Small Sample-Size Theater

Software, politics, economics, baked goods.

Jul 15
This is Anandtech’s superb visualization of how the iPhone maps cellular signal strength onto its bar meter, both before and after the change in iOS 4.0.1. Their coverage of the iPhone 4 antenna story has been meticulous, quantitative, and detail-oriented, unlike virtually everyone else’s.

via anandtech.com

This is Anandtech’s superb visualization of how the iPhone maps cellular signal strength onto its bar meter, both before and after the change in iOS 4.0.1. Their coverage of the iPhone 4 antenna story has been meticulous, quantitative, and detail-oriented, unlike virtually everyone else’s.

via anandtech.com


Jul 11

Jul 10

Jun 30

Poems by Google Voice

First in a series.

I'll I'll it's mean 
wondering 
if you are going to camp 
where i fall and wait 
for brides 
and he wearing reputational job 
together. 
Anyway bye.

By Google Voice, with an assist from my mom.


Jun 25

May 14
Damn, neglected to blog this fabulous NYT infographic, depicting the debt relationships of Greece, Ireland, Spain, Portugal, and Italy. It’s the sexiest pentagram I’ve ever seen.

Damn, neglected to blog this fabulous NYT infographic, depicting the debt relationships of Greece, Ireland, Spain, Portugal, and Italy. It’s the sexiest pentagram I’ve ever seen.


May 10

May 9

May 7

May 5
This has been my desktop pattern for about a year. I adore it. The worst transitional problem to the fabulous new higher-resolution laptop is that this image no longer fills the screen without pixelation. Quel dommage.

via www.amusement.fr

This has been my desktop pattern for about a year. I adore it. The worst transitional problem to the fabulous new higher-resolution laptop is that this image no longer fills the screen without pixelation. Quel dommage.

via www.amusement.fr


Mar 30

Court-packing

From Alan Brinkley’s review of Jeff Shesol’s “Supreme Power”, about FDR’s attempt to expand the Supreme Court, a charming detail I’d never heard before:

Shesol also draws attention to a more mundane but nevertheless considerable factor in the shift of the court. In 1937 Roosevelt supported, and Congress approved, a bill to assure retired justices that they would continue to receive their judicial salaries even after retirement. The absence of such benefits had deterred some aged justices from retiring; once the pensions were assured, several of them resigned.

Would that Obama had such low-hanging fruit to pick.



Mar 26

Texas

An eye-popping detail from Michael Luo’s NYT article on the ACA’s effect on state Medicaid budgets:

Texas, which has some of the most restrictive Medicaid eligibility rules in the country for adults, currently covers working parents only if they do not earn more than roughly 20 percent of the federal poverty level. The program does not cover childless adults.

He mentions in the preceding paragraph that the federal poverty level for a family of four is $29,300. 20% of that is $5,860 per year.

So while Obamacare winds up subsidizing states like Massachusetts which have done a good job keeping people from going uninsured, it’s administering a richly deserved beatdown to states like Texas, Arizona, and California which prefer letting people die in the streets to hiking taxes by a nickel. Good for Obamacare.


Mar 25

John Gottman

Gottman is the psychologist profiled in “Blink” who analyzes couples’ interactions and predicts whether they’ll get divorced. Sadly, Laurie Abraham notes in Slate that his methodology wasn’t everything Malcolm Gladwell made it out to be:

So what does it mean to predict divorce? For the 1998 study, which focused on videotapes of 57 newlywed couples, I assumed that Gottman had, in the first instance, sorted them into three groups—will divorce, will be happy, will be unhappy but still married—based on the conflict-variables he believed distinguished marriages that last from those that don’t (contempt, little positive affect, elevated male heart rate, etc.). Then, at six years, he’d checked to see how right, or wrong, his predictions had been. That isn’t how it worked. He knew the marital status of his subjects at six years, and he fed that information into a computer along with the communication patterns turned up on the videos. Then he asked the computer, in effect: Create an equation that maximizes the ability of my chosen variables to distinguish among the divorced, happy, and unhappy.

The upshot? What Gottman did wasn’t really a prediction of the future but a formula built after the couples’ outcomes were already known. This isn’t to say that developing such formulas isn’t a valuable—indeed, a critical—first step in being able to make a prediction. The next step, however—one absolutely required by the scientific method—is to apply your equation to a fresh sample to see whether it actually works. That is especially necessary with small data slices (such as 57 couples), because patterns that appear important are more likely to be mere flukes. But Gottman never did that. Each paper he’s published heralding so-called predictions is based on a new equation created after the fact by a computer model.

It gets worse when she tackles his accuracy rate, and its failure to account for false positives and false negatives. Bummer.


Page 1 of 4