Re: [asa] Letters to Sam Harris a "Maladjusted Misotheist"

From: P vM <pvm.pandas@gmail.com>
Date: Tue Dec 05 2006 - 16:41:30 EST

I have switched accounts since Yahoo seems to often mangle my postings

Pim

I see, you do accept a human component. That's a good start and if my
comment misrepresented your position then I apologize. The quote from
which I gathered your position suggested as much. So we now have the
existence of natural cycles, as well as a human caused component. The
human caused component has been shown to be a significant contribution
to the global warming we are experiencing right now.

As to the hockey stick graph, I ran across my good friend Tim Lambert
when researching this online

------------begin quote---------
Criticism of a McKitrick paper

Tim Lambert has McKitrick's own data analysis in a 2004 paper with
Patrick Michaels. Among other things, Lambert found a bug in which the
input to a cosine function was in degrees instead of radians. The
authors have acknowledged the error and published a corrected version.
They claim that the effects were "very small", that the correction
"improved the overall fit", and that their overall conclusion was
unaffected. Yet, after Lambert ran the regressions using the correct
angle measurments, he found that they "no longer "explain" half of the
surface warming trend McKitrick has pointed out."criticised McKitrick
also states that Lambert was only able to spot the bug because the
data and code used in the paper were put on a website upon
publication, as is usual in econometrics but rare in climate
reconstructions.
--------------end quote---------

Lambert's musings include an analysis of the impact of the number of
weather stations on the temperature graphs
(http://timlambert.org/2004/04/mckitrick/) as well as McKitrick et
al's hockey stick arguments http://timlambert.org/2005/02/climate3/

The claim that the software produces a hockey stick anytime is a red
herring as the question is: is the hockey stick statistically
significant

--------------begin quote---------
 Statistician Francis Zwiers of Environment Canada (a government
agency) notes that Mr. Mann's method "preferentially produces hockey
sticks when there are none in the data." This strikes me as a big red
herring. If you do a linear regression on random data, you'll produce
a straight line. Does that mean that linear regression is invalid
because it preferentially produces straight lines when there are none
in the data? Of course not. What is important is whether the result of
the regression is statistically significant—for random data it won't
be. William Connolley did some experiments and reports:

What that appears to demonstrate is that M&M are right about one
thing: it often does lead to a "hockey stick" shape in random data.
But the problem is that the variance-explained of the PC1 done this
way is tiny: the first eigenvalue is about 0.03. Whereas when you run
it on real data the first eigenvalue is about 0.55 (back to 1000) or
0.38 (back to 1400). Which means the two problems are very different.
--------------end quote---------

More can be found here:
http://www.sourcewatch.org/index.php?title=Ross_McKitrick

In other words, Janice's objections to the Hockey Stick are the real
red herring as it ignores that the data are statistically significant,
and even though the program may produce hockey sticks using random
data, the resulting match is not one of statistical significance.

Statistics 101. And perhaps an apology is in order for calling the
hockey stick fraudulent?

Hope this clarifies... Augustine would have been proud :-)

To unsubscribe, send a message to majordomo@calvin.edu with
"unsubscribe asa" (no quotes) as the body of the message.
Received on Tue Dec 5 16:42:25 2006

This archive was generated by hypermail 2.1.8 : Tue Dec 05 2006 - 16:42:25 EST