Buy

Books
Click images for more details

Support

 

Twitter
Recent comments
Recent posts
Currently discussing
  • Jun 23 - Mark Hodgson on
    COP 23
  • Jun 22 - Mark Hodgson on
    COP 23
Links

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

Powered by Squarespace
« Diary dates, sea ice edition | Main | Quote of the day, hidden truths edition »
Friday
Mar272015

Lew paper shredded

BH regulars Jonathan Jones and Ruth Dixon have published a much-needed response to Lewandowsky's "Conspiracist Ideation" paper. Appearing in the journal Psychological Science, their study seems to lay to rest the idea that the Lew paper was anything other than a smear-job.

This analysis highlights the fact that a skewed sample can easily mask a nonlinear relationship and lead to serious misinterpretation of modeled relationships (Berk, 1983; Groves, 2006; MacCallum & Mar, 1995). Techniques such as SEM should not be used as a “black box” without thorough initial exploration of the data set to check for nonlinearities (Bentler & Chou, 1987; Cumming, 2014). The curvilinear relationship identified in both the panel-survey data of Lewandowsky, Gignac, and Oberauer (2013) and the blogs-survey data of Lewandowsky, Oberauer, and Gignac (2013) suggests that both respondents convinced of anthropogenic climate change and respondents skeptical about such change were less likely to accept conspiracy theories than were those who were less decided about climate change.

There is an accompanying blog post by Jonathan and Ruth here, which alludes to the long and painful process of getting the paper published as well as linking to Lew's response. It also contains this summary of the Lew paper:

All the data really shows is that people who have no opinion about one fairly technical matter (conspiracy theories) also have no opinion about another fairly technical matter (climate change). Complex models mask this obvious (and trivial) finding.

PrintView Printer Friendly Version

Reader Comments (26)

Dr. Lewandowsky posted About this at the Shaping Tomirrow's World blog. While he claims to appreciate the critique of LOG13 in a peer reviewed forum he forgot to provide a link to the Dixon-Jones commentary. We know he is familiar with links. No less than four links to his own papers are embedded in the post.

http://www.shapingtomorrowsworld.org/lewandowskydj.html

Mar 27, 2015 at 9:44 AM | Unregistered CommenterDGH

Complex models mask this obvious (and trivial) finding.
In fact, Ruth's blog also says
The complex statistical models used by Lewandowsky et al. mask this rather obvious and uninteresting finding
A much more damning comment, in my opinion. I can't imagine someone like Lewandowsky being pleased with a suggestion that anything he does could possibly be uninteresting!

Mar 27, 2015 at 10:04 AM | Registered CommenterMike Jackson

Excellent! Well done all concerned.

I wrote when Lew’s paper came out that his percentages of sceptics believing in conspiracies were lower than in the surveys done on the general public, even including the suspect responses.

An area that Lew didn’t address was the type of conspiracy different people respond to. If you choose a selection of conspiracies that might trigger more on one political side than the other you’d end up with a skewed result. As it was, Lew’s results were so poor that there was almost no signal but it’s worth watching for if Lew tries again.

There will be much gnashing of warmist teeth over this.

Mar 27, 2015 at 10:12 AM | Unregistered CommenterTinyCO2

Sorry but like Cook's work recently covered the mistake is to think that becasue you proved it factual wrong you won .
When in pratice it is simply not a factual argument in the first place. Lew's paper was effective in the way it needed to be , headlines , its actual 'quality' did not matter then and does not matter now .
Its actual one of the signs of climate 'science' dogma that what gets in has little if anything to do with scientific validity , honest or good data . Therefore you cannot take it out by arguing on those grounds.

Mar 27, 2015 at 10:43 AM | Unregistered Commenterknr

a smear job..but this guy is paid from the tax purse supposedly providing good value for money to Sainsbury cashiers who earn a tenth of what he does, right ??

Mar 27, 2015 at 10:49 AM | Unregistered CommenterVenuNotWarmerDueToCO2

All the data really shows is that people who have no opinion about one fairly technical matter (conspiracy theories) also have no opinion about another fairly technical matter (climate change). Complex models mask this obvious (and trivial) finding.

Well, that's one explanation of the bell curve. But here's another.

1) In the US (which was surveyed) there is a political bias towards scepticism on the right and alarmism on the left.
2) Right-wingers believe in right-wing conspiracy theories - Common Purpose, for instance - and disbelieve in left-wing conspiracy theories.
3) Left-wingers believe in left-wing conspiracies - Big Oil, for instance - and disbelieve in right-wing conspiracy theories.
4) Those in the middle don't trust anything and so believe in both sorts of conspiracy theories.
5) That makes a bell curve.

This is testable by comparing these results from the USA with results from Europe where the AGW meme is not rejected so strongly by right-wing parties.

Mar 27, 2015 at 11:01 AM | Registered CommenterM Courtney

Ex Conservative Defence Secretary Micheal Portillo was on BBC 4 last night visiting the National Archive and reading from various MOD Declassified Documents and witness statements referring to UFO sightings.

These Alien Explorers are keeping a very low profile and obviously don,t wish to cause widespread alarm and only seem to park their starships in corn fields rather than drop in on Hyde Park and grab a coffee in Starbucks.

Suppose Stephan Lewandowsky can always apply for a research grant to study the psychology of UFO enthusiasts but at least they get access on the BBC.
Even "Lew Paper" doubt the existence of "Klingons".

Referring to those who doubt the motives of light year hopping Extraterrestrials come to survey our humble civilization well no one refers to those puny humans as UFO Deniers.

PS

Talking of Official Secrets and D Notices Its nearly 30 years since Kyoto and the Thatcher UN speech.
Bish have you or the GWPF been out to Kew Bridge and looked through released historic documents casting early Civil Service doubt on what was then called Global Warming.

Mar 27, 2015 at 11:02 AM | Unregistered Commenterjamspid

Alternative models should reflect alternative theoretically motivated hypotheses, any mention of which is conspicuously lacking in in Dixon and Jones’s Commentary

This is so unbelievably wrong that it's just amazing to see it written down. That's precisely what is so good about the DJ paper - it just presents facts, and allows anyone to see the significance, without asserting as the Greate Lew does that he knows exactly what it all means!

Mar 27, 2015 at 11:08 AM | Registered Commentersteve ta

This idea of "conspiracy" is patently a straw man.

The simple reality is that, like any other organisation, government is first and foremost concerned with its own well-being. Which in this case means funding a climate science with a built-in alarmist bias, since alarmism provides such a handy excuse for govenment to expand itself.

Lewandowsy's "conspiracy" theorists are just ordinary people who decline to bury their heads in the sand about the vested interest of government at work here.

Mar 27, 2015 at 11:22 AM | Unregistered CommenterTuppence

I'll post it here, as Shaping tomorrows World, no longer automatically publishes my comments:

One of the concerns with respect to the original paper - was the title

- NASA faked the moon landing therefore [climate] science is a hoax -

This was considered provocative and inappropriate by many(including Tom Curtis of Skeptical Science) as it was based on 3 respondents to the survey of climate blogs...

0.26% of respondents.

of the non 'climate sceptic' respondents to the survey, there were 6 that believed in the moon hoax, equating to:

0.52% of respondents:

therefore as 99% of respondents did not believe in the headline conspiracy..This title seems very irresponsible, leading to dramatic headlines in the media...


Guardaian: Are climate sceptics more likely to be conspiracy theorists?


Guardian: New research finds that sceptics also tend to support conspiracy theories such as the moon landing being faked.


which then resulted in a lot of attention being drawn to this paper, and some anger when it was based on three anonymous people, (who may or may not be minors, age has been redacted form the data - and minors WERE included in both LOG13 and the PLOS one paper - in the PLOS One paper 2 14 year olds believed in the moon hoax in the survey of the general public, yet age has been redacted from the LOG13 data.

The percentages on both the survey of the general public and the climate blogs showed the conspiracies were believed in tiny numbers, but there were higher percentages on the survey of the general public, than the surveys of the climate blogs..

which would show that climate blog readers (sceptical, non sceptical) were LESS likely to believe in conspiracies than the USA general public.

Will you now release the dataset with the ages unredacted for LOG13, as age IS included in the PLOS One paper of the general public (5 minors were included, and a ~32,000 year old man

Mar 27, 2015 at 11:28 AM | Unregistered CommenterBarry Woods

Can somebody please give me the name of a climate sceptic who believes the moon landing was faked?

Thought not.

Mar 27, 2015 at 11:37 AM | Unregistered CommenterLatimer Alder

Firstly, I am sure Dixon and Jones know this - the LOG12/13 blogs data is fake/suspect. This can shown in many different ways. I wrote about it on WUWT here: Lewandowsky et al 2013: surveying Peter to report on Paul. Asking for LOG12's data is what let to the 'Recursive Fury' paper and its subsequent retraction.

That you can take noisy data like LOG's and prove any association was shown by Brandon Shollenberger. I believe he wrote on WUWT and other locations about it.

Third, while Lew benefited from his journalist and climate-activist network selling his paper/s far and wide, the editor bought Lewandowsky a measure of protection in embargoing the response. This, with the refusal to release the LOG12 raw data, are black marks on the reputation of the journal.

Mar 27, 2015 at 11:38 AM | Registered Commentershub

Lewandowsky added the links. As he notes in the comments at his blog the DOI on Dixon-Jones is not working.

Mar 27, 2015 at 11:49 AM | Unregistered CommenterDGH

Can somebody please give me the name of a climate sceptic who believes the moon landing was faked?
Thought not.
Mar 27, 2015 at 11:37 AM | Unregistered Commenter Latimer Alder

Latimer, I can't think of any climate sceptic who thinks the moon landings were faked, but I can think of a famous one who rightly took offence at the suggestion: https://www.youtube.com/watch?v=wptn5RE2I-k#t=1m20s.

Mar 27, 2015 at 12:09 PM | Registered Commenterlapogus

Shub - see this tweet from Jonathan:

Lewandowsky's climate conspiracy papers are wrong in oh so many ways, but see https://mygardenpond.wordpress.com/2015/03/26/commentary-in-psychological-science/#more-935 … by me and @ruth_dixon for one example

So yes, there are lots of problems with it - they didn't make any serious effort to get sceptic input, they didn't (as claimed) post the survey at sks, some of the responses are probably fakes (giving the researcher the answer he wants) and so on. The question is, what is the best way to get a comment accepted and published. They decided, and clearly it worked, to drop those points and just focus on the fact that the LOG data simply doesn't support the claims. Jose Duarte has a similar focus at his blog.

Steve Mc has just written a short post, making much the same point ("numerous other defects with the Lewandowsky article that are not covered in their comment")

Mar 27, 2015 at 12:35 PM | Registered CommenterPaul Matthews

Latimer Alder / lapogus
Interesting comment under that youtube clip: since the Soviets had the capability to (and almost certainly did) track the Apollos all the way there and all the way back, it is beyond belief that they wouldn't have blown the whistle very quickly and very loudly.
Unless of course they were part of the conspiracy and no doubt there are several theorists who believe that as well.
As someone else pointed out, anyone with two brain cells to rub together wouldn't have been a conspiracy theorist in the first place.

Mar 27, 2015 at 1:01 PM | Registered CommenterMike Jackson

Lew’s reply to Dixon &Jones is paywalled, but in his summary at shapingtomorowsworld he welcomes the criticism, saying: “This is the type of scientific debate that moves the field forward, unlike some of the other responses to our work, detailed here that have only wasted our time and that of other university staff without anything to show for it.”
And the “here” links to the Lew Mann paper The Subterranean War on Science” which begins “Science denial kills...”

All credit to Ruth and Jonathan for their work, but the reason some of us timewasters operated outside the peer review process is not only because of our scientific incompetence, but because our criticisms were not ones which could be aired in a scientific journal. Our point was that Lewandowsky lied. He lied in the paper about the source of his respondents, then in emails to Barry Woods, then he lied about the criticisms of his paper in a second (retracted) paper, and again about the reasons for the retraction. Finally he even lied to fellow author John Cook in emails obtained by Simon Turnill.

“Science denial kills?” Not always. Sometimes it can get you a medal from the Royal Society.

Mar 27, 2015 at 1:17 PM | Registered Commentergeoffchambers

Lapogus: thanks for sharing that Buzz Aldrin clip! Shame that world leaders cannot listen to people with real world experience and achievements, who have science and engineering backgrounds, instead of career CliSci charlatans.

Good on him for dobbing the bloke! What a guy! Sometimes a punch in he mouth is well deserved...

Mar 27, 2015 at 2:19 PM | Registered Commenterthinkingscientist

TS - yes, it's a classic, it always makes me smile.

Mar 27, 2015 at 3:28 PM | Registered Commenterlapogus

Geoff Ch, RE: Lewandowsky's reply

SteveMc has a pdf of the full thing

Mar 27, 2015 at 5:52 PM | Unregistered CommenterJonas N

Perhaps the Lew paper should be recycled into loo paper.

Mar 27, 2015 at 7:33 PM | Unregistered CommenterPeter Stroud

Geoff, and others, we did indeed ask ourselves at the start of the process whether taking the peer-reviewed route (should it be successful) would simply allow Lewandowsky to delegitimate all the valid blog critiques made by you and others. In our view, many of the criticisms of LGO and LOG are better done on blogs and our Comment in no way makes those critiques a waste of time.

But the peer-reviewed literature is a valid alternative to blog criticism, and reaches a different audience. In early 2014, we realised that there were 3 factors that made it worthwhile to pursue that route: (i) we identified a problem using the exact data used by Lewandowsky et al. (which meant that there were no arguments about data collection), (ii) we saw no-one else suggesting that there was a curved relationship between CY and CLIM (though some had come close), and (iii) our result was consistent across both datasets. These characteristics made it just possible that editors and reviewers would not dismiss our paper out of hand. We are also familiar with the process of publishing in the peer-reviewed literature and are lucky enough to have a ‘work address’ that will be taken seriously (we don't think this should be the case, but in practice it does help, though it is of course not a guarantee of success).

And, Shub, we don't think that the survey data was 'faked' by the authors (though some individual entries may have been 'faked' by the respondents). Poor experimental design, poorly implemented, is enough to explain the data. Had it been deliberately manipulated, we don't think that the data would have shown the curved relationship.

Mar 27, 2015 at 8:20 PM | Registered CommenterRuth Dixon

Thanks JonasN. I see Lew's reply is a full article, while Dixon & Jones were limited to 1000 words. So much for the cut and thrust of peer-reviewed science. One side gets a broadsword and the other a pen knife.

Thanks Ruth. I didn't at all mean to suggest that the peer-reviewed route wasn't worthwhile. Indeed, I realise it takes infinitely more effort than the rantings of us bloggers, and it provides a challenge that Lewandowsky can't refuse to meet.

I believe there is another potential peer-reviewed article in the pipeline making a quite different and equally telling point about the two articles.

Mar 27, 2015 at 8:46 PM | Registered Commentergeoffchambers

"Dr. Lewandowsky posted About this at the Shaping Tomirrow's World blog...http://www.shapingtomorrowsworld.org/lewandowskydj.html" --DGH

Thank you for the link, DGH, but I will not be visiting Shagging Tomorrow's World.

Mar 27, 2015 at 9:58 PM | Unregistered Commenterjorgekafkazar

"The complex statistical models used by Lewandowsky et al. mask this rather obvious and uninteresting finding."

Absolute evisceration:-)

And about time too. Well done Jonathan Jones and Ruth Dixon

Mar 27, 2015 at 11:30 PM | Unregistered CommenterDon Keiller

Thanks Ruth. With LOG12/13 one struggles to find the right word for their data: clearly there are some faked entries. Is it faulty? flawed? I think it is fair to say the provenance of the data is suspect unless Lewandowsky can release the metadata and openly establish its veracity. Certainly I didn't mean to say the authors sat down and created the data. It came from somewhere and we don't know from where.

Mar 28, 2015 at 12:36 AM | Registered Commentershub

PostPost a New Comment

Enter your information below to add a new comment.

My response is on my own website »
Author Email (optional):
Author URL (optional):
Post:
 
Some HTML allowed: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <code> <em> <i> <strike> <strong>