Monday, October 26, 2009

Recent global cooling isn't in the statistics

A nice article from Seth Borenstein, one of the better climate science reporters, tries to explain how, statistically, there is no such thing as recent global cooling.
The case that the Earth might be cooling partly stems from recent weather. Last year was cooler than previous years. It's been a while since the super-hot years of 1998 and 2005. So is this a longer climate trend or just weather's normal ups and downs?

In a blind test, the AP gave temperature data to four independent statisticians and asked them to look for trends, without telling them what the numbers represented. The experts found no true temperature declines over time.

"If you look at the data and sort of cherry-pick a micro-trend within a bigger trend, that technique is particularly suspect," said John Grego, a professor of statistics at the University of South Carolina.
I love the idea of the AP asking 4 statisticians to just analyze a time series without giving the source of the numbers.

I don't know why the satellite data is labeled by Borenstein as "preferred by skeptics". They used to like it when an incorrect analysis suggested it contradicted model predictions. Not so much after the mistake was corrected.

The gist of this article is that, in statistics, you can't just throw out the data you don't like. That's what deniers are doing when they choose to only look at the last few years or so and say: "the data says the globe is cooling". But they have no way of knowing if that is temporary or permanent. The honest thing to do is to look at all the data and that data says its warming.