Posts Tagged ‘statistics’
In oral arguments before the Supreme Court last week, Chief Justice John G. Roberts Jr. introduced a statistical claim that he took to imply that an important provision of the Voting Rights Act has become outmoded.
Section 5 of the Voting Rights Act, which is being challenged by Shelby County, Ala., in the case before the court, requires that certain states, counties and townships with a history of racial discrimination get approval (or “pre-clearance”) from the Department of Justice before making changes to their voting laws. But Chief Justice Roberts said that Mississippi, which is covered by Section 5, has the best ratio of African-American to white turnout, while Massachusetts, which is not covered, has the worst, he said…
As much as it pleases me to see statistical data introduced in the Supreme Court, the act of citing statistical factoids is not the same thing as drawing sound inferences from them…
Like other polls, the Current Population Survey is subject to sampling error, a result of collecting data among a random subsample of the population rather than everyone in the state. In states like Massachusetts that have low African-American populations, the margin of error can be especially high: it was plus-or-minus 9.6 percentage points in estimating the black turnout rate in 2004, according to the Census Bureau. Even in Mississippi, which has a larger black population, the margin of error was 5.2 percentage points…
The debate might be more constructive if we return to the substantive questions that I posed earlier. First, are the voting rates in Massachusetts and Mississippi representative of a broader trend? If so, it seems wrong to suggest that Chief Justice Roberts misconstrued the data merely because he failed to mention the margin of error. But if Massachusetts and Mississippi are outliers, then the chief justice may be guilty…Cherry-picking the evidence…is the greater statistical sin, in my view, since it involves making misleading rather than merely imprecise claims.
The bigger potential flaw with Chief Justice Roberts’s argument is not with the statistics he cites but with the conclusion he draws from them…
…The fact that black turnout rates are now roughly as high in states covered by Section 5 might be taken as evidence that the Voting Rights Act has been effective. There were huge regional differences in black turnout rates in the early 1960s, before the Voting Rights Act was passed. (In the 1964 election, for example, nonwhite turnout was about 45 percent in the South, but close to 70 percent elsewhere in the country.) These differences have largely evaporated now.
How much of this is because of the Voting Rights Act, as opposed to other voter protections that have been adopted since that time, or other societal changes? And even if the Voting Rights Act has been important in facilitating the changes, how many of the gains might be lost if the Section 5 requirements were dropped now?…
Statistical analysis can inform the answers if applied thoughtfully. But statistics can obscure the truth when they become divorced from the historical, legal and logical context of a case.
Roberts proved to the world that opportunism holds a higher priority in his pantheon of justice – in his testimony before Congress when he was being confirmed for office. Almost every decision since has reflected that opportunism, lack of forthcoming honesty. A few recent cases may illustrate qualms on his part – I hope.
Regardless, Nate Silver stands as the voice of expert testimony about statistics which the Republican Party learned to their recent dismay.
Average life expectancy is one of two statistics commonly used to compare the health-care systems of different nations. (The other is infant mortality.)
One of the puzzles about the U.S. system is that we spend far and away the most money per capita for health care, but we rank 50th in average life expectancy — after Macau, Malta, and Turks and Caicos, among others.
We are all familiar with statistics about how much of health-care spending takes place in the last year of life, and with stories about old people who are tortured with costly treatments they don’t want and which prolong dying but don’t extend life in any meaningful sense.
Certainly, ailing old people should be allowed to die in peace, if that’s what they want, and not be subject to excruciatingly painful surgeries and drugs that will do nothing for them. These are more the fault of lawyers than doctors. In our experience, doctors can be all too cool and rational in their thinking about the end of life. It’s fear of lawsuits (or, in a few cases, trolling for customers) that prevents doctors from behaving rationally when prescribing treatment for the old and terminally ill…
So what do we do about old people who, on balance, would rather get even older — whatever that means in terms of “quality of life” — than give up? This is one of the indelicate, unmentionable questions in the health-care debate…
In short, all the Republican talk during the health-care- reform debate about “death panels” was melodramatic and unfair, but not ridiculous. One way or another, holding down health-care costs will require policies that deny treatment to people who want it. And want it because it will extend their lives.
This goes on already, all the time. Health insurance companies have been known to deny payment for treatments deemed unnecessary. Age limits for organ transplants are another example. All policies that involve denying care because of “quality of life” considerations are, in effect, “death panels.” But no society can afford to give every citizen every possible therapy…
How do you persuade fellow citizens to accept limits on their right to consume health-care resources? The trick, we think, is to ask them when they’re healthy, not when they’re sick. If you think a $200,000 operation is going to give you a few more years to live, it’s going to be hard to convince you that it’s not worth the cost. But before then, when your odds of needing that expensive operation are the same as everybody else’s, you might well choose a system that offers a higher life expectancy, even though it costs less. In fact, why wouldn’t you?
Bloomberg View articles don’t always try to answer the questions they ask. This is one that sort of suggests alternatives; but, the final resolution isn’t settled yet. We’re stuck with politicians, insurance companies, healthcare corporations and their own versions of “death panels” in charge of negotiating with us.
You already know who has the most power in that dialectic – and it ain’t us.
The U.S. workplace is polarizing between the education haves and have-nots, says David Autor, professor of economics at Massachusetts Institute of Technology in Cambridge. So-called middle-skill jobs, typically well-paying work that doesn’t require extensive higher education, are vanishing, dividing the labor force into high- and low-skill positions. While women are moving up the knowledge ladder, male educational attainment is growing at a slower rate.
“It is terrific that women are getting higher levels of education,” Autor says. “The problem is that males are not.”
Men lagging behind on education raises problems for how fast the U.S. economy can grow because there aren’t enough highly skilled Americans, creating a mismatch between company demand and labor-market supply.
Bonnie Dunbar, Chicago-based Boeing Co. (BA)’s director of higher education and science, technology, engineering and math, says the U.S. doesn’t produce enough engineers to fill the needs of growing businesses like hers that also must replace retiring professionals.
“There is a shortfall now,” Dunbar says. “It is a recruitment challenge. You have these 70,000 engineers graduating every year, and you have all the companies in the U.S. competing for them…”
The article that brought me to this TED washing machine and Hans Rosling was in the NY TIMES the other day. Now, you would have to subscribe to their digital edition to read that article; so – as I did the last time the TIMES farted around with a paywall – I found a newspaper that pays even more than you or me to reprint their articles.
Read the article after you watch the video. It discusses many of the ways that Hans Rosling and his Gapminder website work very hard to make data very easy to understand.
If you’re reading my blog on an iPad, the video link up top may not work. Here’s a link directly to the video at TED.
My mantra hasn’t changed: Order wisely.
A person’s risk of stroke is associated with the number of fast-food restaurants near their residence, according to a study presented Thursday at a stroke conference in San Diego, California.
Researchers led by Dr. Lewis B. Morgenstern at the University of Michigan in Ann Arbor counted 1,247 strokes caused by blood clots in 64 census tracts in Nueces County, Texas, which includes Corpus Christi, from January 2000 through June 2003.
They also mapped the county’s 262 fast-food restaurants and then adjusted for socioeconomic status and demographics and found a statistically significant association.
“The association suggested that the risk of stroke in a neighborhood increased by 1 percent for every fast-food restaurant,” the authors wrote in a poster presented at the American Stroke Association’s International Stroke Conference….
Morgenstern, director of the University of Michigan’s stroke program and professor of neurology and epidemiology, warned that the finding does not prove that proximity to fast-food restaurants caused the increase in strokes of people living nearby.
“What we don’t know is whether fast food actually increased the risk because of its contents or whether fast-food restaurants are a marker of unhealthy neighborhoods,” he said.
So I guess the moral to the story is that we are supposed to stay away from power lines and brick-and-mortar fast food joints– just in case.