# blueollie

## Statistical stupidity from NPR

I am no longer surprised when NPR commits a statistical howler.

Today, they aired a touching story about a black hockey player and the racism that he endured. So far, so good.

But then, they go on to say this:

Despite stars like P.K. Subban and Evander Kane, hockey remains a stubbornly white sport. Only about five percent of NHL players are black 28 years after James.

Uh, exactly why is this a problem?

So making the assumption that one would expect zero black players from other than the US or Canada (think of the hockey powers of this world), IF the representation were exactly proportional, we’d expect:

$(.5)(2.9) + (.25)(12.6) = 4.6$ percent, which is about what they have.

So why is 5 percent a problem? My guess: they assume that blacks are grossly over represented in football and basketball, they should be in hockey as well? If so, why?

Of course, this isn’t as bad as some idiot academic administrator with a Ph. D. insisting that everyone needs to be above the department average, but …well…let’s just say that I am cranky and that NPR comes across as smug.

February 27, 2015

## You don’t see this much: Bible fable called out as “fable”

On Rewrite: Lawrence O’Donnell calls out the State of Kentucky for funding religion (by funding the Noah’s Ark Park) but also points out that this story is merely folklore; a fable if you will. You don’t see that done very much in the mainstream media, at least not on mainstream television. Note: his Rewrite segment is NOT hostile to Christianity or Judaism, at least in the way that most educated Jews and Christians practice it.

August 5, 2014

## The National Review “disses” Differential Equations

[…]One part insecure hipsterism, one part unwarranted condescension, the two defining characteristics of self-professed nerds are (a) the belief that one can discover all of the secrets of human experience through differential equations and (b) the unlovely tendency to presume themselves to be smarter than everybody else in the world. Prominent examples include […]

(emphasis mine).

Oh noes! I love differential equations! 🙂

Yeah, I am just having fun with the quote; what really sticks in the craw of people like this is that many of us reject the idea that humans are the focal point of some deity and claim that “supernatural” explanations are really no explanation at all. 🙂

Keep in mind that the National Review is supposed to be their “intellectual” magazine; in fact, it probably ranks alongside Salon.

July 30, 2014

## The Nation: lazy journalism

There was a time when I subscribed to The Nation. But I grew tired of its lazy journalism; many of the articles were just opinions with an anecdote here or there to back them up.

I talked about one of their articles already; I am now going to follow up. This is the “Mothers who put their kids at risk is OUR failure” article:

You’ve probably heard the name Shanesha Taylor at this point. She’s the Arizona mother who was arrested for leaving her children in the car while she went to a job interview. Her story went viral thanks likely to a truly heart-wrenching, tear-stained mugshot. Taylor, who was homeless, says her babysitter flaked on her and she didn’t know what else to do while she went to a job interview for a position that would have significantly improved her family’s financial situation. […]

Whose fault is it that these children were put in these situations to begin with? These weren’t mothers doing drugs or other dangerous activities and neglecting their children; they were both mothers trying to hold down jobs to provide for their children while stuck swirling in a Catch-22. Can’t work or interview without childcare, but can’t afford childcare without a job that pays enough to cover the ever-increasing cost. Taylor and Harrell are both holding up their end of the deal: don’t rely on public assistance, go out and get work to provide for your children. Our country has reneged on its end of that deal: we’ll help you pay for someone to watch your children if you go to work.

Emphasis mine. One could argue: “where is the father?” or other things (e. g., I feel that one should be in a reasonable position to provide for one’s kids prior to having them; of course sometimes bad things happen and even a reasonable parent can’t anticipate every bad turn of life) but that isn’t the point here.

The point is what I emphasized: the “no drugs”.

PHOENIX – Prosecutors and a Phoenix woman reached a deal that would allow her to avoid prosecution for leaving her two young sons alone in a hot car while she was at a job interview.

Shanesha Taylor, who faced being tried on two felony child abuse charges, said gratitude was the only thing she felt after the agreement was reached Friday.

“I’m grateful for the offer that was extended to me and the opportunity to resolve this situation as well as to show my intentions,” said Taylor, who shed a few tears while standing outside the courthouse.

Maricopa County Attorney Bill Montgomery said his office and the 35-year-old mother of three have an agreement under which he’ll dismiss the charges against her if she meets several conditions.

Those include completing parenting and substance abuse treatment programs and establishing education and child care trust funds for her children.

CBS affiliate KPHO reports Montgomery stressed the case will only go away if all the conditions are met. “We have not dropped the charges at all,” he said. “If you don’t complete everything, if you don’t abide by the terms and conditions of that agreement, then the prosecution picks back up.”

Emphasis mine. Note the “substance abuse treatment programs”. I suppose that this could have meant, say, alcohol but if one is poor…well, never mind.

It appears that The Nation didn’t do its homework. Yeah, it did say “dangerous drugs” but her actions were “dangerous” to the kids, no?

Now we come to the NFL: The Nation comments on the “violence against women” problem that the NFL has:

The NFL, as many have been writing for too many years, has a violence-against-women problem. The incidents are too many to catalogue.

If you are looking for actual evidence, aside from a collection of incidents, you won’t find it there.

To see if the NFL really does have a problem, you’d need to compare NFL players with men of the same age and socio-economic background. You can see one study (Duke University) here and a less rigorous, but more public friendly study here.

Note: this study only compares the NFL to adult men; you should really correct for age and socio-economic background:

I don’t think that The Nation is as bad as, say, Newsmax. I get the impression that Newsmax deliberately misleads (example here) where The Nation is a bit “activist like”; it has good intentions but is incompetent. I won’t even mention The Nation once carrying climate change denial columns.

It might be best to think of it as a Salon which as been around longer.

July 24, 2014

## Nate Silver’s new website: growing pains….

Nate Silver’s new website 538.com has come under fire a bit.

First, let me tell you what I think the site does well: it made an early midterm election prediction which is grim for the Democrats. I am sad to say that I think it is an accurate prediction (well thought out, well analyzed). I have heard that there has been some criticism, but this sounds suspiciously like the type of “wishful thinking” we saw from Republicans in 2012. It honestly looks grim for us.

Where the criticism is

538 has a stated goal of doing “data driven journalism”. There are some problems inherent in this task.

1. Data takes a long time to gather and to properly analyze.
2. When one is talking about a highly technical area such as economics or science, having expertise in such fields is ESSENTIAL (non-negotiable) to using such data properly.
3. When you have claimed to make a data driven argument in a technical area, those who know what they are talking about will fact check you and find every possible hole in your argument.
4. If your goal is to provide a simplified presentation to the reader who doesn’t regularly read the specialized economics and science journals, you’ll end up making some simplifications and omissions and you’ll likely be taken to task for that.

However, I think that there is a place for what 538 is trying to do: it isn’t to compete with the experts (it can’t do that) or even with the science/technical magazines (it can’t do that either). But what it can do is to make the public aware of the general issues that the professionals ARE dealing with along with the data and perhaps whet the appetite for more. But it can’t compete with, say, Scientific American or the economics magazines.

For now, 538 is facing growing pains. Here is one response to the first attempts: it is brutal but raises fair points.

Here is a 538 article on the question: “has climate change contributed to the increased cost of the recent natural disasters”. I thought that the article was fine, as “food for thought.” But as to a definitive conclusion: no.l

Basically, the 538 article said that the growing expense of damage from things like hurricanes came mainly from the fact that there is now more to damage…at least for right now. And yes, as of this moment, via the NOAA:

It is premature to conclude that human activities–and particularly greenhouse gas emissions that cause global warming–have already had a detectable impact on Atlantic hurricane activity. That said, human activities may have already caused changes that are not yet detectable due to the small magnitude of the changes or observational limitations, or are not yet properly modeled (e.g., aerosol effects).

I think that the 538 article was trying to make that point. But 538 is listening to the criticism.

Personally: I find the idea interesting and I’ll continue to read the site regularly. However I am not looking to the site for answers but rather to see what is being talked about and what metrics are being discussed.

March 28, 2014

## Five Thirty Eight Starts up again….the discussion

I admit that while I haven’t read every new 538 article, I’ve enjoyed most of what I’ve read.

What I see here isn’t really new, but it is well put together. For example: this article correctly asserts that the increase in storm/disaster damage really isn’t due to global warming (at least there is no evidence for it) but rather because there is more there to damage in the first place.

I honestly think that articles that talk about the “subject being debated” have some value; it is nice to know what the argument is about. So far, I’ve liked what I’ve seen.

FiveThirtyEight is a data journalism organization. Let me explain what we mean by that, and why we think the intersection of data and journalism is so important.

If you’re a casual reader of FiveThirtyEight, you may associate us with election forecasting, and in particular with the 2012 presidential election, when our election model “called” 50 out of 50 states right.

Certainly we had a good night. But this was and remains a tremendously overrated accomplishment. Other forecasters, using broadly similar methods, performed just as well or nearly as well, correctly predicting the outcome in 48 or 49 or 50 states. It wasn’t all that hard to figure out that President Obama, ahead in the overwhelming majority of nonpartisan polls in states such as Ohio, Pennsylvania, Nevada, Iowa and Wisconsin, was the favorite to win them, and was therefore the favorite to win the Electoral College.

Instead, our forecasts stood out in comparison to others in the mainstream media. Commentators as prestigious as George F. Will and Michael Barone predicted not just a Mitt Romney win, but a Romney sweep in most or all of the swing states. Meanwhile, some news reporters defaulted to characterizing the races as “toss-ups” when the evidence suggested otherwise.1

So, why the need for data journalism? One important point:

Students who enter college with the intent to major in journalism or communications have above-average test scores in reading and writing, but below-average scores in mathematics. Furthermore, young people with strong math skills will normally have more alternatives to journalism when they embark upon their careers and may enter other fields.4

This is problematic. The news media, as much as it’s been maligned, still plays a central a role in disseminating knowledge. More than 80 percent of American adults spend at least some time with the news each day. (By comparison, about 25 percent of Americans of all ages are enrolled in educational programs.)

Meanwhile, almost everything from our sporting events to our love lives now leaves behind a data trail. Much of this data is available freely or cheaply. There is no lack of interest in exploring and exploiting it: Google searches for terms like “big data” and “data analytics” have grown at exponential rates, almost as quickly as the quantity of data itself has grown.

But this new website is now without critics.

feel bad about picking on a young staffer, but I think this piece on corporate cash hoards — which is the site’s inaugural economic analysis — is a good example. The post tells us that the much-cited \$2 trillion corporate cash hoard has been revised down by half a trillion dollars. That’s kind of interesting, I guess, although it’s striking that the post offers neither a link to the data nor a summary table of pre- and post-revision numbers; I’m supposed to know my way around these numbers, and I can’t figure out exactly which series they’re referring to. (Use FRED!)

More to the point, however, what does this downward revision tell us? We’re told that the “whole narrative” is gone; which narrative? Is the notion that profits are high, but investment remains low, no longer borne out by the data? (I’m pretty sure it’s still true.) What is the model that has been refuted?

“Neener neener, people have been citing a number that was wrong” is just not helpful. Tell me something meaningful! Tell me why the data matter!

Krugman goes further in another blog post:

Now, about FiveThirtyEight: I hope that Nate Silver understands what it actually means to be a fox. The fox, according to Archilocus, knows many things. But he does know these things — he doesn’t approach each topic as a blank slate, or imagine that there are general-purpose data-analysis tools that absolve him from any need to understand the particular subject he’s tackling. Even the most basic question — where are the data I need? — often takes a fair bit of expertise; I know my way around macro data and some (but not all) trade data, but I turn to real experts for guidance on health data, labor market data, and more.

What would be really bad is if this turns into a Freakonomics-type exercise, all contrarianism without any appreciation for the importance of actual expertise. And Michael Mann reminds me that Nate’s book already had some disturbing tendencies in that direction.

Yes: there is no substitute for knowing what you are talking about….and the problem with the “opinion pundits” is that frequently: they don’t know what they are talking about.

March 19, 2014

## No, the Starbucks CEO did NOT say that he didn’t want conservative customers. And about the lesbians are fat study….

For the record, here is what the Starbucks CEO said, and in context:

Howard Schultz, the outspoken CEO of global coffee chain Starbucks, calmly but firmly defended his company’s support of same-sex marriage last week at a shareholder meeting.

In response to a challenge from a shareholder that the company’s support of same-sex marriage was hurting the company’s stock price, Schultz explained that it’s not about the bottom line but about “respecting diversity,” according to KPLU-FM, a local affiliate of NPR.

Last year, the Seattle-based company openly supported Washington state’s referendum that legalized same-sex marriage. As a result, the National Organization for Marriage launched a boycott of the coffee giant. During the company’s annual meeting in Seattle last week, shareholder Tom Strobhar spoke up, suggesting that the boycott was affecting the company’s stock value: “In the first full quarter after this boycott was announced, our sales and our earnings — shall we say politely — were a little disappointing,” he said.

(MORE: Starbucks’ Big Mug)

Schultz shot back that Starbucks’ endorsement of marriage equality wasn’t bad for business:

“If you feel, respectfully, that you can get a higher return than the 38% you got last year, it’s a free country. You can sell your shares of Starbucks and buy shares in another company. Thank you very much,” Schultz said, to applause from the audience.

But Schultz was quick to underscore that it wasn’t even an economic decision to support gay rights. It was simply right for its people. “The lens in which we are making that decision is through the lens of our people. We employ over 200,000 people in this company, and we want to embrace diversity,” he retorted.

This had NOTHING to do with customers; this was only a reply to someone who thought that the company’s endorsement of same sex marriage had hurt its stock prices.

Of course that is too subtle for some people:

(facepalm)

And about Rush Limbaugh talking about the “why are lesbians fat” study: here is information about the real study:

The study, according to its abstract, is in fact examining the connection between obesity and sexual orientation. But there’s more here than the knee-jerk (and not very subtle) lesbian fat joke. It’s important to remember that nearly half of straight women are obese, too, and that the study is also figuring out why straight men are more often overweight than gay men:

It is now well-established that women of minority sexual orientation are disproportionately affected by the obesity epidemic, with nearly three-quarters of adult lesbians overweight or obese, compared to half of heterosexual women. In stark contrast, among men, heterosexual males have nearly double the risk of obesity compared to gay males. Despite clear evidence from descriptive epidemiologic research that sexual orientation and gender markedly pattern obesity disparities, there is almost no prospective, analytic epidemiologic research into the causes of these disparities.

In short, it is seeing if there is any causation to sexual orientation and obesity; either way, for either sex.

Oh boy…if you chat on the internet for any time at all, you can see evidence that many people simply don’t understand what they read (and that is a politically neutral condition)

March 26, 2013

## 20 March: evolution and devolution, big cats and other things.

Evolution
Jerry Coyne has an interesting post on mimicry in nature: this happens when one animal evolves to resemble something else; for example, sometimes an animal can evolve to look like something that preys on its natural enemies. However, read the post all the way down; there is a case in which the females evolved more mimicry than the males: though more mimicry might help the males live longer, it might have cost them potential mates if the females retained preferences for the “lesser evolved” males.

Here is a case in which swallows are evolving smaller wings….and at the same time, we are finding that fewer swallows are becoming roadkill:

A new study out of the University of Tulsa in Oklahoma seems to suggest that the cliff swallows there are adapting to their modified environments in an interesting way. Researchers found their wings may be getting shorter to help them take get out of the way of traffic.

“We found that by picking up dead birds killed by vehicles over the last 30 years, the wing lengths on these birds has changed, and we’re finding many fewer dead birds now than we were finding 30 years ago,” said Professor Charles Brown of University of Tulsa in Oklahoma. “So it looks like something is going on in the population enabling these birds to better avoid being hit by cars.”

According to data collected in the study, the swallows’ wing span decreased about 10 percent. Though that is not a large number, Brown says it’s significant because it’s happening in birds.

“It’s actually quite a bit as bird morphology goes,” said Brown. “Bird morphology is fairly static, it doesn’t really change much in response to selection, and this is actually a very dramatic change in a morphological trait.”

Though scientific evidence points to how natural selection allowing swallows to avoid being killed by vehicles, there are many other environmental factors that can contribute to such a evolution. For instance, Brown says that a change in the availability of insects, the bird’s natural prey, and changes to their habitat are factors to consider. Also, natural selection fluctuates over time, so adaptations we’re seeing now could cease to exist in the long term.

We shall see. Interesting, no?

I don’t get this behavior
I am not a Big Cat person (at all) but this is an awesome short video. It shows a cheeta paying a visit to some tourists in a tourist truck. It doesn’t really threaten the people in the truck, but it gets up close and personal; it “almost” behaves like a pet….a standoffish pet.

(hat tip: Jerry Coyne)

Mathematics
This is sort of random, but Jeffrey Shallit posts about a recently deceased mathematician and gives one of his results:

Here is a very simple, yet little-known result that proved useful to me recently. I’m surprised it is not better known, since it seems to be a natural question.
Suppose you have a directed graph G = (V,E) with n vertices that is strongly connected (so there is a directed path from every vertex to every other vertex). Consider the length of the shortest closed walk W that visits every vertex. In the worst case, how long can W be?

Here, as usual, by a “closed walk” we mean that we start at some vertex and return to it, and we are allowed to repeat vertices and edges. We measure the length of W by the number of edges, and write it as |W|. Such a walk is sometimes called a “Hamiltonian walk” in the literature.

The answer is floor((n+1)2/4). This simple result was apparently first proved by Yahya Ould Hamidoune, in Proposition 2.1 of his paper published in Discrete Mathematics 26 (1979), 227-234. Hamidoune just recently passed away; he was apparently one Mauritania’s most famous mathematicians, and proved many deeper results than the little proposition above. But his graph inequality might prove useful to others, so I reproduce his proof here.

Surf to Shallit’s blog to see the proof; it is one that, even if you aren’t a specialist, you can get something out of (with some intellectual effort).

Paul Krugman
He gets just a little bit snarky and I love it.
First, he cautions people:

Some readers have asked me to reply to this Steve Keen piece claiming that I don’t understand the IS-LM model. Sigh. I really don’t want to spend time fighting against people with whom I don’t really have a current policy disagreement — and this is so silly, besides. But to satisfy those who are for some reason nervous, here’s a brief explanation of why somebody doesn’t understand IS-LM.[…]

He then says, aha! The IS market is out of equilibrium when we’re in a liquidity trap, but Krugman writes as if it were in equilibrium! Gotcha!

Um, it pays to read the labels. Those savings and investment curves are what the supply and demand for funds would be if the economy were at full employment. They’re not the curves that actually apply when the economy is operating below full employment. In the IS-LM model, the quantity of funds supplied is always equal to the quantity of funds demanded — because the level of output adjusts. This is true both when the zero lower bound applies and when it doesn’t. […]

So what Keen thinks is a big logical fallacy on my part is just a failure of reading comprehension on his part.

Look, IS-LM could be all wrong; but I am accurately reflecting the way that model works. And while I am not infallible, I have done a lot of economic modeling in my time; if you think that I’ve made an elementary logical error, you might want to check your reasoning very carefully before going with it.

Seriously folks. These smart, famous people are sometimes wrong about conjectures or sometimes make mistakes. But they almost NEVER make “elementary mistakes” such as these. If you think that your “common sense” has found an elementary flaw in their work, YOU are almost certainly wrong.

Now what about conservative critics (mostly non-specialists): Krugman has little patience with them:

All of which raises an interesting question: why don’t people like Hinderaker who have been wrong about everything for years and years — demonstrably wrong, in ways that would have lost anyone who believed them a lot of money — ever reconsider? Shouldn’t the thought at least enter their minds that maybe economic analysis is not their strong point? Shouldn’t they at least entertain the notion that they are talking to the wrong “experts”?

So why doesn’t this happen? Part of it, surely, is the Dunning-Kruger effect: the truly incompetent are too incompetent to realize that they’re incompetent. Part of it, also, is the Madoff “affinity fraud” effect: people trust someone they perceive as part of their tribe — in this case the tribe of liberal-haters — and are blind to evidence that they are being taken for a ride.

The surprise, I’d say, is just how strong the Dunning-Kruger-Madoff effect has proved in the face of economic crisis. Year after year in which the predictions of their crowd have gone totally astray haven’t shaken their faith at all. They still believe that reading the WSJ editorial page and watching Fox are the way to know what’s going to happen to the economy, and nothing will change their minds.

Here is what I think that Krugman misses (remember, this is NOT economic policy but a conjecture as to why Fox and company stays in business despite getting just about everything wrong):

The Wall Street Journal and Fox are more about entertainment than anything else. People(*) often see “truth” as “what makes sense to me” and “what confirms what I already think”. These media outlets cater to that crowd. Accuracy is of no importance; it is about keeping the reader entertained.

(*): I used to think of this as a characteristic of conservatives, but have found that it really isn’t “just” conservatives. I am prone to making this mistake too and therefore have to be vigilant.

Michele Bachmann
She doesn’t appreciate it when she gets called out for just making stuff up. This is just over 9 minutes (from CNN) and is hilarious.

March 20, 2013

## One reason I mistrust journalists

What? Paul Krugman compared Alan Simpson to Bernie Madoff???? Well, no. Fortunately, I had read the Krugman article in question:

As I’ve written on previous occasions, the Bernie Madoff phenomenon helped me understand a lot about the persistence of bad economics. Madoff flourished through “affinity fraud”; his investors thought he was their kind of guy, so they didn’t look hard at how he was allegedly making money. And I realized that a similar phenomenon explains the enduring popularity of goldbugs and fiscal doomsayers — including, say, the Wall Street Journal editorial page — despite years of being wrong about everything; their devotees, who consist in large part of cranky old white men, see kindred spirits and can’t see past that to the consistently terrible analysis.

But it’s not just the goldbugs who benefit from affinity fraud, a point driven home by Ezra Klein’s piece on Alan Simpson. Simpson is, demonstrably, grossly ignorant on precisely the subjects on which he is treated as a guru, not understanding the finances of Social Security, the truth about life expectancy, and much more. He is also a reliably terrible forecaster, having predicted an imminent fiscal crisis — within two years — um, two years ago. Yet he remains not only respectable among the Beltway crowd; as Ezra says, he’s lionized in a way that looks from the outside like a clear violation of journalistic norms:[…]

See: what Krugman is referring to is that many see Simpson as “their kind of guy” and therefore don’t fact check him or even ask “does he know what he is talking about”, just as many investors did with Madoff. Krugman really isn’t comparing Simpson to Madoff. It is the phenomenon of “affinity fraud”.

I wonder if the person who wrote this headline bothered to read the Krugman article or has any reading comprehension skills at all.

## NPR: what has happened to you?

During the 2012 election, I spent a great deal of time trying to convince my NPR listening friends that the election was NOT close. But they kept telling me what they were hearing…on NPR.

Well, recently, some stuff came out about feral cats and how these are an invasive predator. Some data analysis was done on the damage that they do.

n fact, the situation is no laughing matter. Cats are hunters and other creatures do fall prey to them in significant numbers.

And yet there are serious reasons to suspect the reliability of the new, extreme cat-killer statistics.

The study at issue is a meta-analysis, an overarching review that aggregates data from previously published sources. The accuracy of meta-studies in health and medicine raises some concern, and it’s easy to see why: for a meta-analysis to be solid, wise choices must be made among the available sources of information, and results that may vary wildly must be weighed fairly.

Fair enough but the article really doesn’t advance beyond this point. Nevertheless a scientifically savvy reader weighed in (in the comments):

While I appreciate that this article attempts to explain what a meta analysis is, they can’t refute the findings, cats kill a significant (many billions) number of small animals. The authors used conservative estimates because they know there is uncertainty. The scientists say “We estimate that free-ranging domestic cats kill 1.4–3.7 billion birds and 6.9–20.7 billion mammals annually.” The author of this NPR story is calling their research into question but has no data to refute the scientists findings and shows their lack of objectivity, by saying “Demonizing cats with shaky statistics”. The research does not demonize cats, its simply bring together the data about how many animals cats kill. The author simply doesn’t like the researches findings. It rings similar to the folks who deny climate change… “we don’t like it so its not true”…

It seems that most people just don’t like to think that their beloved cat, goes out and kills small animals, and house after house it adds up. It’s what predators do. Dogs kill lots of small animals when people go hiking with them on leash, cats kill small animals when they go outside. Murder is not the best word, effective predators is much better.

This article’s author says “The truth is that we do need to better understand the relationship between cats and the greater natural world.”That is exactly what the scientists did… with sounds science based on the data availiable using conservative estimates.. This article is far below the quality of journalism that I expect from NPR. […]

To which the article author replies:

Hi, James. You’re right that I’m not a neutral observer of this matter. I’m a blogger, and not writing as a science reporter– I get to have a point of view! […]

Emphasis mine.

This author (Barbara J. King) sounds more like an entitled snowflake than an author. Yes, everyone is “entitled to a point of view” but you aren’t entitled to have it taken seriously by anyone else.

I wonder if NPR has reached the Fox News point: you are LESS informed after hearing/reading them than you were before.