Quotulatiousness

October 29, 2011

More on Malthus

Filed under: Books, Economics, History, Media — Tags: , , , — Nicholas @ 10:57

Tim Harford poses and answers some common questions about the much-talked-about 7-billionth birth:

There will be 7bn of us come Halloween? You’re kidding.

Someone at the UNPFA has a sense of humour, it seems. This is a terrifying prospect to some and cheery for others, while most of us find it irrelevant. Halloween seems appropriate.

This is a statistical projection, and statistical projections don’t have a sense of humour.

But they do have margins of error. The UNPFA doesn’t even know whether the seven billionth person will be born in 2011. Even the UK is currently relying on 10-year old census data. There are places in the world where the data are decades old and we’re just guessing at the population. Still, such celebrations — if they are celebrations — do pass the time.

[. . .]

So Malthus was wrong?

Even Robert Malthus realised that there was such a thing as birth control. His more excitable successors, such as Paul Ehrlich, author in 1968 of The Population Bomb, have been fairly thoroughly rebutted by subsequent events. Dan Gardner, author of the fascinating Future Babble, summarises Ehrlich’s three scenarios for the 1980s as “everybody dies” (starvation-triggered nuclear war), “every third human dies” (starvation-triggered virus) and in the optimistic scenario “a billion people still die of starvation”.

October 26, 2011

Mis-perception of relative risks

Filed under: Football, Health, Randomness — Tags: , , , — Nicholas @ 00:03

Gregg Easterbrook provides a good example of how difficult people often find to discern the relative weight of risks:

The first consideration is that both absolute numbers of football deaths and rates of death compared to participants are in long-term decline — mirroring the decline in many forms of risk in society. Age-adjusted rates of all deaths in the United States have declined for 10 consecutive years. Auto fatalities have been declining for more than a generation. Winning the War on War, an important new book by Joshua Goldstein [. . .] shows that despite the impression created by cable news, exposure to violence is in decline both in the United States and worldwide.

[. . .]

Data from the National Center for Catastrophic Sport Injury Research reflects a steady decline in deaths caused by football. Table 1 of the center’s most recent report shows that in the past decade, 34 high school, three pro and two college football players have died as the direct result of games or practices, with the primary cause of deaths being heat stroke. That is entirely awful — but much lower than the rate of a generation ago. In 1968 alone, 26 high school players died as a direct result of football; last year, the number was two. Table 3 of the report shows the direct fatality rate from high school football peaked at 2.6 deaths per 100,000 players in 1969 and declined steadily to 0.13 deaths per 100,000 in 2010. That means a 1968 high school football player was 20 times more likely to die than a 2010 player. (The main reason for declining deaths was that football helmets were improved to eliminate skull fractures.)

[. . .]

How to compare the slight risk of a terrible football outcome to other common risks experienced by the young? Consider the risk of being in a car. About 3,000 teens die each year in car crashes. There are about 21.3 million Americans between 15 and 19 years of age. Teens average about 146 miles driven per week, roughly 150 hours per year of driving. These figures yield a roughly one in 1 million chance that a teen will die in an hour of driving. The National Federation of State High School Associations reports that 1.1 million boys (and a few girls) played high school football last academic year. A typical high school football season would include, in games and practice, perhaps 75 hours of exposure to contact. That’s about 80 million total hours of exposure to contact on the part of high school football players. The National Center for Catastrophic Sport Injury Research reports a recent average of three deaths per year directly caused by high school football. That’s a roughly one in 27 million chance of a high school player dying from an hour of football contact.

These are all rough estimates. Taking them together, a teenager has a one in 1 million chance of dying in an hour behind the wheel, compared to a one in 27 million chance of dying in an hour of football contact. Being in pads on a football field is less deadly than driving to high school for class. Many contemporary parents, especially moms, might say, “I don’t want you playing football because it’s so dangerous, but it’s fine for you to drive to the mall.” As regards mortality, this misperceives the risks.

October 5, 2011

The irony of Bletchley Park’s funding windfall

Filed under: Britain, History, Technology, WW2 — Tags: , , — Nicholas @ 10:47

Cory Doctorow has the good news about Bletchley Park’s recent grant:

Bletchley Park, the birthplace of modern crypto and the home of the WWII codebreaking effort, has received a £4.6m Heritage Lottery Fund grant to fund restoration efforts and new exhibits. Bletchley was broken up after the war and its work was literally buried as part of the Cold War climate of secrecy that prevailed. In the years that followed, neglect and time led to the near-destruction of many of the historic sites. The Bletchley Park trust has since done amazing work on a shoestring budget to restore and preserve Bletchley, creating a fabulous museum and rebuilding some of the most beautiful electromechanical computers I’ve ever seen.

[. . .]

Ironically, the money to restore Bletchley has come from the lottery, a government-run system designed to reinforce and exploit statistical innumeracy of the sort that Bletchley’s cryptographers overcame in order to help win the war.

August 8, 2011

ESPN’s new attempt at a more accurate Quarterback rating system

Filed under: Football — Tags: , , — Nicholas @ 17:25

The existing quarterback ranking is hard to understand and concentrates on the “passing” side of the quarterback’s job. ESPN is introducing a more broad-based ranking system:

The Total Quarterback Rating is a statistical measure that incorporates the contexts and details of throws and what they mean for wins. It’s built from the team level down to the quarterback, where we understand first what each play means to the team, then give credit to the quarterback for what happened on a play based on what he contributed.

[. . .]

Total QBR Basics

A quick primer on the fundamentals of Total Quarterback Rating:

Scoring: 0-100, from low to high. An average QB would be at 50.
Win Probability: All QB plays are scored based on how much they contribute to a win. By determining expected point totals for almost any situation, Total QBR is able to apply points to a quarterback based on every type of play he would be involved in.
Dividing Credit: Total QBR factors in such things as overthrows, underthrows, yards after the catch and more to accurately determine how much a QB contributes to each play.
Clutch Index: How critical a certain play is based on when it happens in a game is factored into the score.

Under the new ranking, Brett Favre’s performance gets a lot less impressive (if an average QB would score 50 points):

  • 2008 – New York Jets – 41.7
  • 2009 – Minnesota Vikings – 63.1
  • 2010 – Minnesota Vikings – 25.8

June 30, 2011

Does exposure to porn increase the incidence of rape?

Filed under: Law, Media — Tags: , , , — Nicholas @ 14:54

In brief, it appears not:

But while theorising is all very well, it is necessary occasionally to fine-tune such theories by looking at the empirical evidence. And the most obvious fact about porn and rape is that reported rape incidence — at least in the United States, where a National Crime Victimization Survey takes place every year — has been falling in recent decades as porn becomes ever more available.

[. . .]

Now yes, it is absolutely true that correlation and causation are not the same thing. But at first glance we’d have a hard time claiming that the greater availability of porn led to more rapes: simply because there are fewer rapes reported while there’s definitely more porn.

[. . .]

In D’Amato’s paper, he uses Freakonomics-style statistics (one of his colleagues wrote the Freakonomics abortion and crime paper with Levitt) to try to tease out evidence of something more than just correlation.

What he found is that the lower the internet penetration in 2004 in a US state, the higher the rape rate had risen and that the higher the internet penetration, the lower rate had fallen.

We expect, for those societal reasons, that the reported rape rate will have risen over the time period. And where there’s no or limited internet access, it has. Where there is high internet access it has fallen, the fall being greater than the general societal rise.

Thus we have an empirical connection between internet access and lower rape figures. Whether it’s porn or not is a different matter: they could all be playing Second Life instead. An unlikely way to bet though really.

May 24, 2011

“Why does dubious social science keep showing up in medical journals?”

Filed under: Economics, Media, Science — Tags: , , , , — Nicholas @ 10:08

William Easterly and Laura Freschi have determined the decision tree for publishing crappy social science research:

Aid Watch has complained before about shaky social science analysis or shaky numbers published in medical journals, which were then featured in major news stories. We questioned creative data on stillbirths, a study on health aid, and another on maternal mortality.

Just this week, yet another medical journal article got headlines for giving us the number of women raped in the DR Congo (standard headline: a rape a minute). The study applied country-wide a 2007 estimate of the rate of sexual violence in a small sample (of unknown and undiscussed bias). It did this using female population by province and age-cohort — in a country whose last census was in 1984.

We are starting to wonder, why does dubious social science keep showing up in medical journals?

The medical journals may not have as much capacity to catch flaws in social science as in medicine. They may desire to advocate for more action on tragic social problems. The news media understably assume the medical journals ARE vetting the research.

H/T to Tim Harford for the link.

April 25, 2011

Majority in reach for Harper, if Ontario numbers hold up

Filed under: Cancon, Politics — Tags: , , , — Nicholas @ 11:17

The latest Nanos/Globe & Mail poll shows that the Conservatives might just be able to reach majority status if the Ontario numbers stay steady for the final week:

Nationally, the NDP is statistically tied for second place with the Liberals. But another story is emerging out of Ontario, where they are running third; the party’s surge in Quebec and other regions has not given it a similar bump in Ontario.

Pollster Nik Nanos sees this as a boon for the Tories — one that could well provide the Conservatives a route to that coveted majority.

“Talk about Jack Layton in Stornoway has actually helped the Conservatives in Ontario,” Mr. Nanos said Monday. “The Conservatives best chance to win a majority is in Ontario. If their numbers hold or start ramping up in Ontario that could be good news for the Conservatives. One of the scenarios that we could be looking at now is a squeaker of a majority government.”

Of course, the regional numbers are subject to a larger margin of error:

There is a margin of error of plus or minus 64 percentage points, 19 times out of 20, for the provincial sample.

I hope there’s a decimal place somewhere in that MoE.

April 18, 2011

The Magic Washing Machine, by Hans Rosling

Filed under: Economics, Environment, Health, Technology — Tags: , , , — Nicholas @ 09:49

H/T to Jon for the link.

February 24, 2011

They’re called “factoids”, not “facts”

Filed under: Bureaucracy, Education, Government, USA — Tags: , , , — Nicholas @ 07:46

There’s a factoid in common circulation at the moment that, measured by SAT scores, the states that ban collective bargaining for teachers rank almost dead last, while Wisconsin ranks 2nd. Neal McCluskey explains that this is not particularly true:

Now, aside from the factoid, if true, providing no real insight into whether collective bargaining is good or bad for education — there are myriad variables at work other than collective bargaining, none of which does this control for — but the factoid itself is highly dubious. Again, it is hard to find the original source for this, but I looked up 2009 ACT and SAT state rankings, and at the very least it seems highly unlikely that Virginia ranks 44th out of all states. According to the ACT ranking, for instance, Virginia places 22nd, and on the SAT (assuming the linked to list is accurate — I’m doing this fast), it ranked 33rd. It’s hard to see how those would be combined for a 44th place overall finish.

How about the Wisconsin second place-finish? Well, that is accurate for the SAT, but notably only 5 percent of Wisconsin students took the SAT — a negligible rate. On the ACT, which is the main test taken in the Badger State, Wisconsin finished 13th — not bad, but hardly great.

So what does this tell you? Not that collective bargaining is educationally good or bad — like I said, you just can’t get there from here — but that you have to be very careful about your sources of information. Unfortunately, that seems especially true when you’re dealing with education.

January 23, 2011

Lawrence Solomon on the coming crash in China

Filed under: China, Economics, Government — Tags: , , — Nicholas @ 12:17

If you think I’ve been too chipper and dismissive on the medium-to-long term issues that could cause a Chinese meltdown, you’ll enjoy Lawrence Solomon’s article:

In China, the resentments are palpable. Many of the 300 million people who have risen out of poverty flaunt their new wealth, often egregiously so. This is especially so with the new class of rich, all but non-existent just a few years ago, which now includes some 500,000 millionaires and 200 billionaires. Worse, the gap between rich and poor has been increasing. Ominously, the bottom billion views as illegitimate the wealth of the top 300 million.

How did so many become so rich so quickly? For the most part, through corruption. Twenty years ago, the Communist Party decided that “getting rich is glorious,” giving the green light to lawless capitalism. The rulers in China started by awarding themselves and their families the lion’s share of the state’s resources in the guise of privatization, and by selling licences and other access to the economy to cronies in exchange for bribes. The system of corruption, and the public acceptance of corruption, is now pervasive — even minor officials in government backwaters are now able to enrich themselves handsomely.

[. . .]

The corruption extends to the enforcement of regulatory standards for health and safety, which few in China trust. In recent years China has endured a tainted milk scandal and a tainted blood scandal, each of which implicated corrupt officials in widespread death and debilitation. In a devastating 2008 earthquake, some 90,000 perished, one-third of them children buried alive in 7,000 shoddily built “tofu schools” that skimped on materials. Nearby buildings for the elites that met building standards, including a school for the children of the rich, were largely unscathed.

[. . .]

China is a powder keg that could explode at any moment. And if it does explode, chaos could ensue — as the Chinese are only too well aware, the country has a brutal history of carnage at the hands of unruly mobs. For this reason, corrupt officials inside China, likely by the tens of thousands, have made contingency plans, obtaining foreign passports, buying second homes abroad, establishing their families and businesses abroad, or otherwise planning their escapes. Also for this reason, much of the middle class supports the government’s increasingly repressive efforts.

Compared to my rather milder criticisms, this is strong stuff indeed.

H/T to my former virtual landlord for the link, who referred to this as my “hobby horse in full gallop”.

January 21, 2011

Remaking Red Dawn as a metaphor for US fear of China

Filed under: China, Economics, Media, USA — Tags: , , , , — Nicholas @ 12:59

David Harsanyi notes the remake of the 1980’s movie Red Dawn with the Chinese taking the place of the original film’s Soviet and Cuban troops:

Doubtlessly, the remake will be entertaining and offer a far more plausible plot line than the original — seeing that the Chinese, well, they have a proper army. Producers will almost certainly capitalize on a growing alarmism regarding China’s growth. Few issues, in fact, can bring right and left together in this polarized world of ours than a shared knowledge that China is bad news.

Now, the American populace can typically be divided into two categories: 1. Those who don’t care one whit about foreign policy. 2. Newspaper editors.

So before Chinese President Hu Jintao was here meeting with the president, Andrew Kohut of the Pew Research Center took to the pages of The Wall Street Journal and explained what we think about the topic.

Apparently, 47 percent of those he surveyed cited China as the world’s top economic power. (Only 31 percent properly identified it as the U.S., which has an economy nearly three times the size.) Another Pew survey from last year found that 47 percent of us consider China’s growth a “bad thing” for the United States. A new CNN poll found that 58 percent of us believe that China’s “wealth and economic power” are a threat to the U.S.

I’m certain our relationship with China is layered with international complexity and fraught with danger. But why would we fear the aspects of China’s ascendancy — its “wealth and economic power” — that pose the least threat to United States? Unlike ideological clashes, economic competition can be mutually beneficial. A country with real economic wealth is typically free and doesn’t look kindly on radical behavior. Suicide bombers rarely drive top-of-the-line BMWs.

I have a long history of doubting the stated size and growth of the Chinese economy and therefore feeling that the “threat” they pose is overstated. Overall, the economic growth in China is a good thing, both for China and for the world economy, but there’s still too much malignancy from the “bad old days” of the command economy that haven’t been properly dealt with. China is big, and getting bigger, but will face severe problems the longer these historical artifacts remain unexamined and unresolved.

January 17, 2011

Another reason to view self-reported study data with caution

Filed under: Britain, Science — Tags: , , , — Nicholas @ 09:30

There’s a reason that studies that depend on direct observation/measurement often differ in their results from studies that depend on self-reporting by the group being studied — because people lie:

Many mothers are under so much pressure to appear like perfect parents that they cover up how much television their children watch or what they cook their families, according to a survey.

Such “white lies” also extend to how much “quality time” mothers spend with their partner, website Netmums said its survey of 5,000 people suggested.

The parenting site said mothers often made each other feel “inadequate”.

[. . .]

Almost two-thirds of those surveyed said they had been less than honest with other mothers about how well they were coping and almost half covered up financial worries.

Almost a quarter of mothers admitted to downplaying how much television their children actually watched — and one in five “span a yarn” over how long they played with their children.

January 3, 2011

Healthy skepticism about study results

Filed under: Bureaucracy, Media, Science — Tags: , , , , — Nicholas @ 13:30

John Allen Paulos provides some useful mental tools to use when presented with unlikely published findings from various studies:

Ioannidis examined the evidence in 45 well-publicized health studies from major journals appearing between 1990 and 2003. His conclusion: the results of more than one third of these studies were flatly contradicted or significantly weakened by later work.

The same general idea is discussed in “The Truth Wears Off,” an article by Jonah Lehrer that appeared last month in the New Yorker magazine. Lehrer termed the phenomenon the “decline effect,” by which he meant the tendency for replication of scientific results to fail — that is, for the evidence supporting scientific results to seemingly weaken over time, disappear altogether, or even suggest opposite conclusions.

[. . .]

One reason for some of the instances of the decline effect is provided by regression to the mean, the tendency for an extreme value of a random quantity dependent on many variables to be followed by a value closer to the average or mean.

[. . .]

This phenomenon leads to nonsense when people attribute the regression to the mean as the result of something real, rather than to the natural behavior of any randomly varying quantity.

[. . .]

In some instances, another factor contributing to the decline effect is sample size. It’s become common knowledge that polls that survey large groups of people have a smaller margin of error than those that canvass a small number. Not just a poll, but any experiment or measurement that examines a large number of test subjects will have a smaller margin of error than one having fewer subjects.

Not surprisingly, results of experiments and studies with small samples often appear in the literature, and these results frequently suggest that the observed effects are quite large — at one end or the other of the large margin of error. When researchers attempt to demonstrate the effect on a larger sample of subjects, the margin of error is smaller and so the effect size seems to shrink or decline.

[. . .]

Publication bias is, no doubt, also part of the reason for the decline effect. That is to say that seemingly significant experimental results will be published much more readily than those that suggest no experimental effect or only a small one. People, including journal editors, naturally prefer papers announcing or at least suggesting a dramatic breakthrough to those saying, in effect, “Ehh, nothing much here.”

The availability error, the tendency to be unduly influenced by results that, for one reason or another, are more psychologically available to us, is another factor. Results that are especially striking or counterintuitive or consistent with experimenters’ pet theories also more likely will result in publication.

December 30, 2010

Cartographic explanation for the order of secession

Filed under: History, USA — Tags: , , , — Nicholas @ 00:20

A fascinating NYT post looks at one of the most influential maps of the US Civil War period:

The 1860 Census was the last time the federal government took a count of the South’s vast slave population. Several months later, the United States Coast Survey — arguably the most important scientific agency in the nation at the time — issued two maps of slavery that drew on the Census data, the first of Virginia and the second of Southern states as a whole. Though many Americans knew that dependence on slave labor varied throughout the South, these maps uniquely captured the complexity of the institution and struck a chord with a public hungry for information about the rebellion.

The map uses what was then a new technique in statistical cartography: Each county not only displays its slave population numerically, but is shaded (the darker the shading, the higher the number of slaves) to visualize the concentration of slavery across the region. The counties along the Mississippi River and in coastal South Carolina are almost black, while Kentucky and the Appalachians are nearly white.

H/T to Walter Olson for the link.

December 20, 2010

Once again, correlation is not causation

Filed under: Britain, Media, Science — Tags: , , — Nicholas @ 12:50

An excellent example of what statistical analysis can and cannot show:

Do mobile phone towers make people more likely to procreate? Could it be possible that mobile phone radiation somehow aids fertilisation, or maybe there’s just something romantic about a mobile phone transmitter mast protruding from the landscape?

These questions are our natural response to learning that variation in the number of mobile phone masts across the country exactly matches variation in the number of live births. For every extra mobile phone mast in an area, there are 17.6 more babies born above the national average.

This was discovered by taking the publicly available data on the number of mobile phone masts in each county across the United Kingdom and then matching it against the live birth data for the same counties. When a regression line is calculated it has a “correlation coefficient” (a measure of how good the match is) of 98.1 out of 100. To be “statistically significant” a pattern in a dataset needs to be less than 5% likely to be found in random data (known as a “p-value”), and the masts-births correlation only has a 0.00003% probability of occurring by chance.

Part of the problem is that our brains have evolved to detect patterns and relationships — even when they’re not really there:

Mobile phone masts, however, have absolutely no bearing on the number of births. There is no causal link between the masts and the births despite the strong correlation. Both the number of mobile phone transmitters and the number of live births are linked to a third, independent factor: the local population size. As the population of an area goes up, so do both the number of mobile phone users and the number people giving birth.

The problem is that our first instinct is to assume that a correlation means that one factor is causing the other. While this does not cause a problem when using pattern-spotting as an evolved survival tool, it does cause severe problems when assessing possible health scares based on a recently uncovered correlation. For the majority of cases, correlation does not indicate the presence of causality.

H/T to Maggie Koerth-Baker for the link.

« Newer PostsOlder Posts »

Powered by WordPress