Mark Roulo on baseball statistics

re: the 32-parameter value-added model in NYC

One thing I like doing for discussions like this is to try and find a sports analogy. People tend no to get so hung up on non-PC conclusion in sports, but also often care a lot. This can lead to enlightenment.

So ... baseball:

(1) You can get a *VERY* good handle on how valuable a batter is with just two values, which can be combined into one number. You need on-base percentage (OBP) , which is, for every 100 times he comes to the plate, how often does he get on base? And you need slugging percentage (SPG) , which says how many bases he gets each time he has an at-bat. In both cases, more is better. And you can combine them with this: (OBP*3 + SPG)/2 to get a number that works the way most people who follow baseball can understand.

There ARE more sophisticated models, but they don't improve on this one by much. So ... two parameters, both of which are pretty easily understood.

(2) For pitchers it is a bit more complicated, but you can basically track strikeouts, walks and home runs and then put them together to get a single number. Again, one can improve (for starting pitchers, you also care about how "efficient" they are), but basically you'll get the right answer for ranking pitchers with just these three.

I get that teaching is more complicated. But 32 parameters is nuts.

Mark Roulo on the mathefication of the universe

"What I've seen in academia is that the various disciplines seem to 'complexifiy' themselves, either by becoming 'theoretical,' in the case of language-based disciplines, or by becoming 'mathified,' in the case of the social sciences."

The mathefication is not just an academic thing. The real world is becoming more quantitative. Some examples:

(1) Major League Baseball has (slowly ... with a lot of resistance) started paying attention to statistics *much* more when evaluating players. The key here isn't just that people are paying attention to things like batting average. They have *always* done that. The key is that people are starting to try to correlate different things with winning. So, the modern baseball stats-head mostly doesn't care about batting average.

The stats are easily available to someone with a *solid* high school math education. The point, however, is that even baseball is getting much more quantitative than it historically has.

(2) Drug Design. More and more companies are trying to design drugs using computer models (not just physics/chemistry simulators). This requires *lots* of math beyond what a normal PhD chemist would know.

(3) Quantitative supply chain management. Think about what Wal-Mart does. Very mathy. Wasn't done by anyone 30 years ago.

(4) Wall Street Trading. I'd say that today if you don't have a very heavy math background, you basically *can't* trade stocks/bonds/etc on Wall Street today. There may be some exceptions, but the field is much more quantitative than 30 years ago. Read up on LTCM (which went down in flames!) for more details.

(5) SQM (Statistical Quality Control), used by many manufacturing companies, is a mathematical approach to quality control.

So it isn't just academia. A lot more jobs have gotten quantitative in the last 30 years.

Which sorta makes things like TERC even more scary.