Buy

Books
Click images for more details

Support

 

Twitter
Recent comments
Recent posts
Currently discussing
Links

A few sites I've stumbled across recently....

Powered by Squarespace

Discussion > Merry Christmas, Mr Steyn

Wegman's statistics couldn't be faulted so he was trashed over an irrelevancy. C'mon, Phil, be irrelevant.
===========

Dec 23, 2016 at 6:10 PM | Unregistered Commenterkim

That was the true position of the NAS and NSF. They admitted the method was wrong, but said the answer was correct anyway,

Nope, they admitted there were flaws, no study of this size and groundbreaking nature could ever be perfect, but even correcting the flaws did not change the conclusions. To quote Prof Bloomfield (again)

while the issues are real, they had a very minimal effect, not a material effect on the final reconstruction.

Dec 23, 2016 at 6:38 PM | Unregistered CommenterPhil Clarke

Well, Kim, Ritson identified problems with the 'red noise' Wegman used, it had an unrealistic level of autocorrelation, but Wegman never responded (or provided code or data).

But, disregarding the fact that 35 of the 91 pages were mostly plagiarized text, some copy-pasted straight from wikipedia, the point about Wegman is that the flaws he identified, far from proving MBH a crock, as asserted above, actually had no consequential effect on the study conclusions.

Dec 23, 2016 at 6:48 PM | Unregistered CommenterPhil Clarke

Hah, you're such a predictable tool, Phil. Live by the straight shaft, die by the straight shaft.
=================

Dec 23, 2016 at 6:59 PM | Unregistered Commenterkim

GC. They supported Wegman's conclusions at the Senate hearings, probably because there was a chance they would be called to account by the senate should they have been proved not telling the truth. Also there was considerable support for Wegman's conclusions in the statistics world. Tamino cited support from Ian Jolliffe for Mann's methods.

Ian Jollliffe.

"He gained his PhD in Statistics in 1970, and has been an active teacher and researcher in Applied Statistics since then. His thesis was on variable selection in principal component analysis (PCA), and topics related to PCA have formed a substantial strand of his research throughout his career. The second edition of his book "Principal Component Analysis" published in 2002, is probably the most comprehensive text on the subject and has more than 20000 citations."

His response is below (not the full version)

Apologies if this is not the correct place to make these comments. I am a complete newcomer to this largely anonymous mode of communication. I’d be grateful if my comments could be displayed wherever it is appropriate for them to appear.
It has recently come to my notice that on the following website, http://tamino.wordpress.com/2008/03/06/pca-part-4-non-centered-hockey-sticks/ .. , my views have been misrepresented, and I would therefore like to correct any wrong impression that has been given.

An apology from the person who wrote the page would be nice.

In reacting to Wegman’s criticism of ‘decentred’ PCA, the author says that Wegman is ‘just plain wrong’ and goes on to say ‘You shouldn’t just take my word for it, but you *should* take the word of Ian Jolliffe, one of the world’s foremost experts on PCA, author of a seminal book on the subject. He takes an interesting look at the centering issue in this presentation.’

It is flattering to be recognised as a world expert, and I’d like to think that the final sentence is true, though only ‘toy’ examples were given. However there is a strong implication that I have endorsed ‘decentred PCA’. This is ‘just plain wrong’.

...

It certainly does not endorse decentred PCA. Indeed I had not understood what MBH had done until a few months ago.

...

I can’t claim to have read more than a tiny fraction of the vast amount written on the controversy surrounding decentred PCA (life is too short), but from what I’ve seen, this quote is entirely appropriate for that technique. There are an awful lot of red herrings, and a fair amount of bluster, out there in the discussion I’ve seen, but my main concern is that I don’t know how to interpret the results when such a strange centring is used? Does anyone? What are you optimising? A peculiar mixture of means and variances? An argument I’ve seen is that the standard PCA and decentred PCA are simply different ways of describing/decomposing the data, so decentring is OK. But equally, if both are OK, why be perverse and choose the technique whose results are hard to interpret? Of course, given that the data appear to be non-stationary, it’s arguable whether you should be using any type of PCA.

I am by no means a climate change denier. My strong impressive is that the evidence rests on much much more than the hockey stick. It therefore seems crazy that the MBH hockey stick has been given such prominence and that a group of influential climate scientists have doggedly defended a piece of dubious statistics.? Misrepresenting the views of an independent scientist does little for their case either. It gives ammunition to those who wish to discredit climate change research more generally. It is possible that there are good reasons for decentred PCA to be the technique of choice for some types of analyses and that it has some virtues that I have so far failed to grasp, but I remain sceptical.

Ian Jolliffe

Of course, if Professor Jolliffe had know he'd be coming up against Phil Clarke he may have moderated his language.

Dec 23, 2016 at 7:02 PM | Unregistered Commentergeronimo

Phil will be along to quote Jolliffe's bow to CAGW.
============

Dec 23, 2016 at 7:06 PM | Unregistered Commenterkim

Oops, g has it already.
===============

Dec 23, 2016 at 7:07 PM | Unregistered Commenterkim

Fortunately, g has the quote in the context, which damns the Hockey Stick. Jolliffe exposes his ignorance of the climate debate, but inadvertently reveals the fatal flaw in the strategy of dependence of the cause upon the Piltdown Mann's Crook't Stick. The evidence of natural variability has been suppressed, fuzzing the question of attribution of warming, laying waste to his 'much, much more' evidence.
====================

Dec 23, 2016 at 7:22 PM | Unregistered Commenterkim

Phil Clarke at 4.27pm.

Sadly you once more demonstrate the fallibility of my memory. I concede the point.

But can you explain Mann's apparent reluctance to make disclosure in any of the cases he commences? If I were a plaintiff confident in my case and claiming substantial damages, I would wish to get to trial quickly, be vindicated and collect my damages and costs. Libel cases are time-consuming, wearing and expensive. To drag them out any longer than necessary seems odd. Why not crack on with them?

We can only speculate as to the reasons for the delays and such speculation might be wrong. One explanation might be a lack of confidence regarding the outcome of a trial. Another might be that it's useful to issue proceedings to cow potential opponents, especially if you enjoy sources of funding not available to your opponents.

https://climatesciencedefensefund.org/about/

"Climate scientists have been harassed for more than 25 years. For most of those, we’ve been on our own to handle the problem. The Climate Science Legal Defense Fund is key to making sure we can focus on our science, and not the harassment.” — Dr. Michael Mann, Penn State

"We were established with one goal: to protect the scientific endeavor. Legal actions against scientists are also attacks on the scientific endeavor as a whole, which slow or prevent critical advancements in technology, medicine, and our understanding of the planet.

"The Climate Science Legal Defense Fund (CSLDF) works to defend climate scientists who are dragged into litigation or otherwise threatened with legal attacks and harassment by politically and ideologically motivated groups.

"We also work to educate members of the scientific community, helping them gain a better understanding of the legal issues surrounding their work, and to educate the public about the legal issues facing climate scientists."

Oh the irony!

Dec 23, 2016 at 8:05 PM | Unregistered CommenterMark Hodgson

But can you explain Mann's apparent reluctance to make disclosure in any of the cases he commences?

Given that I am unaware of any such case, nope. Examples?

Dec 23, 2016 at 8:24 PM | Unregistered CommenterPhil Clarke

While Phil's scouring alarmist cites for rebuttals of the actual words in the hearing and from Jolliffe let's consider this.

You have to ask how a seminal work like MBH1998 could be accepted to have flaws yet it's conclusions be true by the scientific community. There wasn't a plethora of papers out there agreeing with its conclusion that there hadn't been a MWP. So how did NAS, and NSF draw the conclusion that there were flaws, but the answer was correct? Nothing they said proffered any other evidence, just that the method might have been wrong, but the conclusions were correct, and so turned a 100% consensus that there was a MWP into a 97% (phony of course) acceptance that humans had caused warming in the 20th century?

Dec 23, 2016 at 8:25 PM | Unregistered Commentergeronimo

Phil - the cases against Ball and Steyn, of course.

Dec 23, 2016 at 8:30 PM | Unregistered CommenterMark Hodgson

Mark, I have no special knowledge of Dr Mann's motivations, nor any burning desire to speculate.

Dec 23, 2016 at 9:30 PM | Unregistered CommenterPhil Clarke

There wasn't a plethora of papers out there agreeing with its conclusion that there hadn't been a MWP. So how did NAS, and NSF draw the conclusion that there were flaws, but the answer was correct? Nothing they said proffered any other evidence,

Geronimo, I can only suggest that you actually read the report before attempting inaccurate paraphrasing. Just look at Figure 1. Here's the caption

Smoothed reconstructions of large-scale (Northern Hemisphere mean or global mean) surface temperature variations from six different research teams are shown along with the instrumental record of global mean surface temperature. Each curve portrays a somewhat different history of temperature variations and is subject to a somewhat different set of uncertainties that generally increase going backward in time (as indicated by the gray shading). This set of reconstructions conveys a qualitatively consistent picture of temperature changes over the last 1,100 years and especially over the last 400

Dec 23, 2016 at 9:51 PM | Unregistered CommenterPhil Clarke

geronimo - thank you. Luckily Ian Joliffe was very polite and didn't just write bollox in big letters over Mann's masterpiece of careful statistical selection.

Phil Clarke, so you have no idea why Mann should fail to produce documentation that he has been asked for, which could have resolved this matter in his favour 3 (?) years ago, if it proved him to be a knight in shining armour, boldly riding to slay dragons that no climate scientist had ever managed to slay before?

I wonder why you don't want to speculate on his motives. I am sure 97% of Climate Scientists, now facing redundancy before next Christmas would love Mann to save their jobs, but they must be losing faith in Mann and the robust nature of his Stick's fabrication.

Dec 23, 2016 at 10:09 PM | Unregistered Commentergolf charlie

"Geronimo, I can only suggest that you actually read the report before attempting inaccurate paraphrasing."

Which report? I have been careful to provide verbatim statements from the scientists in question, to my knowledge I haven't paraphrased anybody.

Let's re-iterate what we have so far:

1. Wegman, an expert in statistical analysis, says that Mann's Hockey stick was achieved by applying an unknown technique of statistical analysis and that it is seriously flawed.

2. North and Bloomberg agree with Wegman's analysis but say that it doesn't matter because Mann's conclusions were correct, without providing a single piece of corroborative evidence - because there isn't any.

3. Tamino says that Jolliffe - probably the world expert in PCA analysis disagrees with Wegman.

4. Jolliffe unequivocally says that he does agree with Wegman (Along with North and Bloomberg) and says he doesn't understand how any signal can be understood by using PCA de-centering.

Have I missed something? The entire body of opinion is that Mann used a technique that couldn't possibly get a signal from the data using his statistical techniques, but two of the them say, without a scintilla of evidence, that it doesn't matter because the result is correct?

What paraphrasing are you talking about?

Dec 23, 2016 at 11:14 PM | Unregistered Commentergeronimo

geronimo, meanwhile, the honesty, integrity and independence of NAS has been brought into question, along with many other, allegedly respected professional bodies.

https://wattsupwiththat.com/2016/12/23/the-command-control-center-of-climate-alarmism/

Grant Foster, aka Tamino, has always supported Mann and the Hockey Teamsters.

Looking at the number of financial donors involved, the letters RICO spring to mind.

Dec 23, 2016 at 11:56 PM | Unregistered Commentergolf charlie

Heh, gc, re: bollix. Here's a small self serving anecdote, but I can't resist. When Tamino first posted claiming that Jolliffe supported Mann, JeanS, over @ StevieMac's wrote 'Garbage.' I immediately ran over to Tamino's and posted 'Garbage'. Tamino took that as evidence that there was conspiracy and collusion amongst the skeptics. Someone had to point out to the poor man that all I'd done was spot JeanS's comment.

I wish that post and comment stream were still available. As through a glass darkly, heh.
==================

Dec 23, 2016 at 11:57 PM | Unregistered Commenterkim

Which report?

This one Surface Temperature Reconstructions for the Last 2,000 Years

Compiled by the NRC and published by NAS. When you mentioned NAS and NRF I naturally assumed you knew what you were talking about. My mistake.

Let's re-iterate what we have so far:
1. Wegman, an expert in statistical analysis, says that Mann's Hockey stick was achieved by applying an unknown technique of statistical analysis and that it is seriously flawed.

Utter, utter bollocks. Wegman found fault with some of the methodological choices, however,  even if Mann et al had consulted Wegman and his colleagues on PC centering conventions at the time, the difference in the outcome would have been nil.

North and Bloomberg agree with Wegman's analysis but say that it doesn't matter because Mann's conclusions were correct, without providing a single piece of corroborative evidence - because there isn't any.

Oh, FFS. Just read the report.

Jolliffe unequivocally says that he does agree with Wegman (Along with North and Bloomberg) and says he doesn't understand how any signal can be understood by using PCA de-centering.

It has been demonstrated, many times over, that PCA de-centering had an insignificant impact on the conclusions. You get the same answer with centered PCA, and with no PCA.

Dec 23, 2016 at 11:57 PM | Unregistered CommenterPhil Clarke

er, 'bollux'. Gee, these Anglicisms can be tough, but oh, how delightful.

Here's Lowell in 'A Fable for Critics', 1848:

"You steal Englishmen's books and think Englishmen's thoughts;
With their salt on your tail your wild eagle is caught;
Your literature suits its each whisper and motion
To what will be thought of it over the ocean."

H/t Mencken, who else?
========

Dec 24, 2016 at 12:08 AM | Unregistered Commenterkim

Heh, 'bollocks', pronounced 'bullshit'.
==========

Dec 24, 2016 at 12:11 AM | Unregistered Commenterkim

It has been demonstrated, many times over, that PCA de-centering had an insignificant impact on the conclusions. You get the same answer with centered PCA, and with no PCA.

Dec 23, 2016 at 11:57 PM | Phil Clarke

Phil Clarke, was it demonstrated as many times as Gergis et al, and all the others confirmed the Hockey Stick?

What percentage of the 97% of Climate Scientists have given up on Mann's Hockey Stick, and just want to "move on from the Hockeystick", and do all of the remainder, including yourself, still believe the Hockey Stick is worth saving?

Is there to be a revised Consensus, fabricated to confirm the percentage of the 97%, that believe there is still a 97% Consensus, and how the science was settled, before the Hockey Stick, and maintained thereafter? Or should Climate Science try to stick with evidence that will stand up in court, unlike Mann's, which needs to be kept out of court, and the public's eye, at total cost to the livelihoods of 97% of Climate Scientists?

Dec 24, 2016 at 1:30 AM | Unregistered Commentergolf charlie

The climatocracy should be careful about what they wish for.

Dec 24, 2016 at 4:41 AM | Unregistered Commenterhunter

Gloating is not one of my better human emotions, but sometimes, well, you know...
From The Climate Change Election
The 2016 presidential election may be America's last chance to elect a leader who will halt climate change.

"This will be a make-or-break presidency as far as our ability to avert a climate change catastrophe," says Michael Mann, meteorology professor and director of the Earth System Science Center at Penn State University

[...]
"If we are going to avoid catastrophic, irreversible climate change impacts, we have to be ramping down our carbon emissions dramatically in the years ahead. The current administration has begun that process, but our next president must not only continue but build on that progress," Mann says.

Now what makes me think we are going to offered yet more "last chances" in 2017?

Oh! How I yearn for the merciful release of the year when we will be finally spared another opportunity to dramatically ramp down one more final last chance ever to save the planet before it is finally catastrophically irreversibly too late ever.

Dec 24, 2016 at 4:53 AM | Unregistered Commentermichael hart

"It has been demonstrated, many times over, that PCA de-centering had an insignificant impact on the conclusions. You get the same answer with centered PCA, and with no PCA."

Professor Jolliffe addressed this canard, if the above is true then why use the methodology that has unknown.

"An argument I’ve seen is that the standard PCA and decentred PCA are simply different ways of describing/decomposing the data, so decentring is OK. But equally, if both are OK, why be perverse and choose the technique whose results are hard to interpret?"

Dec 24, 2016 at 6:06 AM | Unregistered Commentergeronimo