Re: Democrats try to hide anti-global warming report

On Wed, 01 Jul 2009 12:48:01 -0700, "garycarson"
<garycarson@xxxxxxxxxxxxxxxxxxxxxxx> wrote:

On Jul 1 2009 1:51 PM, FL Turbo wrote:

On Wed, 01 Jul 2009 11:05:32 -0700, "garycarson"
<garycarson@xxxxxxxxxxxxxxxxxxxxxxx> wrote:

On Jul 1 2009 11:40 AM, FL Turbo wrote:

On Tue, 30 Jun 2009 15:22:56 -0700, "garycarson"
<garycarson@xxxxxxxxxxxxxxxxxxxxxxx> wrote:

On Jun 30 2009 2:07 PM, FL Tur


------------------------------------------------------------------------
After reviewing the scientific literature that the EPA is relying on,
Carlin said, he concluded that it was at least three years out of date
and did not reflect the latest research.
"My personal view is that there is not currently any reason to
regulate (carbon dioxide)," he said. "There may be in the future. But
global temperatures are roughly where they were in the mid-20th
century.
They're not going up, and if anything they're going down."
-----------------------------------------------------------------------

Well, he didn't say that they have been uniformly going down every
single year of the 11, but the trend was still down, not up.

Well, no, he didn't say anything about trend. Globald temp has a lot of
noise. It's hard to identify the signal. He's talking about his
"personal view"? What the hell does that mean?


My guess is that he has personally looked at the data and tried to
separate the wheat from the chaff.

Statistical analysis is a tricky business, ain't it?

I'm not a meterologist, but I am an economist. I've done graduate work in
economics, taught economics, and published in economics journals. I've
also done graduate work in statistics and taught statistics.

The standard econometric model is as you suggest, Y = X + e where X is a
deterministic component (wheat) and e is a random component (chaff or
noise). I know of no reason to think that model or general approach to
data analysis is appropriate for global tempature estimates.


It seems to me that a whole lot of the AGW proponents rely on computer
models and statistical analysis to support their conclusions.

So?


Is my concept of what constitutes statistical analysis wrong?

Yes.


It could well be that a more appropriate model treats the noise as an
inherent part of the process rather than some external shock or
measurement error. In fact, there's a recent article in management
science about something like that in finance, just looking at portfolio
risk and ignoring expected returns. Such a model outperforms one that
tries to maximize expected returns. Because that basic model above is
flawed.


Well, you lost me here.
I don't understand what you're talking about.

You might model the noise as something external to the system thatneeds to
be extracted and ignored. That's what most economists do. Or you might
model the noise as the system itself, something that should not be ignored
but should be the focus.


So how do you determine whether that "noise" is internal or external?
Maybe a personal judgment?

Sometimes you get a stronger signal by using a model that has a focus on
the noise rather than on the signal.


It depends on your personal selection of the model, doesn't it?

That means economietric type approaches just might not be appropriate at
all.

Is that clearer?


So it "just might not", but that then leaves it open to "just might".

From what you have told me, it depends on personal judgment about what
approach is more valid.




Just because this years temp is the same as the temp in 1950 says very
little about trend -- it could well have an upward trend but just be the
same in those two years because of noise (variance).


Here are a few handy dandy little "blink comparison" charts showing
the NASA data from 2000 and comparing it to the 2009 data graphs.

So?

So their suggestion is that NASA has been "cooking the books" when
they made adjustments to the raw data.

What is your explanation for the differences?

I'm not a meteorologist.

Well, you're a statistical guru, aren't you?
Couldn't you express an educated opinion if you saw the raw data and
the "adjusted" data?

Here is a site run by a statistics wonk.

http://www.climateaudit.org/

Opportunism and the Models
by Steve McIntyre on July 1st, 2009
Many CA readers have probably been checking out some interesting post
at Lucia's about Stefan Rahmstorf's opportunistic smoothing of
temperature observations in Copenhagen.
See here here and here at Lucia's. Also see David Stockwell's recent
post here and his recent E&E paper on Rahmstorf et al (Science 2007)
(Rahmstorf here).
Also see the recent Copenhagen Synthesis Report here.
[Update - Jul 2] David Stockwell had an excellent comment on this
issue in April 2008 here - see Rahmstorf comment at #14 (thanks to
PaulM for drawing this to my attention).

----------------------------------------------------------------
--------------------------------------------------------

Figure 1. Excerpt from Rahmstorf et al 2007. "All trends are nonlinear
trend lines and are computed with an embedding period of 11 years."

Commenters at Lucia's and David's state that Rahmstorf refused to
disclose his smoothing method (which proved ultimately to be a sort of
Mannian smoothing) on the basis that he did not hold the copyright.
Eventually Jean S figured it out and his method was used in David
Stockwell's E&E paper. David has an R-port of the method online (using
an R-package ssa presently unavailable for Windows).

Secondly, Rahmstorf has zeroed both models and observations on 1990. I
recall some controversy about Willis Eschenbach zeroing GISS models on
1958; I have a vague recollection of Hansen's dogs saying that this
was WRONG. I don't vouch for this recollection, but, if the events
were as I vaguely recall, I don't see any material difference in
Rahmstorf's centering here.

In David Stockwell's E&E article, he observed that Rahmstorf's method
applied to updated GISS and CRU resulted in the smooth tapering off.
See the online article for the following image. Obviously the tapering
off diminishes the rhetorical impact considerably.
--------------------------------------------------------------------------

Jean S once again figured this out - Rahmstorf opportunistically
changed the smoothing parameter to one that yielded an image that was
rhetorically more effective and failed to disclose the change in
accounting procedure, falsely reporting that he used the same
parameter as in the prior article. This is what the "Community" calls
"GARP" - Generally Accepted Realclimate Procedure.

I've done a few experiments comparing AR4 A1B models to updated CRU
data. More on this tomorrow. I've done my own port of Rahmstorfian
smoothing to R without using the ssa package - working from first
principles. It uses nothing more complicated than svd and a
quasi-Mannian padding. (Rahmsdorf's "copyright" pretext is absurd BTW.
The Community really has to tell the Team to stop such nonsense.)
---------------------------------------------------------
--------------------------------------------------------

Needless to say, my eyes crossed and my brain glazed over right at
Fig. 1.

Maybe a statistics guru would know exactly what they are talking
about?

Sometimes adjustments are appropriate. For example, the raw measurements
might include a known measurement bias and you'll get better estimates by
making adjustments to compensate for that bias.


And again, some one or group has to make a decision on exactly how to
make the adjustments.

The US census is an example. Every 10 years there's a debate in the
statistics community about whether or not we should do census counts or do
sampling estimates. Sampling estimates actually work better than attempts
to do direct counts. But, the law specifies counts. So we do a census
that we know we could do better with less money by making adjustments to
the raw data.


So then again, we come back to the basic problem of just exactly who
should be doing the adjustments in question.

It shouldn't surprise anyone that as an Associate member of the VRWC,
I don't trust the Census Bureau, with the help of ACORN under
President 0 , to make that adjustment.

You're a World Class Cynic yourself, aren't you?

Can you say that you trust them any more than I do?


The basic point there being that NASA has made "adjustments" to their
data chart over the years, presumably to reflect the more accurate
measurements in later years.
(I say "presumably")

So?


So ditto to the above.


Now, I don't know any more about statistics than I could get from a
"Statistics for Dummies" book, but I think you could probably get
through the wonky dissertations on this site.



http://wattsupwiththat.com/2009/06/28/nasa-giss-adjustments-galore-rewriting-climate-history/#more-8991

Actually, I'm more of a fan of science -- observation, theory, testing,
iterate.

What's your suggesting is more a process of observation followed by
conclusion. That kind of leaves out the science part.


Oh, bullshit.

I suggest that we keep on making more observations and then adjusting
our conclusions based on the latest evidence.

That's not the way science works.


Oh, really?
Science says to disregard the latest data?

I don't think so.


It's the opposite of the GWA's, with the horrible example of AlGore
insisting that all the science is settled, and we must act NOW.

Maybe we should. It's kind of a Pascal's wager sort of analysis.


Funny.

You would surely reject a Pascal's Wager argument about god, yet you
think that maybe we should adopt it about GW.

My Irony Meter gives that an 8/10.
.

Relevant Pages

  • Solutions manuals available
    ... An Introduction for the Engineering, ... Understandable Statistics 7th Ed by Charles Henry Brase, ... Automotive Mathematics ... Science of Electronics, The: Digital (Thomas L. Floyd & David ...
    (sci.physics.accelerators)
  • Re: Howard theory - "cannot be computed"
    ... fairytale stories - not science. ... gap distance is the minimum possible gap distance. ... agreed that your statistics would be valid *if* evolution involved ...
    (talk.origins)
  • Re: Kanye West
    ... science for political reasons) that attitude, ... the mind. ... Scientists are human, with all the ... One can tweak statistics to mask a negative result as maybe positive. ...
    (alt.guitar.bass)
  • Re: Short-lived professions?
    ... statistics predict the occurrence of improbable events, ... Events remain undetermined and the laws of statistics require ... clear", Josh could know... ... Josh's science has sloughed off the concept that some fences may be ...
    (misc.writing)
  • Re: Democrats try to hide anti-global warming report
    ... economics, taught economics, and published in economics journals. ... also done graduate work in statistics and taught statistics. ... noise). ... Sometimes adjustments are appropriate. ...
    (rec.gambling.poker)