I’m sure I freaked out some of the science minded around here with my posts on Lomborg and Lee. It’s just a blog though and it’s about whatever catches my attention next. You are all welcome to contribute and dilute my opinions at your whim. DeWitt Payne, is very much science first, and he’s done something which is very interesting. Unfortunately, getting the documentation/post from him is sometimes like pulling teeth.
LL
I’m going back to science stuff for a while, unless someone drops another crazy link on a thread. Basically, after some time the politics of climate become so sickeningly bad that it’s impossible to listen to.
What DeWitt discovered/revealed was that with a different red noise model matched to the Mann08 proxy data than I used in my posts, he was able to retain 31 percent of the series, even though they had zero signal.
DeWitt Payne said
September 1, 2010 at 8:00 pm e
After a few false starts with the loop and array indexes, I created 1209 synthetic random series with the same parameters as the Mann infilled data with an ARFIMA (1,d,1) model. There were 4 series that returned AR coefficients greater than 1 and one with an AR coefficient less than -1. I set those coefficients to 0.999 and -0.999 so I wouldn’t see warnings about non-stationary series. <b>I still get acceptance of 31% of the no signal series, i.e. a Hockey Stick. That’s after scaling all the series to a mean of zero and an sd of 1. </b>I’ll have to try not scaling, but if I don’t scale, the average over all series is not zero. But then maybe it shouldn’t be. Adding the signal 1:1 with the noise, the acceptance was 80%. At a ratio of 5x noise to signal, the acceptance was about 40% with the usual behavior of squashing the ‘reconstructed’ sine wave signal relative to the calibration period.
Read the rest of this entry »