Steve McIntyre takes Lewandowsky’s statistical screed to task and writes:
Lewandowsky’s most recent blog post really makes one wonder about the qualifications at the University of West Anglia Western Australia.
Lewandowsky commenced his post as follows:
The science of statistics is all about differentiating signal from noise. This exercise is far from trivial: Although there is enough computing power in today’s laptops to churn out very sophisticated analyses, it is easily overlooked that data analysis is also a cognitive activity.
Numerical skills alone are often insufficient to understand a data set—indeed, number-crunching ability that’s unaccompanied by informed judgment can often do more harm than good.
This fact frequently becomes apparent in the climate arena, where the ability to use pivot tables in Excel or to do a simple linear regressions is often over-interpreted as deep statistical competence.
I mostly agree with this part of Lewandowsky’s comment, though I would not characterize statistics as merely “differentiating signal from noise”. In respect to his comment about regarding the ability to do a linear regression as deep competence, I presume that he was thinking here of his cousin institute, the University of East Anglia (UEA), where, in a Climategate email, Phil Jones was baffled as to how to calculate a linear trend on his own – with or without Excel. At Phil Jones’ UEA, someone who could carry out a linear regression must have seemed like a deity. Perhaps the situation is similar at Lewandowsky’s UWA. However, this is obviously not the case at Climate Audit, where many readers are accomplished and professional statisticians.
Actually, I’d be inclined to take Lewandowsky’s comment even further – adding that the ability to insert data into canned factor analysis or SEM algorithms (without understanding the mathematics of the underlying programs) is often “over-interpreted as deep statistical competence” – here Lewandowsky should look in the mirror.
Lewandowsky continued:
Two related problems and misconceptions appear to be pervasive: first, blog analysts have failed to differentiate between signal and noise, and second, no one who has toyed with our data has thus far exhibited any knowledge of the crucial notion of a latent construct or latent variable.
In today’s post, I’m going to comment on Lewandowsky’s first claim, while disputing his second claim. (Principal components, a frequent topic at this blog, are a form of latent variable analysis. Factor analysis is somewhat different but related algorithm. Anyone familiar with principal components – as many CA readers are by now – can readily grasp the style of algorithm, though not necessarily sharing Lewandowsky’s apparent reification.)
In respect to “signal vs noise”, Lewandowsky continued:
We use the item in our title, viz. that NASA faked the moon landing, for illustration. Several commentators have argued that the title was misleading because if one only considers level X of climate “skepticism” and level Y of moon endorsement, then there were none or only very few data points in that cell in the Excel spreadsheet.
Perhaps.
But that is drilling into the noise and ignoring the signal.
The signal turns out to be there and it is quite unambiguous: computing a Pearson correlation across all data points between the moon-landing item and HIV denial reveals a correlation of -.25. Likewise, for lung cancer, the correlation is -.23. Both are highly significant at p < .0000…0001 (the exact value is 10 -16, which is another way of saying that the probability of those correlations arising by chance is infinitesimally small).
These paragraphs are about as wrongheaded as anything you’ll ever read.
Read the rest here at Lewandowsky’s Fake Correlation
So Lewandowsky took garbage data, applied inept and inappropriate “statistical analysis” and ….. voila! He has a paper for Psychological Science to warm the cockles of every Alarmist heart.
Meanwhile, down under in Lew-Lew Land, he has published NINE stream of consciousness blog articles blasting critics and failing to address the substantive issues.
What a shame, “Professor” Lewandowsky, you are not contributing to understanding (well except by negative example of what not to do). Perhaps such self-immolation of a fervent CAGWarmist is educational somehow….
“Climate science”: you can make things up as you go along.
I almost feel sorry for him…. A Psychologist trying to teach McIntyre about statistics….
The Rule of Holes seems to apply here.
In the same way that I would like to speak a foreign language,but know that I can’t get the hang of it, I find statistical analysis fascinating even though most of it goes straight over my head.
This post highlights a major problem in climate science. We have a team of alarmists who are not expert at statistics but are using statistics to give governments around the world the ammo to demand crazy restrictions on mankind’s commercial activities (CO2 reduction); not to mention Billions upon Billions of tax dollars down the toilet.
Why are they able to get these papers, based upon statistics, published without having a real statistician co-author? Could a Phil Jones type ever be trusted (no matter which side he is on) if we can’t trust his abilities in statistics?
I understand that Climate Science proponents have a tendency to believe in left-wing conspiracy theories like 9/11 was faked by Republicans to jusitfy Gulf War II. Funny, no such question was included by loony Lew.
The science of statistics? Lewandowsky’s “work” has nothing to do with science, but rather the old attempt of using statistics based on very small groups as an evidence for vastly larger groups, which pretty ridiculous and unscientific.
Science and statistics are not synonymous.
Discovery of a numerical discrepancy is not science. Accounting for that discrepancy in a reproducible manner is science.
UWA used to be a very highly regarded institution once, but as with nearly all others, ideology has probably trumped education. I wasted a year there in the ’60s, but that was my fault …
Lol. The trick-cyclist is going to ‘teach’ Steve McIntyre how to do stats.
I think someone has fed Lewandowsky with some BIG statistics words which he thinks he can use to baffle the rest of the world with,
As they say “A little knowledge is dangerous”.
After Steve has finished with him I would like to see what Mr William Briggs has to say about Lewandowsky’s effort.
Maybe Lewandowski is just trying out his newly found speciality as an Morphologist.
The problem is not insufficient “statistical competence”. EVERY use of statistics is an attempt to compensate for lack of data, and expert use of stats is more dangerous than amateur.
If you’re dealing with an actual natural phenomenon, you need to analyze it with actual measurements and (where possible) an actual experiment. Statistics are an admission of failure.
Prof Lewandowsky complains that there has been little discussion of the concept of latent constructs. Plenty of description on the Net about what they are. In one invented example, using a collection of observations to suggest a factor-in-common, like using measured observations such as wealth, happiness in marriage, abundance of food, smiling often, giving gifts … all lumped together into a ‘quality of life’ which makes the stats analysis less cumbersome.
Our first child started to bring home kindergarten finger paintings that were painted all in black. We researched the possible deep significance of this as a latent construct, found lots of psychological reasons to be worried. At the appointment with the Kindergarten Head, we were promptly told that the kindy had run out of all paint colours except black.
The latent construct, used badly, can lead up a garden path.
Psychologists are some of the most sophisticated statisticians in academia. Lewandowsky can do the sums correctly, but poses the wrong questions. He proves nothing, it is shallow. It is clear to me that he assumes all of his nominated questionaire “conspiracies” (and perhaps we need to examine what he means by that term) are false and irrational by definition and takes off from there. Wouldn’t it be prudent to provide some weighting to the relative craziness of each conspiracy in the questioniare when doing the stats? The fact is, every now and then hidden conspiracies are exposed; for example I believe the Iran-Contra affair is no longer a theory but clearly was a deliberately hidden conspiracy. Perhaps even the most fundamental question, why try to even look for an association between climate science scepticism and conspiracy theories. Does he assume that all sceptics think there is some sort of conspiracy going on? He’s sounding like the conspiracy theorist to me, all those bad sceptics are banding together in secret and doing bad things.
“If your experiment needs statistics, you ought to have designed a better experiment”
— Ernest Rutherford
Hi Anthony. Have just read some puerile tweets from so called US “journalists” abusing you and your site. All I can say is take heart, you have major support out here for your work. You may like to know that our family (which includes a paleontologist, a marine biologist, a statistician and a chef) all look forward to reading the articles and discussing their various merits.You do a fantastic job to pull it all together so professionally.Cheers and best wishes from Oz. We think you are wonderful.
This is the first time I have looked at a blog post by Lewandowsky and Oberauer, and so I don’t know if any one else has made the comment, But what on earth is Lewandowsky doing in creating a post on what he perceives to be a Sceptic V “Realist” attitude to interpreting time series data in a discussion which is supposed to be about detecting the signal from noisy data? His selection of what he perceives as sceptics traits in interpreting graphical data surely demonstrates his highly negative attitude to sceptics and therefore his professional unsuitability in producing and interpreting sceptics attitudes to climate science and moon landings. Coupled with his clear associations with Cooke and “Sceptical Science,” this should bring into grave doubt any conclusions that might have been gained from his survey results and in an honest world withdrawal should have been automatic.
” data analysis is also a cognitive activity”. & “informed judgment” are code words for “what ever I want the data to show, is what the data shows.”
The sad state of climate scientists today [major facepalm].
markstoval says:
September 19, 2012 at 2:45 am
This post highlights a major problem in climate science. We have a team of alarmists who are not expert at statistics but are using statistics to give governments around the world the ammo to demand crazy restrictions on mankind’s commercial activities (CO2 reduction); not to mention Billions upon Billions of tax dollars down the toilet.
Why are they able to get these papers, based upon statistics, published without having a real statistician co-author?
__________
Because the “peers” who review the papers do not understand statistics either. Moreover, a “if it bleeeds (CAGW) it leads” mentality seems to be pervasive amongst Journal editors.
This is a good example of politically motivated “subjective research (post modern science)” at it’s worst. I advise “true believers” to maintain some distance or go down the drain with him.
Lews notes to self: 1.Work on understanding Stastics.
2. Work on Acting.
#, Use less starch.
Yikes
Psychology is to science as Alchemy is to Chemistry.
But it employs a lot of people who otherwise would be only qualified to ask folks if they would like fries with their order.
At least Lew has a fall back career.
I agree with “mem”. Lew’s pomposity is off-the-scale .
OMG
Why go to all that statistical bother when the truth can be had by reading WUWT? I say, WUWT?