A couple of days ago I wrote that people from Titan TV interviewed me, and a slew of others, at the Heartland Climate Conference. Their piece is now on the web and can be found here. I didn’t make the cut, sadly; proving once again I have the perfect face for radio.
I gather, by the selection and arrangement of the sounds bites presented, the Titan TV reporter was attempting irony and humor, which I can tell you ain’t easy. Most who try fail.
Oh—and you’ll get this if you watch the two-minute video—I do not own a car, or motorcycle, or any other form of transportation, not even a bike, and I have not owned any of these for over a decade. I walk most places and I actually do use those miniature fluorescent light bulbs to illuminate my exorbitantly expensive 800 square feet, but only to foil Con Edison’s plan to take as much of my paycheck as the money-besotted Congress does.
I thought that was actually pretty funny. It was an obvious “Colbert” riff, but in that context the conference came off looking pretty good.
William, many of us are hopelessly confused and still more hopelessly uninformed about PCA. Right now there is an interesting correspondence going on on Tamino about MBH and the McIntyre analysis of MBH, not to mention Wegman’s endorsement of MM…..
Do you have time to write a simple authoritative explanation of what has been done by who and who is right and who is wrong? You will be doing us all an immense favor if you can.
Anon,
I’d be happy to post something about principal components analysis. Do you have a specific link in mind where examples are being used?
Briggs
http://tamino.wordpress.com/2008/03/06/pca-part-4-non-centered-hockey-sticks/
is the current case. The Wegman report was another:
http://www.climateaudit.org/pdf/others/07142006_Wegman_Report.pdf
http://www.uoguelph.ca/~rmckitri/research/StupakResponse.pdf
http://www.uoguelph.ca/~rmckitri/research/McKitrick-hockeystick.pdf
s a lay account of the issue. See also
http://www.uoguelph.ca/~rmckitri/research/PCnotes.pdf
I really cannot get to the bottom of this thing. Decentered PCA, data mining and so on. Eigenvalues! Help!
Cheers.
William, it looks to me like a two by two matrix. But I do not understand this stuff properly.
It seems like we have a time series which may or may not contain a trend.
We apply PCA using the mean of a subset of the series, rather than the mean of the series. I don’t actually understand how to calculate PCA, so I am not sure what this really means. Then there seem to be four possibilities: the data has a trend and DPCA either picks it correctly or wrongly fails to pick it. It has no trend, and DPCA wrongly shows one anyway, or else correctly says it has no trend.
Don’t know if I understand the debate at all, but one question seems to be whether using the mean of a subset of the series makes a difference to the answer in some, or in all, of the above four cases.
All,
I will get to the PCA stuff in a little bit. It’s very easy to be confused by these things, and even when they are used perfectly correctly, they do not always mean what you think they do (how’s that for confusing!).
See today’s post for more confusion.
Briggs
1. The humor was well done, gentle.
2. I’m bummed that you went to the Heartland Conference. Please tell me that you thought Watts and such to be poor thinkers.