The statistical curve of nostalgia

Vinyl sales are on an upward swing! 

A remarkable 2.9 million vinyl LPs have been sold in the U.S. so far this year, up 33.5 percent from 2012, according to Nielsen SoundScan (NLSN). In fact, vinyl has been steadily on the rise since bottoming out in 2006, when only 858,000 records were sold. In just seven years, the 65-year-old format has bounced back 338 percent.

But in the scheme of things, it's not really that popular. 

But here’s the thing: Even in today’s diminished music business, 2.9 million albums isn’t very much. Vinyl sales make up only 1.4 percent of all albums sold so far this year, according to Nielsen SoundScan, which makes touting the “comeback” of vinyl a little bit like telling a double amputee that at least he won’t have to spend money on winter gloves.

It strikes me that this type of sales curve, a long period of decline followed by a slight upward rebound that doesn't get you anywhere close to the earlier peaks, is the shape of many things that go out of style before making a minor comeback as a novelty, a nostalgic fashion statement.

Nate Silver and Sam Wang on impact of shutdown

Sam Wang penned an article on the impact of the government shutdown on Republicans and their House seats. It's titled "Republicans could lose their House majority because of the shutdown":

Since the election is over a year away, it is hard to predict how this will translate to future seat gain/loss. If the election were held today, Democrats would pick up around 30 seats, giving them control of the chamber. I do not expect this to happen. Many things will happen in the coming 12 months, and the current crisis might be a distant memory. But at this point I do expect Democrats to pick up seats next year, an exception to the midterm rule.

Nate Silver was the more famous of the election prediction pundits from the last Presidential election, but among people who followed that space closely Sam Wang's Princeton Election Consortium was just as much a must-follow. Silver's relaunch of FiveThirtyEight.com hasn't arrived yet, but in the meantime he penned a quick piece over at Grantland, his temporary home.

1. The media is probably overstating the magnitude of the shutdown's political impact.

Remember Syria? The fiscal cliff? Benghazi? The IRS scandal? The collapse of immigration reform? All of these were hyped as game-changing political moments by the news media, just as so many stories were during the election last year. In each case, the public's interest quickly waned once the news cycle turned over to another story. Most political stories have a fairly short half-life and won't turn out to be as consequential as they seem at the time.

Some took these two pieces as an opportunity to pit the two pundits against each other, but as Wang notes, the two are not as far apart as provocative headlines might make it seem. Wang does think this time could be different, though.

Multiple polls, including detailed onerom NBC/WSJ, show that public sentiment has turned against the GOP. Under the radar, gerrymandered districts are swinging much harder than I was expecting. If the election were today, Democrats would control the House by about 50 seats. That will fade, but by how much?

Silver lists other events that didn’t move opinion: Benghazi, and the IRS business, and Syria. But the shutdown has, bigtime. I agree with him that most pundits emit bulls**t, which is why I am working on a prediction model. Right now, the model is saying: as long as the GOP stays on its current path, where the House goes next fall is an even-money bet.

How this impacts the next election will be a fascinating test of whether this gambit by the extremists in the Republican Party really boomerangs on them. Any system that divorces costs from actions really kills the feedback loop that's needed for continuous improvement. 

The Most Dangerous Equation

That's the title of a chapter (PDF) excerpted from  Picturing the Uncertain World. Even if you're not a statistician by trade, it's an interesting read. The subject is De Moivre's equation, and the author makes a great argument that people's misunderstanding of the equation has led to “billions of dollars of loss over centuries, yielding untold hardship.”

A long discussion of the chapter is here at Metafilter. 

The economics of pick-up artists

Via Kottke, an analysis by Katie Baker of why pick-up artists' game might not work as well in Denmark.  Avert your eyes now if you're sensitive to some colorful language:

Don’t Bang Denmark—note the dramatic title change—is a cranky volume that (spoiler alert!) probably won’t help any Roosh acolytes score. Roosh calls it the “most angry book” he’s ever written. “This book is a warning of how bad things can get for a single man looking for beautiful, feminine, sexy women.”

What’s blocking the pussy flow in Denmark? The country’s excellent social welfare services. Really.

...

As Roosh himself admits in Don’t Bang Denmark, Nordic social democracy doesn’t support his kind. His guidebook concludes with a resigned “bottom line” acknowledgment that his time in Denmark “liberalized me when it came to a government taking care of its citizens….Denmark sucks balls for women, but it kills the United States when it comes to having a higher standard of living.” Still, he won’t be going back anytime soon.

Beneath the craziness lies a potentially interesting economic argument about the forces driving transactions in the mating market. 

ShotScores

The great Kirk Goldsberry has pulled back the curtains on a new measure of basketball shooting prowess which he calls ShotScores. 

By overlaying players' shot constellations, we can estimate the expected total number of points that an average NBA shooter would produce, based on where he took his shots; then we can compare a particular player's actual yield against it.

When you put it like that, it sounds so basic, yet it's been difficult until now to measure something like this. But no more. We can finally factor in degree of difficulty when judging a player's shooting ability.

Goldsberry ran the numbers for last season, and the top three players in ShotScores were the following: 

1. LeBron James
2. Kevin Durant
3. Stephen Curry

Always helpful when you create a new statistic and it passes the eye test. Counter-intuitive results are more intriguing, but it's helpful for adoption when your results mesh with the opinion of NBA scouts and analysts. 

Incidentally, the NBA signed a deal with STATS Inc. to install SportVU cameras in all of its stadiums for the upcoming season, so we're about to enter a Golden Age of basketball analysis. I'd argue that the NBA, of all the major U.S. sports leagues, has released the most comprehensive set of statistics to the public through its website. I could spend hours just combing through that stuff, and it will only get better if they include SportVU data.

As an example, Henry Abbott of Truehoop highlights a few new basketball strategies that have become accepted wisdom in the past few years thanks to new analysis.