Thursday, December 30, 2010

Health Related Links

1. Mandatory minimums lead to competing increasing drug purity. When there is a per unit tax, people switch from the taxed margin (quantity) to the untaxed margin (quality).

2. A racial gap in condom use. This is tricky. More condom use among African American males does not lead to less disease. It may in fact be a response to higher disease incidence. They also have a higher degree of concurrent partners.  Make no mistake, this has only very little to do with race, and a lot to factors correlated with race, such as sex ratios, education, etc.

3. Beware of substitution effects. When the price of one drug goes up, addicts substitute.

4. Technology and health. Even as technology promises to improve our health outcomes, it has a dark side. At worst it can kill the patient. Or it can cure the patient of an ailment that would never have killed the patient (by killing a slow growing tumor), thus making its marginal efficacy in terms of increasing life zero, yet its cost is far from zero. Still at other times the technology might just be overused.

Saturday, December 18, 2010

What do practitioners need to know about regression? - Statistical Modeling, Causal Inference, and Social Science

From Andrew Gelman:

What do practitioners need to know about regression? - Statistical Modeling, Causal Inference, and Social Science:
"More specifically, here are some tips:

- The difference between 'significant' and 'non-significant' is not itself statistically significant.

- Don't just analyze your variables straight out of the box. You can break continuous variables into categories (for example, instead of age and age-squared, you can use indicators for 19-29, 30-44, 45-64, 65+), and, from the other direction, you can average several related variables to create a combined score.

- You can typically treat a discrete outcome (for example, responses on a 1-5 scale) as numeric. Don't worry about ordered logit/probit/etc,, just run your regression already.

- Take the two most important input variables in your regression and throw in their interaction."

Greg Mankiw's Blog: The Tax Deal

Here is the breakdown on the payroll tax deduction. Greg Mankiw's Blog: The Tax Deal. If it was permanent, then whether it came from the employers share or the employees share would not make a difference. In the short run a temporary cut makes a big difference. This one is clearly weighted towards boosting consumption.

Wednesday, December 08, 2010

Rational Addiction

A funny video, skewering the idea of "rational addiction"

History

Krugman makes an important point in response to Pence and Ryan calling for a discussion of the gold standard.
In other news, Republicans have demanded that doctors consider reintroducing the practice of treating illness by bleeding their patients.

I love the sarcasm. But my issue with Krugman occurs further up in the entry when he says:
There’s a widespread impression that Keynesian fiscal policy has failed. I would argue that this impression is wrong — that the truth is that it was never tried.
Yeah Paul that is exactly what the monetarists said after the experiment in the 80s. And I'm sure you'd skewer them for such a weaselly response. The truth is dogmatic adherents to some ideology will always claim we just didn't quite try hard enough to follow it.

Monday, December 06, 2010

Finding Happiness

In the econ literature there is a pretty well known U shaped relationship between age and happiness, with happiness being at its lowest around middle age. So I thought that meant my happiness had nowhere to go but up.

It turns out that it is probably not true.
The inclusion of the usual socio-economic variables in a cross-section leads to a U-shape in age that results from indirectly-age-related reverse causality. Putting it simply: good things, like getting a job and getting married, appear to happen to middle aged individuals who were already happy. . . . The found effect of age in fixed-effect regressions is simply too large and too out of line with everything else we know to be believable. The difference between first-time respondents and stayers and between the number of years someone stays in the panel doesn't allow for explanations based on fixed traits or observables. There has to be either a problem on the left-hand side (i.e. the measurement of happiness over the life of a panel) or on the right-hand side (selection on time-varying unobservables).
But maybe I should just listen to Penelope Trunk and stop trying to be happy. Of course maybe I shouldn't take her advice, even if I wouldn't mind having sex with her - it would be different. Speaking of sex, I hear that helps improve happiness.

Previous musings on happiness.

Sunday, December 05, 2010

A New Country

Located somewhere close to kerplakistan, the NYT finds a new country. My secondary residence: LAPTOPISTAN
Published with Blogger-droid v1.6.5

Friday, December 03, 2010

Competition

When class bores, texting soars. Wow, it is a good thing my class isn't boring.
Published with Blogger-droid v1.6.5