Category Archive 'Statistics'
24 Mar 2018

Actors Cold Read Statistical Facts About Guns


04 Oct 2017

A Young Statistician Looks at the Gun Control Debate

, ,

Leah Libresco Y ’11,, a statistician and former newswriter at FiveThirtyEight, a data journalism site, looks rationally at Gun Control arguments.

Before I started researching gun deaths, gun-control policy used to frustrate me. I wished the National Rifle Association would stop blocking common-sense gun-control reforms such as banning assault weapons, restricting silencers, shrinking magazine sizes and all the other measures that could make guns less deadly.

Then, my colleagues and I at FiveThirtyEight spent three months analyzing all 33,000 lives ended by guns each year in the United States, and I wound up frustrated in a whole new way. We looked at what interventions might have saved those people, and the case for the policies I’d lobbied for crumbled when I examined the evidence. The best ideas left standing were narrowly tailored interventions to protect subtypes of potential victims, not broad attempts to limit the lethality of guns. …

As my co-workers and I kept looking at the data, it seemed less and less clear that one broad gun-control restriction could make a big difference. Two-thirds of gun deaths in the United States every year are suicides. Almost no proposed restriction would make it meaningfully harder for people with guns on hand to use them. I couldn’t even answer my most desperate question: If I had a friend who had guns in his home and a history of suicide attempts, was there anything I could do that would help?

However, the next-largest set of gun deaths — 1 in 5 — were young men aged 15 to 34, killed in homicides. These men were most likely to die at the hands of other young men, often related to gang loyalties or other street violence. And the last notable group of similar deaths was the 1,700 women murdered per year, usually as the result of domestic violence. Far more people were killed in these ways than in mass-shooting incidents, but few of the popularly floated policies were tailored to serve them.

By the time we published our project, I didn’t believe in many of the interventions I’d heard politicians tout. I was still anti-gun, at least from the point of view of most gun owners, and I don’t want a gun in my home, as I think the risk outweighs the benefits. But I can’t endorse policies whose only selling point is that gun owners hate them. Policies that often seem as if they were drafted by people who have encountered guns only as a figure in a briefing book or an image on the news.

Instead, I found the most hope in more narrowly tailored interventions.


31 Mar 2017

“Fewer Than 1% of Papers Published in Today’s Scientific Journals Follow Scientific Method”

, , , , ,

Breitbart has some really bad news.

Fewer than 1 percent of papers published in scientific journals follow the scientific method, according to research by Wharton School professor and forecasting expert J. Scott Armstrong.

Professor Armstrong, who co-founded the peer-reviewed Journal of Forecasting in 1982 and the International Journal of Forecasting in 1985, made the claim in a presentation about what he considers to be “alarmism” from forecasters over man-made climate change.

“We also go through journals and rate how well they conform to the scientific method. I used to think that maybe 10 percent of papers in my field … were maybe useful. Now it looks like maybe, one tenth of one percent follow the scientific method” said Armstrong in his presentation, which can be watched in full below. “People just don’t do it.”

Armstrong defined eight criteria for compliance with the scientific method, including full disclosure of methods, data, and other reliable information, conclusions that are consistent with the evidence, valid and simple methods, and valid and reliable data.

According to Armstrong, very little of the forecasting in climate change debate adheres to these criteria. “For example, for disclosure, we were working on polar bear [population] forecasts, and we were asked to review the government’s polar bear forecast. We asked, ‘could you send us the data’ and they said ‘No’… So we had to do it without knowing what the data were.”

According to Armstrong, forecasts from the Intergovernmental Panel on Climate Change (IPCC) violate all eight criteria.

“Why is this all happening? Nobody asks them!” said Armstrong, who says that people who submit papers to journals are not required to follow the scientific method.

A must-read.

13 Jan 2017

Time to Send in the Armed Forces

, ,

30 Apr 2015

Settled Science

, , , , , ,


Hat tip to Glenn Reynolds.

17 Jul 2014

Applying Math to Myth

, , ,

Network combining the five major Icelandic sagas. White nodes represent characters who appear in more than one saga. There is a large overlap of characters from Laxdæla Saga (green) and Njáls Saga (red). The other sagas are Egil (blue), Vatnsdaela (yellow), and Gisla (light blue).

Veronique Greenwood, at the Verge, describes a fascinating application of the techniques of statistical physics to identify patterns and relationships in medieval literature.

An unusual article recently appeared in the magazine of the Royal Statistical Society and American Statistical Association.

It featured web-like diagrams of lines connecting nodes, a hallmark of research that analyzes networks. But each node, rather than being a plain dot, was the head of a burly, red-bearded Viking sporting a horned hat, his tresses blowing in the wind.

This whimsical-seeming piece of scholarship went on to describe the social network of more than 1,500 characters in the Icelandic Sagas, epic tales about the colonization of Iceland around a thousand years ago that were first written down a few hundred years after that. It was the work of a pair of statistical physicists, Ralph Kenna of University of Coventry in the UK and his graduate student Pádraig Mac Carron, now at Oxford, who are applying the tools of their trade to works of epic literature, legend, and myth.

For this particular analysis, they painstakingly recorded the relationship of every settler in 18 sagas. The resulting web of interactions helped shed light on theories humanities scholars have been discussing for years, and even picked up on some previously unnoticed patterns. Their work is part of a movement that promises a new way to approach old questions in literature, history, and archaeology, with fanciful diagrams as just the appetizer.

Demonstration of social network analysis, with red lines representing unfriendly connections and green lines representing friendly ones.

The story of how Kenna and Mac Carron got here begins with the Irish tale of the cattle-raid of Cooley, or the Táin Bó Cúailnge. That yarn tells how the warrior-queen Medb of Connacht rallies an army to steal a fine bull from Ulster, and how youthful Cúchulainn, an Ulster folk hero, stands against her. Complete with a maiden prophet with three pupils in each eye, wild chariot rides, and an enormous cast of characters, it’s a story to grip anyone’s imagination.

It’s a story that Kenna and Mac Carron, who are both Irish, have known since childhood. Several years ago, Kenna, who has a successful career as a physicist, found his thoughts returning to mythology. It wasn’t as big a departure as it might seem at first. “In statistical physics, you’re dealing with objects such as gasses that are comprised of molecules and atoms,” he says. “The system consists of many small entities, and so many of them you cannot deal with them individually, you have to deal with them statistically.” Some physicists have started to use similar methods to look at how large numbers of people interact to produce aspects of human society, and Kenna wondered whether they could be applied to myths and stories. The Táin, which comes to us in pieces from many different manuscripts, the oldest nearly 1,000 years old, is considered literature rather than historical account. But it might still encode, in a way statistics can reveal, information about the society that produced it. Math might also help classify tales in a new way, quantitatively, in addition to the usual qualitative classifications.

Hat tip to Karen L. Myers.

27 May 2014

The 97% Myth

, , , , ,


In the Wall Street Journal, Joseph Bast and Roy Spencer look at the evidence, and find that the oft-repeated claim that “97% of climate scientists” subscribe to a belief in Catastrophist Anthropogenic Warmism is just as empty a claim as the newspaper headlines about melting glacier and Polar icecaps.

Last week Secretary of State John Kerry warned graduating students at Boston College of the “crippling consequences” of climate change. “Ninety-seven percent of the world’s scientists,” he added, “tell us this is urgent.”

Where did Mr. Kerry get the 97% figure? Perhaps from his boss, President Obama, who tweeted on May 16 that “Ninety-seven percent of scientists agree: #climate change is real, man-made and dangerous.” Or maybe from NASA, which posted (in more measured language) on its website, “Ninety-seven percent of climate scientists agree that climate-warming trends over the past century are very likely due to human activities.”

Yet the assertion that 97% of scientists believe that climate change is a man-made, urgent problem is a fiction. The so-called consensus comes from a handful of surveys and abstract-counting exercises that have been contradicted by more reliable research.

One frequently cited source for the consensus is a 2004 opinion essay published in Science magazine by Naomi Oreskes, a science historian now at Harvard. She claimed to have examined abstracts of 928 articles published in scientific journals between 1993 and 2003, and found that 75% supported the view that human activities are responsible for most of the observed warming over the previous 50 years while none directly dissented.

Ms. Oreskes’s definition of consensus covered “man-made” but left out “dangerous”—and scores of articles by prominent scientists such as Richard Lindzen, John Christy, Sherwood Idso and Patrick Michaels, who question the consensus, were excluded. The methodology is also flawed. A study published earlier this year in Nature noted that abstracts of academic papers often contain claims that aren’t substantiated in the papers.

Read the whole thing.

14 May 2014

Spurious Correlations

, , ,

Divorce rate in Maine
correlates with
Per capita consumption of margarine (US)


Correlation: 0.992558

Amusing web-site mocks statistical evidence by posting a daily graph and quantitative data demonstrating a meaningless correlation between two totally unconnected collections of events.

Hat tip to Scott Drum.

24 Mar 2014

“Lies, Damned Lies, and Statistics”

, , ,

Judith Levy, editor of Ricochet, went through 175 responses to The Edge’s 2014 inquiry: What scientific idea is ready for retirement?, and selected a few responses offering very likely the best candidate: statistics.

Emanuel Derman, professor of financial engineering at Columbia, wrote that the power of statistics is an idea worth retiring:

    …nowadays the world, and especially the world of the social sciences, is increasingly in love with statistics and data science as a source of knowledge and truth itself. Some people have even claimed that computer-aided statistical analysis of patterns will replace our traditional methods of discovering the truth, not only in the social sciences and medicine, but in the natural sciences too.

    … Statistics—the field itself—is a kind of Caliban, sired somewhere on an island in the region between mathematics and the natural sciences. It is neither purely a language nor purely a science of the natural world, but rather a collection of techniques to be applied, I believe, to test hypotheses. Statistics in isolation can seek only to find past tendencies and correlations, and assume that they will persist. But in a famous unattributed phrase, correlation is not causation.

    Science is a battle to find causes and explanations amidst the confusion of data. Let us not get too enamored of data science, whose great triumphs so far are mainly in advertising and persuasion. Data alone has no voice. There is no “raw” data, as Kepler’s saga shows. Choosing what data to collect and how to think about it takes insight into the invisible; making good sense of the data collected requires the classic conservative methods: intuition, modeling, theorizing, and then, finally, statistics.

Science journalist Charles Seife wrote that “statistical significance” is almost invariably misused, to the point that it has become

    a boon for the mediocre and for the credulous, for the dishonest and for the merely incompetent. It turns a meaningless result into something publishable, transforms a waste of time and effort into the raw fuel of scientific careers. It was designed to help researchers distinguish a real effect from a statistical fluke, but it has become a quantitative justification for dressing nonsense up in the mantle of respectability. And it’s the single biggest reason that most of the scientific and medical literature isn’t worth the paper it’s written on.
08 Jan 2014

Taking the Wider View…

, ,

26 Jan 2013

David Mamet Debunks Gun Control

, , , ,

According to US Dept of Health and Human Services
There are roughly 700,000 employed physicians in the U.S
There are roughly 120,000 accidental deaths caused by physician per year
That means there are roughly 0.171 accidental deaths per physician per year

According to the FBI
There are roughly 80, 000, 000 gun owners in the U.S
There are roughly 30,000 gun-related deaths (accidental/non-accidental) per year
That means there are roughly 0.000375 deaths per gun owner per year

David Mamet
takes on Gun Control in Newsweek no less:

The Left loves a phantom statistic that a firearm in the hands of a citizen is X times more likely to cause accidental damage than to be used in the prevention of crime, but what is there about criminals that ensures that their gun use is accident-free? If, indeed, a firearm were more dangerous to its possessors than to potential aggressors, would it not make sense for the government to arm all criminals, and let them accidentally shoot themselves?

Read the whole thing.

28 Dec 2012

Look at Britain to See Where Empirical Solutions to Violence Finally Lead

, , , , , , , , , ,

One of my Yale classmates yesterday forwarded this New York Times editorial denouncing the National Rifle Association’s efforts to prevent sophistors, economists, calculators, and “leading experts” on violence from artfully collecting data and massaging statistics in order to produce a scientific, apparently empirical case favoring gun control.

Why would the naughty NRA oppose data collection and scientific research by well-credentialed experts?

The NRA sensibly opposes these so-called empirical studies because it knows that when you get to establish the principles used for collecting data and the methodologies employed in arranging the assembled information and evaluating the results, you possess the ability to prove any case you want to prove, empirically. The NRA knows that figures lie and liars figure, and that there are lies, damned lies, and statistics.

Where does such empiricism lead? Just look at Britain where conventional pocket knives are banned as “offensive weapons” and “leading experts” have been calling in recent years for a ban on pointed kitchen knives.

[Accident & Emergency] doctors are calling for a ban on long pointed kitchen knives to reduce deaths from stabbing.

A team from West Middlesex University Hospital said violent crime is on the increase – and kitchen knives are used in as many as half of all stabbings.

They argued many assaults are committed impulsively, prompted by alcohol and drugs, and a kitchen knife often makes an all too available weapon.

The research is published in the British Medical Journal.

The researchers said there was no reason for long pointed knives to be publicly available at all.

They consulted 10 top chefs from around the UK, and found such knives have little practical value in the kitchen.

None of the chefs felt such knives were essential, since the point of a short blade was just as useful when a sharp end was needed.

The researchers said a short pointed knife may cause a substantial superficial wound if used in an assault – but is unlikely to penetrate to inner organs.


They won’t stop with taking away our guns. As the example of Britain shows, they will go to the most absurd lengths in criminalizing innocent and harmless possession of marginal examples of weapons in their fanatical pursuit of the elimination of every kind of risk and hazard by the calculative power of human reason operating through the coercive agency of the state.

A disabled caravanner who kept a penknife in his glove compartment to use on picnics has blasted the authorities after being dragged through court for possessing an offensive weapon.

Rodney Knowles, 61, walks with the aid of a stick and had used the Swiss Army knife to cut up fruit on picnics with his wife.

Knowles yesterday admitted possessing an offensive weapon at Torquay Magistrates Court. He was given a conditional discharge.

But speaking after the hearing, he said: ‘It’s a stupid law. Now I have a criminal record.’

05 Apr 2012

Historians Raise Estimate of Civil War Losses

, ,

Major Innes Randolph’s defiant “I’m a Good Old Rebel” song (1914) boasted of Northern casualties inflicted and expressed regret that Southern resistance had not piled up an even larger score.

I followed old Mars’ Robert
For four year, near about,
Got wounded in three places
And starved at Pint Lookout;

I cotched the rheumatism
A campin’ in the snow,
I killed a chance of Yankees,
I’d like to kill some mo’.

Three hundred thousand Yankees
Is stiff in Southern dust;
We got three hundred thousand
Before they conquered us;

They died of Southern fever
And Southern steel and shot,
I wish we got three million
Instead of what we got.

A new examination of Civil War enumerated losses, reported in the New York Times, contends that Major Randolph came closer to his expressed goal than was previously thought.

For 110 years, the numbers stood as gospel: 618,222 men died in the Civil War, 360,222 from the North and 258,000 from the South — by far the greatest toll of any war in American history.

But new research shows that the numbers were far too low.

By combing through newly digitized census data from the 19th century, J. David Hacker, a demographic historian from Binghamton University in New York, has recalculated the death toll and increased it by more than 20 percent — to 750,000.

The new figure is already winning acceptance from scholars.

Read the whole thing.

12 May 2011

$70 Fill Ups and Low Inflation Rates

, , ,

Joe Queenan does a fine job of mocking the federal government’s “core inflation rate” calculation methodology.

[I]magine my surprise when the latest economic data came out and we were told that inflation wasn’t much of a problem at all. The price index for core personal consumption expenditures increased a piddling 0.9% from the previous year, keeping the national inflation rate far, far below what economists see as the danger level.

Hang on a second, I thought: What about my exorbitant fuel costs and the two bucks for my disgusting coffee and the $1.25 for my stale, tasteless bagel, with no schmear, no butter, no nothing? If inflation had jumped just a puny 0.9% in the past 12 months, why did it feel like everything that I bought last week had gone up 25%?

The answer lies in the way economists calculate what they call “core” price indexes. The core personal consumption expenditures index (PCE), for example, computes the cost of a representative basket of goods that consumers might buy—like used copies of “Madden 2009” and lace camisoles and jumbo-size containers of Percocet and personally autographed Kenny Chesney guitar picks and Blu-ray discs of “AVP: Alien vs. Predator” —but it cuts out variables like food and energy prices. This makes the month-to-month reporting on inflation less volatile, far less subject to the vicissitudes of the market.

At first glance, this seems baffling. Removing fuel and food costs from the index purely for the sake of statistical balance seems a bit like saying, “All told, four million people died in World War II. Well, unless you include the people who died in concentration camps. And, oh yeah, the 20 million Russians.” It’s a bit like saying, “On average, a major league baseball team will win 3.2 World Series each century. Obviously, not the Cubs. And we’ve thrown out the New York Yankees and their 27 world championships because it doesn’t provide a true snapshot of the game at any given moment.” It’s a bit like saying, “Billy Joel never wrote a single song that just totally sucks and makes people’s skin crawl. Unless you include ‘Captain Jack.’ Which we deliberately left out of our sample because it skews the results. Maybe we should have left out ‘Piano Man,’ too.”

Read the whole thing.

Your are browsing
the Archives of Never Yet Melted in the 'Statistics' Category.

Entries (RSS)
Comments (RSS)
Feed Shark