Conspiracy-Theorist Lewandowsky Tries to Manufacture Doubt
By Steve McIntyre
As CA readers are aware, Stephan Lewandowsky of the University of Western Australia recently published an article relying on fraudulent responses at stridently anti-skeptic blogs to yield fake results.
In addition, it turns out that Lewandowsky misrepresented explained variances from principal components as explained variances from factor analysis, a very minor peccadillo in comparison. In a recent post, I observed inconsistencies resulting from this misdescription, but was then unable to diagnose precisely what Lewandowsky had done. In today’s post, I’ll establish this point.
Rather than conceding the problems of his reliance on fake/fraudulent data and thanking his critics for enabling him to withdraw the paper, Lewandowsky has instead doubled down by not merely pressing forward with publication of results relying on fake data, but attempting to “manufacture doubt” about the validity of criticisms, including his most recent diatribe – to which I respond today.
In a post several days ago, I temporarily considered other issues in the Lewandowsky article beyond the reliance on fake responses, reporting on my then progress in trying to replicate results – not easy since his article omitted relevant methodological information. Separate from this, Roman Mureika and I (but especially Roman) have made further progress in trying to replicate the SEM steps – more on this later.
I reported a puzzle about explained variance results as reported in Lewandowsky’s article – results that could not be replicated using a standard factor analysis algorithm. Roman Mureika also tried to figure out the discrepancy without success. I pointed out that Lewandowsky’s factor analysis did not seem to have much effect on the downstream results where the real problems lay.
The reason why we were unable to replicate Lewandowsky’s explained variance from factor analysis was that his explained variance results were not from factor analysis, but from the different (though related) technique of principal components, a technique very familiar to CA readers.
The clue to reverse engineering this particular Lewandowsky misrepresentation came from a passim comment in Lewandowsky’s blog in which he stated:
Applied to the five “climate science” items, the first factor had an eigenvalue of 4.3, representing 86% of the variance. The second factor had an eigenvalue of only .30, representing a mere 6% of the variance. Factors are ordered by their eigenvalues, so all further factors represent even less variance.
Eigenvalues are a term that arise from singular value (“eigen”) decomposition SVD. As an experiment, I did a simple SVD of the correlation matrix – the first step in principal components, a technique used in principal components and was immediately able to replicate this and other Lewandowsky results, as detailed below. Lewandowsky’s explained variance did not come from the factors arising from factor analysis, but from the eigenvectors arising from principal components. No wonder that we couldn’t replicate his explained variances.
But instead of conceding these results, Lewandowsky fabricated an issue regarding the number of retained eigenvectors in this analysis, a point that I had not taken issue and which did not affect the criticism, as I’ll detail.
Please read the rest here: Conspiracy-Theorist Lewandowsky Tries to Manufacture Doubt
As a side show note, here’s a window into the mind of Professor Lewandowsky:
Discover more from Watts Up With That?
Subscribe to get the latest posts sent to your email.
Ray Campbell says:
September 21, 2012 at 9:03 am
You, Sir are an absolute wanker with no clue whatsoever. Give up science and consider a career in comedy.
——————————————-
Destined to failure also.
Being a joke != Delivering a joke
I was relieved when I noticed he had an American accent – so he’s not one of ours 🙂
Lew’s sewer science
eugene wr gallun
I do not find it surprising that belief in free markets and climate skepticism are correlated. Both are conservative causes in general, in that those of us who wish all loose ends tied up before changing fundamental beliefs find both causes desirable. That does not mean these causes are any more connected than that though.
The psychology profession is notorious for being practised by persons with deep psychological problems, and this man falls into that category. Pot Kettle. He appears to be projecting his own paranoia onto those he opposes. He is hardly a climate scientist himself, so his opinion counts no more than any layman’s.
A real climate scientist convinced of the reality of AGW would welcome skepticism as a golden opportunity to present the arguments and measurements that have moved them to that position. In general they do not, which tends to reinforce the view that they are merely implementing a political agenda or protecting their career.
“A real climate scientist convinced of the reality of AGW would welcome skepticism as a golden opportunity to present the arguments and measurements that have moved them to that position.”
They do now (e.g. Dr Richard Betts) and used to still more but, even though it can be a fun game, whack-a-mole gets a bit tedious after a while.
Increasingly progressives are just making stuff up to get what they want. This is why we can no longer afford to vote Democrat.
jorgekafkazar says
“”Colin Porter says: “…We can now all spell the real name “Lewandowsky,” that is every body except spell checker, which continues to treat his name with disdain.”
It’s easy to check. If you can rearrange the letters to spell phantasy slewed wonk, you’ve got it right.””
Excellent. I could never have thought of an anagram like that, even though you have used artistic license with your spelling. Perhaps you or others could conjure up more terms of endearment from anagrams of our favourite climate scientists.
OK, I watched the video. The fool is dead set nuts and in desperate need of a spell in the padded little white room.
Tried to get to Jo Nova’s site through Climate Depot. Account Suspended?
“his explained variance results were not from factor analysis, but from the different (though related) technique of principal components”
PCA is a special case of factor analysis (actually the simplest case), so the statement clumsily reveals ignorance that needs to be corrected.
Cautionary note for lay readers:
A commenter named “James Lane” has made false & misleading statements on the parallel Climate Audit thread.
Sloppy thinking on multivariate methods is hopelessly widespread, including in academia. If results based on multivariate methods are important to me for some purpose, I trust no one and need to run a LOT of CAREFUL diagnostics independently (starting with a basic scatterplot matrix, a step which should never be skipped).
The following may provide Steve McIntyre opportunity for at least a somewhat graceful exit from deeply incisive (and absolutely correct) comments of “faustusnotes” on the issue of factor matrix rotation:
http://support.sas.com/documentation/cdl/en/statug/63347/HTML/default/viewer.htm#statug_factor_sect002.htm
=
“A frequent source of confusion in the field of factor analysis is the term factor. It sometimes refers to a hypothetical, unobservable variable, as in the phrase common factor. In this sense, factor analysis must be distinguished from component analysis since a component is an observable linear combination. Factor is also used in the sense of matrix factor, in that one matrix is a factor of a second matrix if the first matrix multiplied by its transpose equals the second matrix. In this sense, factor analysis refers to all methods of data analysis that use matrix factors, including component analysis and common factor analysis.”
=
Anagram Genius rearranged “Stephan Lewandowsky” as “wonky deathless pawn”, i..e. a wonky zombie. Score!
Can you guys in the USA please send a team down here and take this mad man back. Australia is a nice place. We don’t need nutters like this guy. What a whack-job …
SunderlandSteve says:
September 21, 2012 at 8:42 am
I hereby give permission to Anthony to give my e-mail to you.
We are between 6 & 10 miles apart..
DaveE.
David A. Evans says:
September 23, 2012 at 4:23 pm
????