Frequentist vs Bayesian

Layfolks hoping to sound sophisticated often ask their statistician aquaintences the following buzz-question: "Are you a frequentist or a bayesian?" I have always been terrified by this question. As an imposter in the field of statistics, I am terrified by almost any question having to do with data.

Suppose I want to know the average height of people in the US. This average I will call hpop. To estimate hpop, I randomly choose 100 people and take their heights, and compute the average height. Call this sample average hsamp. For most people and I, saying "hpop is probably somewhere near hsamp" is good enough. But a statistician wants to know exactly how close hpop is to hsamp, and with what probability.

At this point, a frequentist (not to be confused with a Freakwentest), creates a "confidence interval." This involves estimating the variance of heights, and then applying some theoretical crap having to do with "normal" distributions to come up with a minimum number, say 5.5 ft, and a maximum number, say 5.7 feet, such that we can be "95% confident" that hpop is between 5.5 and 5.7 feet.

A bayesian, on the other hand, does something weird and ends up with a statement like "the probability that hpop is between 5.5 and 5.7 is approximately 0.95." This sounds a lot like being 95% confident that hpop is between 5.5 and 5.7, but it's not.

Someday I will have a better answer for the question, but until then I am an opportunist, picking between frequentist or bayesian methods on the basis of convenience instead of ideology.

The Fragmentation of an Ethnicity

Introducing four new essential terms for the evolving US Mennonite ethnicity. I invented the term Mennonista to describe liberal activists of a Mennonite ethnicity. But wait, I didn't exactly invent the term; it was already in use. Mennocons are Mennonites who voted for George Bush and watch Fox News. Libernites are Mennonites who lean libertarian. Millenonites tend to be younger, and Mennonite colleges cater to these youth as "Millenials." Millenonites are conformists who don't pay attention to politics or salvation, focusing instead on sports or videogames.

Musicians are people

I stepped alone into a bar. The door girl asked for ID. She took her time finding the DOB on my DC DL. I took a cushioned wall seat at the back, between two occupied tables. The people next to me didn't look at me. I looked at them only long enough to figure out that they were not looking at me. Then I looked straight ahead, at the stage.

"Slumdog" had his electric violin out. Between songs he wiped sweat off his mid-fifties Indian face with some kind of cloth. A guest with a guitar would play two songs, and Slumdog would play along. Then Slumdog would call up the next act. Mostly young men with guitars. Songs that you could tell they wrote.

A young boy with a guitar and enough confidence to run for president sang about high school. He didn't notice that we were clapping for his confidence more than for his music. Slumdog clapped the loudest. But darn, the boy wasn't bad for a 15-year old.

The next guy to come on stage was over the hill, and seemed to begrudge the tunes out of his guitar. He was good enough to be in a touring band. But ten years ago he suddenly realized that he was never going to make it big-time, and ever since then he has been trying to learn how to enjoy music for its intrinsic enjoyability. He supposes that playing for free with his friend Slumdog is a good start, but it doesn't come natural.

A meloncholy mid-twenties fellow played one of the first songs he ever wrote. He strummed slowly in a minor key, and his voice was even more minor than his chords. He was minoring the minor, probably too much alcohol, out of stage fright.

I could see it was getting dark outside, so I went out. It was nice out in the dark.

A soundbyte from the soundbitten for the soundbiter

Today the chairman practiced for his upcoming "Town Hall" gig in Kansas, to be moderated by Jim Lehrer on PBS. I gave the chairman some soundbyte practice:

I hear a lot of talk about increasing regulation to fix the economy. It seems ironic that we are looking to regulation as the solution even though over-regulation may have been part of what created this crisis. For example, government sponsored enterprises such as Fannie and Freddie created much of the toxic debt by purchasing subprime mortgages. Do you see a place for deregulation as a tool for addressing the crisis?

The chairman's response was polished and lame, as if had given some thought ahead of time about how to avoid this question. He had two points.

First he agreed that it is correct to put some blame on Fannie and Freddie; they should not have been buying some of those mortgages. Then he said that the problem is not the quantity of regulation, but the quality. He leaned heavily on this point through the rest of the Q&A, even referring back to my question at one point to restate his answer. He said it's not a question of how much regulation we have, but instead it is a question of whether we are making smart regulation.

Duh? Yes, duh. This was soundbyte time. What else could have he said? Did I expect him to commit political suicide and provide a list of ongoing government programs that are currently planting the seeds of the next great crisis? Of course not. But he could have taken the opportunity to promote my libertarian creed:

• Federal programs are easy to create, costly to run, highly fallible, and difficult to kill.
• We must take every opportunity to kill unnecessary regulation.
• Existing government regulations should be constantly examined for unintended consequences.

Maybe he will do better in Kansas, after reading this post.

Light on the Face of the Earth

Willie Nelson does reggae, and the internets will let you hear it. We used to have seeqpod.com to let us listen to most any song. A while ago seeqpod became "cocooned for metamorphosis," never to emerge, probably taken down by lawsuits. But grooveshark.com has brought light (in the form of free music) back on the face of the earth.

Bernanke Takes Questions

The chairman of the Federal Reserve may be taking questions from the crowd in the near future. Anyone have a question I should relay?

The financial crisis explained

This is paws-down the best explanation of our economy that I've seen. Thanks to Mankiw for mentioning it.