Aztlán es mejor que el ColMex

Resultados de la prueba enlace secundaria:

2007
Aztlán	714.4	19 evaluados
ColMex	694.41	200 evaluados
2008
Aztlán	687.84	13 evaluados
ColMex	682.07	194 evaluados

JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA La variancia del promedio de la muestra aumenta conforme el tamaño de la muestra disminuye JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA JA

Bristol vs Sarah

Now that we now that Sarah Palin didn't fake her pregnancy and Bristol Palin is carrying Obama's baby let's talk about something else,

Assume that:

A = Has Down syndrome
B = Mother is between 40-44 years old
C = Mother is between 15-19 years old
Total Births = 4,265,996
15-19 year olds gave birth to 435,427 babies
40-44 year olds of age gave birth to 105,476 babies
Probability of having a Down's child if 17 is 1 in 1200=0.000833333333
Probability of having a Down's child if 44 is 1 in 30=0.0333333333

For Sarah
P(B|A)= P(A|B)P(B)/P(A) = 0.033 * (105,476/4,265,996) / 0.00125 = 0.65

For Bristol
P(C|A)= P(A|C)P(C)/P(A) = 0.00083 * (435,427/4,265,996) / 0.00125 = 0.068

It was never likely that Bristol gave birth to a child with Down syndrome, even if births among girls her age are more than four times as common as women of Sarah Palin's age.

I guess the moral of the story is that while certainly not optimal, and not something I recommend, it is better to have a baby at 17 than at 44.


Source:
[Washington Post (pdf)]

Olympic Efficiency

—Economics and Olympics: An Efficiency Analysis[pdf]

Many Eyes vs. Google Charts

Two charts comparing Many Eyes and Google Charts:

Many Eyes

Google Charts

You can get the data for the chart here Although Many Eyes has more chart types (most of which output chart junk) its charts lack the visual appeal of Google Charts, plus Many Eyes is built with Java which means it's slow and tends to crash my browser while Google Charts uses AJAX. I'll stick with Google Charts for the time being. P.S. I was surprised by the fact that in the US there is a higher percentage of marriages where the male is 10+ years older than the female, it's probably due to the fact that divorce is more common in the US.

Mix stuff and see what happens...

From a response to execrable essay The End of Theory

I can't possibly imagine how he comes to that conclusion. Correlations are a way of catching a scientist's attention, but the models and mechanisms that explain them are how we make the predictions that not only advance science, but generate practical applications. One only needs to look at a promising field that lacks a strong theoretical foundation—high-temperature superconductivity springs to mind—to see how badly the lack of a theory can impact progress. Put in more practical terms, would Anderson be willing to help test a drug that was based on a poorly understood correlation pulled out of a datamine? These days, we like our drugs to have known targets and mechanisms of action and, to get there, we need standard science.
[Arstechnica]

Maybe the pharmaceutical industry wasn't the best example:

Still, the total number of truly novel drugs approved each year has remained relatively constant.
[Freakonomics Blog]

And this is while spending on health reasearch went from $6 billion in 1980 to about $39 billion in 2004! Sometimes theory isn't good enough and you just have to mix stuff and see what happens. Worked for Flemming.