American Elephants

This is going to seem really boring, but stick with me.  There is method in my madness.  Ken Green, who is a scholar at AEI specializing in energy and environment, offers a quick definition from Wikipedia:

Data dredging, according to Wikipedia, is “the inappropriate (sometimes deliberately so) use of data mining to uncover misleading relationships in data. These relationships may be valid within the test set but have no statistical significance in the wider population.” Wikipedia gives a particularly relevant example: “Suppose that observers note that a particular town appears to be a cancer cluster, but lack a firm hypothesis of why this is so. However, they have access to a large amount of demographic data about the town and surrounding area, containing measurements for the area of hundreds or thousands of different variables, mostly uncorrelated. Even if all these variables are independent of the cancer incidence rate, it is highly likely that at least one variable will be significantly correlated with the cancer rate across the area.”

The U.S. Environmental Protection Agency (EPA) wants to regulate carbon dioxide (CO2).  It looks like cap-and-trade will not make it through the Senate, so the next best idea is regulating — and taxing — CO2, under the Clean Air Act, as a “pollutant.” As CO2 is what we exhale, it’s going to take some heavy evidence to get away with that.  Particularly since Climategate has pretty much put a damper on the whole global warming thing.  Congress never intended the Clean Air Act for any such thing, but Obama wants a carbon tax.  So the EPA proposes to give away $1.4 million in up to $300,000 portions to fund directional data dredging that looks only for relationships that suggest that exposure to various air pollutants cause harm to human health.  The polite term for this is “fishing expedition.”

EPA, ever helpful, gives some examples of what such data-dredging exercises might look like.  Air pollution associations with respiratory and cardiovascular disease have been studied extensively, but there might be some “air pollution impacts” on additional health conditions including diabetes, neurological disorders, tooth decay, brain tumors, zits, (Okay, I made up the last three, but surely you see the problems).

While data dredging can identify some correlations, it cannot identify causation.  It’s one thing for scientists to identify illness in a population, and to investigate what it is that might be causing it, but this is “Seek and ye shall find,” looking for ever more obscure health impacts to justify expanded regulation and EPA intrusion into the economy.   This funding proposal should be scrapped.

And the EPA should be scrapped while they’re at it.  (But I said that before).