Born-Again Bayesian

I’m finally getting to the point where I can do my own typing (this is my hand, not Mrs. Tamino’s), but I’ve fallen far enough behind that I have catching up to do in lots of areas. Still, I thought I should resume blogging with a thank-you to readers.

AIC part 1: Kullback-Leibler Divergence

Warning! This post is mathematical. Disinterested readers beware!

One of the goals of time series analysis is to model the signal underlying the data. If the data have some random element to them, they’ll follow some probability distribution. The distribution might be dependent on external variables (like time), in which case we usually create a model in which the mean of the distribution is time-dependent. Suppose, for example, we model a variable as following a straight line time trend, plus random noise:

,

Message to readers

Thanks to all for continuing to visit in spite of the absence of posts. My injury was more severe than I thought at first. However, my wife is willing to help with typing so I hope to post something before too long … I can’t yet say exactly when, but possibly soon.

As for Steve McIntyre’s latest: I’m really not that interested. He just doesn’t have the credibility to merit attention. I have way better things to do.

Seasonal Cycle in Central England Temperature

For the moment, just a graph:

Seasons

I noted in this post that the GISS data since 1975 show a seasonal pattern (an annual cycle) in spite of being temperature anomaly. This is because they’re anomaly relative to a 1951-1980 baseline, so the seasonal pattern which is subtracted from the data is the average annual cycle from 1951-1980. The annual cycle in global temperature isn’t perfectly constant, and the difference between the annual cycle at any given moment and its average for the baseline period is detectable in the GISS data.

MacGruber!

MacGruber!
Makin’ lifesaving inventions out of household materials
MacGruber!
Gettin’ in and out of ultra-sticky situations
MacGruber!
The guy’s a friggin’ genius
MacGruber!!!

….. Scene: American Petroleum Institute Control Room …..

Andy: The door’s jammed, MacGruber. We’re trapped!

Vicky: And from the looks of that bomb, those methane clathrates are gonna explode in twenty seconds!

Andy: That’ll really increase global warming, MacGruber!

MacGruber: Calm down … I’ll defuse this bomb … Andy, hand me that paper clip.

Andy: Right here, MacGruber.

MacGruber: Vicky, hand me that scotch tape.

Vicky: You got it, MacGruber.

Andy: Wow. It says here that the American Enterprise Institute will pay ten thousand dollars for articles denying global warming.

MacGruber: Really? Boy, I could sure use that kind of money.

Vicky: Ten seconds, MacGruber!!!

MacGruber: Hold on, hold on. Tell me more about that ten thousand

Boom!

Crystal Ball

Gaze into the crystal ball …

Summer ‘09

It’s no surprise how often denialists focus on regions with cooler-than-average temperatures to imply that the globe itself is cooling. The latest spate of such posts is about this summer in the U.S.; maybe the “best” is this one:

Reply to Lucy Skywalker

You ask if I’m being fair. I doubt that you’ve been honest — not even with yourself.

Conservative Republican

John Warner is a conservative republican. He’s also a former senator from Virginia, former Navy secretary, and former chairman of the Senate Armed Services Committee. He was recently interviewed for Politics Daily, and talked about his efforts to support climate legislation.