipulates (or at least heavily implies) neutrality.

If a contract promises arbitration, there has to be some way for a court to determine whether the company met that obligation. Currently, there's "no right to appeal," and "unlike court proceedings, arbitration is secret, with no transcripts or written decisions, so that nosy reporters or other potential plaintiffs can't learn what's going on behind closed doors."

If the companies simply want to say that all their customer-service decisions are final, regardless of what the customer was promised and whether the companies delivered, they should write that into the contracts (good luck finding customers). But they cannot have customers sign over the right to sue and claim to replace that right with "arbitration" if the service provided does not meet the definition of "arbitration."

Activists should focus on making sure arbitration is real, rather than on banning arbitration altogether and hurting freedom of contract.