A simple recipe for the manufacturing of doubt

By Klaus Oberauer
Posted on 19 September 2012
Filed under Cognition
and Stephan Lewandowsky
Professor, School of Experimental Psychology and Cabot Institute, University of Bristol

Mr. McIntyre, a self-declared expert in statistics, recently posted an ostensibly unsuccessful attempt to replicate several exploratory factor analyses in our study on the motivated rejection of (climate) science. His wordy post creates the appearance of potential problems with our analysis.

There are no such problems, and it is illustrative to examine how Mr. McIntyre manages to manufacture this erroneous impression.

Our explanation focuses on the factor analysis of the five “climate science” items as just one example, because this is the case where his re-“analysis” deviated most from our actual results.

The trick is simple when you know a bit about exploratory factor analysis (EFA). EFA serves to reduce the dimensionality in a data set. To this end, EFA represents the variance and covariance of a set of observed variables by a smaller number of latent variables (factors) that represent the variance shared among some or all observed variables.

EFA is a non-trivial analysis technique that requires considerable training to be used competently, and a full explanation is far beyond the scope of a single blog post. Suffice it to say that what EFA does is to take a bunch of variables, such as items on a questionnaire, and then replaces the multitude of items with a small number of “factors” that represent the common information that is picked up by those items. In a nutshell, EFA permits you to go from 100 items on an IQ test to a single factor that one might call “intelligence.” (It’s more nuanced than that, but that captures the essential idea for now).

One core aspect of EFA is that the researcher must decide on the number of factors to be extracted from a covariance matrix. There are several well-established criteria that guide this selection. In the case of our data, all acknowledged criteria yield the same conslusions.

For illustrative purposes we focus on the simplest and most straightforward criterion, which states one should extract factors with an eigenvalue > 1.  (If you don’t know what an eigenvalue is, that’s not a problem—all you need to know is that this quantity should be >1 for a factor to be extracted). The reason is that factors with eigenvalues < 1 represent less variance than a single variable, which negates the entire purpose of EFA, namely to represent the most important dimensions of variation in the data in an economical way.

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. 

Our EFA of the climate items thus provides clear evidence that a single factor is sufficient to represent the largest part of the variance in the five “climate science” items.  Moreover, adding further factors with eigenvalues < 1 is counterproductive because they represent less information than the original individual items. (Remember that all acknowledged standard criteria yield the same conclusions.)

Practically, this means that people’s responses to the five questions regarding climate science were so highly correlated that they reflect, to the largest part, variability on a single dimension, namely the acceptance or rejection of climate science. The remaining variance in individual items is most likely mere measurement error.

How could Mr. McIntyre fail to reproduce our EFA?

Simple: In contravention of normal practice, he forced the analysis to extract two factors. This is obvious in his R command line:


In this and all other EFAs posted on Mr. McIntyre’s blog, the number of factors to be extracted was chosen by fiat and without justification.

Remember, the second factor in our EFA for the climate item had an eigenvalue much below 1, and hence its extraction is nonsensical. (As it is by all other criteria as well.)

But that’s not everything.

When more than one factor is extracted, researchers can rotate factors so that each factor represents a substantial, and approximately equal, part of the variance. In R, the default rotation method, which Mr. McIntyre did not overrule, is to use Varimax rotation, which forces the factors to be uncorrelated. As a result of rotation, the variance is split about evenly among the factors extracted.

Of course, this analysis is nonsensical because there is no justification for extracting more than one factor from the set of “climate change” items.

There are two explanations for this obvious flaw in Mr. McIntyre’s re-“analysis”. Either he made a beginner’s mistake, in which case he should stop posing as an expert in statistics and take a refresher of Multivariate Analysis 101. Or else, he intentionally rigged his re-“analysis” so that it deviated from our EFA’s in the hope that no one would see through his manufacture of doubt.

Bookmark and Share


Prev  1  2  3  4  5  6  7  8  9  10  11  12  Next

Comments 301 to 350 out of 568:

  1. @- HAS
    "The first is testing L. et al against the standards of the scientific method, which is a broadly accepted canon. Among a number of deficiencies L. et al fails this test simply because they draw universal conclusions based on a single case (.... - over-generalisation)."

    You are revealing your unfamiliarity with cognitive psych and the scientific method. The L et al paper does NOT draw conclusions based on a single case, the were rather more than one person responding to this survey, and if general conclusions could not be made from surveys then political opinion polls would be incapable of indicating the likely voting pattern of the general population.

    @- "On our second point I don't think I'd want to be treated by someone that treated all clients based on something they seen in a particular idiosyncratically selected sub-population."

    But it would be entirely appropriate to treat the sub-population of science rejecters based on what is seen in that group.
    In other words to accept that it isn't scientific information that forms their views but ideological dogmatism that shapes their view of the science. Of course such political intransigence is rarely treated as a clinical condition, such madness is usually regarded as a virtue ! {grin}
  2. Stephan / Klaus,

    What next? Seems that the debate has moved on since you posted this. Will you be pulling the paper or do you think that it remains valid science?
  3. Billy @340:
    Just a wild guess but I'd reckon that the paper is still the paper and that it has not moved on.
    That's the thing about peer-reviewed research - it's peer-reviewed research. However much McIntyre and his supporters try to put lipstick on his pig, it's just a blog.
  4. Ian, any luck with that definition that suits your purposes?

    Thought not.
  5. Brad Keyes, let's try once more to cut to a chase.

    You claim that Kahan et al demonstrates (or at least supports the claim) that climate change non-alarmism isn't based on rejection of [climate] science. Yet anyone who comprehends the paper can see that the paper itself disagrees with you [my emphasis]:

    "SCT asserts, first, that ordinary members of the public underestimate the seriousness of climate change because of the difficulty of the scientific evidence[3]. If this is correct, concern over climate change should be positively correlated with science literacy - that is, concern should increase as people become more science literate."

    It takes heroic and apparently rather motivated reinterpration to read this as arguing that the correct science-based position is less concern rather than more. Or even to enlist it for an argument that makes that presumption. Especially when the paper also states that hierarchical individualists are, by virtue of their world view, expected to start out by underestimating risks (in general). Even figure 1 (in this version of the paper) which shows a schematic of the predictions of SCT makes it clear that the science-based conclusion is at the higher end of the concern scale. The paper clearly rejects the claim that you are trying to support by citing it!

    Your whole argument about this is predicated on the presumption that climate non-alarmism is the correct response to the scientific evidence. Your novel interpretation of Kahan et al as supporting your position only looks vaguely plausible if one accepts that unsupported premise - and doesn't comprehend the paper very well - but it falls apart in shards of formerly circular logic the instant that premise is removed.

    But it is impressive how hard you are working at reinterpreting the paper - especially since one would think the more straightforward and powerful way to establish that your non-alarmism is not based on rejecting science would be to, you know, show that science via the best inference from all the evidence supports your non-alarmism much better than it supports strong concern.
  6. Response to post #343. Not really Bill but then I didn't think I would. I did point out (#336) that the comment made was not in accord with the comments policy on this blog. In post #337 I got an explanation of what was meant by the comment so I guess I did have some luck, as you put it. As many people in the arena of climate science, both proponents and opponents of AGW, lack any sort of respect for those with opinions different from their own, I expected that any sort of protest however mild, would be excoriated. Sadly, I was right. On a different note why are so many at this site so annoyed with Steve McIntyre. Is it the comments he makes, his temerity in questioning Professor Lewandowsky, that he hasn't got the "right" background, his scepticism or what? Surely if the paper is as good as many here suggest, McIntyre will wind up with egg on his face. Or are those protesting so much apprehensive in case McIntyre is correct? Surely science is about questioning results and conclusions. Perhaps not in climate science?
  7. I believe mocking McIntyre's lack of understanding of stats and cognitive science is partly because, while he accepts the reality and some of the science behind AGW, by his actions he does appear to be a 'proponent' of it. He encourages doubt in the science and panders to the crowd who don't want to address the problem.

    More responsible people who understand the science are very much opposed to AGW and do want to rectify the problem.

    If McIntyre wanted to be respected, he would not restrict his activities to harassing scientists, trying to disrupt and delay their research efforts and encouraging the scientific illiterati to do the same. If he was an independent 'fact-checker' he'd also check papers, presentations and media statements by people like Christy, Lindzen, Soon, de Frietas, Carter, Plimer, SPPI etc and the nonsense put about by anti-science bloggers and entertainers like Monckton.

    There's a difference between questioning results and conclusions (scientists do that all the time) and deliberately manufacturing doubt for the sake of it - with no basis for doing so. McI indulges in the latter not the former.

    (McI usually ends up with egg on his face, like now. He doesn't seem to mind.)

    This is a good summary of how he operates and why he is scorned. In that summation the third sentence in point 2 was off the mark, as can be seen by the headlines and commentary in McI's thirteen posts on the topic to date.
  8. Huh? I'm an affirmer of climate change.

    Good, let's test it then. How far do you go?

    1) CO2 is a greenhouse gas.

    2) Humans are the overwhelming, if not exclusive, cause of the observed rise in atmospheric CO2 concentration over the last several centuries.

    3) CO2 increases equilibrium atmospheric temperature by around 3 dgrees celcius for each doubling over the pre-Industrial Revolution concentration.

    4) The observed rise in global temperature over the last several centuries is only adequately explained by the human-caused increased in CO2.

    5) An increase over the Holocene mean of the mean annual global temperature by around 2 degrees celcius will have serious effects on the biosphere, the hydrosphere, the cryosphere, and pragmatically, on the food/forestry/ fishing resources on which humanity relies.

    6) An increase over the Holocene mean of the mean annual global temperature by around 4 to 6 degrees celcius will have such serious effects on the planet that some or many societies, and indeed cohesive civilisation, are in danger of failing.

    I'm very curious to see if and where you part company with the 6 basic premises above, and how they do or do not inform your approach to both LOG12 and Kahan et al.

    And on the matter of the latter paper, if you want to prove your correctness of interpretation over the rest of us, you have but to ask Stephan Lewandowsky to invite Kahan to write a piece for this forum. It's certainly on-topic, and we'd all have the opportunity to see how well you and your 'sceptical' colleagues have processed the results. Before you do though, please list for comfirmable posterity your 5 or 6 most important dot-point summaries of the essential outcomes of the Kahan et al study.
  9. @- ian
    "On a different note why are so many at this site so annoyed with Steve McIntyre. Is it the comments he makes, his temerity in questioning Professor Lewandowsky, that he hasn't got the "right" background, his scepticism or what? Surely if the paper is as good as many here suggest, McIntyre will wind up with egg on his face."

    He has ended up with egg on his face before, but his followers tend to ignore it. The first hockey stick paleoclimate graph may have had methodological problems, but its confirmation by many other reconstructions using diverse methods and data have confirmed that these problems are of minor effect on the accuracy of the results. McIntyre however still presents his weak critique of that paper as significant despite it being superseded by more recent research that confirms its main points.

    I suspect many who are familiar with the history of climate science denial {the public acts casting doubt onto the majority understanding of AGW} will be aware of McIntyre and his repeated exercises in pedantic 'auditing' of some climate science while studiously ignoring any papers that might cast doubt but is weak or fallacious. Humulun et al on CO2 would be a recent example, but MaClean De Freitas and Carter would be another. It is his conspicuous unilateral application of his 'skepticism' that indicates to most of those that are not biased by their free-market, individualistic authoritarian mental outlook that he does not act with neutrality or integrity in this field.

    Quite apart from his disparaging language and FOI harassment....
  10. Which falsified SCT.

    Um, you do know that the alternative, the cultural cognition thesis, bascially says what I've described above? To repeat my coarse generalisation at post #291:

    To phrase it bluntly, education enhances one's prejudice...

    If one's prejudice is for rationality, a good education will increase an acceptance of the rational, scientific indication of the risks of climate change.

    If one's prejudice is for individuality, a good education will increase the capacity to engage the cognitive contortion/self-delusion required to dismiss the scientific indication of the risks of climate change. In other words, such people can become better at fooling themselves when educated.

    [It's salient to remember that by "individuality" I am referring to the Hierarchy-Individualism type, and not simply to individualism in general.]
  11. I had a brief visit to climate audit, and don't feel like going back again. Immediate accusations of fraud (due to incompetence/lack of knowledge) are appalling to me. Why doesn't he consult with a statistician who specializes in the area?
    Look at what Uri Simonsohn did when he actually detected fraud, working as a professional:
    1. Replicate analyses across multiple papers before suspecting foul play by a given author,
    2. Compare suspected studies to similar ones by other authors,
    3. Extend analyses to raw data,
    4. Contact authors privately, transparently, and give them ample time to consider your concerns,
    5. Offer to discuss matters with a trusted statistically savvy advisor,
    6. Give the authors more time.
    7. If after all this suspicions remains, convey them only to entities tasked with investigating such matters, and do so as discretely as possible.

    Sound familiar? No, I didn't think so.
  12. Stewart.

    You raise a profoundly salient point.

    Whatever McIntyre's doing, it's not in accordance with professionally-accepted protocol.
  13. Bearing in mind that such allegations of professional impropriety are a completely different kettle of fish to discussing flaws in an analysis or legitimately questioning conclusions drawn in scientific papers - showing reasons why (hopefully without personal invective). (Sometimes done on science blogs as a precursor to a refutation or comment in a journal.)
  14. I still struggle to understand how the authors could exclude data collected from two web based sites without discussing that decision in the paper. The decision to make this a blog based study was apparently made after the fact.

    Does the missing data support or contradict the paper's findings?
  15. 51
  16. #51
  17. "Keep reading."

    I already read the whole thing.

    You need to go back and read what I wrote, and then what Kahan et al wrote, and then what I wrote, noting the second time through that what I wrote does not depend in any way on SCT being unfalsified, nor did I argue anywhere that SCT was unfalsified. Then consider what that means for your latest pair of comments.

    Hint: I bolded some bits to help you out the first time through.

    Hint for the second time through: "If this is correct" is a conditional statement about SCT, but the rest of that statement about what should be observed if SCT is correct can only imply that Kahan et al disagree with your claim about what climate science finds.

    Would you care to try again, or withdraw some of your claims?
  18. #351 izen

    See #203, #307, #308
    Some commenters want to ascribe statistical and scholarly credibility to someone who writes explicit code to do a 1:100 cherry-pick, uses unreal parameters for AR processes, and employs false citations to "enhance" a narrative.
  19. "The first hockey stick paleoclimate graph may have had methodological problems, but its confirmation by many other reconstructions using diverse methods and data have confirmed that these problems are of minor effect on the accuracy of the results."


  20. @- JohnMashey
    "Some commenters want to ascribe statistical and scholarly credibility to someone who writes explicit code to do a 1:100 cherry-pick, uses unreal parameters for AR processes, and employs false citations to "enhance" a narrative."

    Some people find his approach congenial because of their preference for free market, hierarchical ideology, not his scientific rigour.
    Rejecting the science of AGW then poses a moral hazard as Stephen Gardiner describes because political ideology matches selfish motives.

    While those wedded to a egalitarian, communitarian ideology may find AGW 'congenial' because it includes community action in its solution, they would find NO AGW more congenial, but they are better able to accept the need for collective action.
    Rejectors of climate science hold selfish dogmas that reject any science that carries the inference that individual self-interest and avoidance of civic regulation will have to be sacrificed to prevent significant environmental damage.
  21. @- Elvis P
    You provide a link showing the difference between the early MMB hockey stick and the mean of some subsequent paleoclimate reconstructions.
    Presumably you are trying to show that later 'hockey sticks' had much larger rising blades because the original underestimated the LIA.
    Not as has been claimed, minimised the MWP.
  22. "Bear in mind that Kahan et al.'s results are equally amenable to the opposite "explanation": i.e. that communitarians accept non-facts because they make them comfortable."

    So the results support the argument that communitarians accept assertions about major threats to the community's well being because it makes them comfortable? Being alarmed ("alarmists") is being comfortable? Do we seem comfortable?

    This, Brad, like virtually everything else you have argued or claimed here, is contrary to logic and fact. It is, as far as I can see or conceive, inconsistent with intellectual honesty. It is, quite clearly and apparently, an argument driven by ideology rather than reason, an argument to a desired result, not from evidence and inference. It is an obvious illustration of the theses of the papers discussed here. And while it is a rather extraordinary in how directly it illustrates that, it is not atypical of the arguments offered by those who share the same ideology and who, as a causal result, reject, as you do despite your factually incorrect assertions to the contrary, climate science.
  23. Is it the comments he makes

    No, wrong.

    his temerity in questioning Professor Lewandowsky

    No, wrong.

    that he hasn't got the "right" background

    No, wrong.

    his scepticism

    No, wrong.

    or what?

    It's the perception that he is not acting in good bad faith.

    Surely if the paper is as good as many here suggest, McIntyre will wind up with egg on his face.

    Not if, say, you were the one holding the eggs.

    Or are those protesting so much apprehensive in case McIntyre is correct?

    No, wrong.

    Surely science is about questioning results and conclusions.

    Yes. Which is why those who are not skeptical of his results and conclusions are not doing science.

    Perhaps not in climate science?

    No, wrong.
  24. @mk #363 - that illogic is what ultimately drives the 'logic' of paranoid conspiracy theories.

    "Evil 'leftists' want climate catastrophe" - no that won't fly, best give a reason.

    "So they can take over the world" - no that won't fly by itself, there'd be no world to take over.

    "So that the evil capitalist bankers can take over the world" - no that won't fly, capitalist bankers aren't leftists.

    Oh heck, just throw it all together and something will stick!
  25. when they're as obtusely recalcitrant to understanding the facts, as you have above demonstrated yourself to be, it really is a bit rich to be expected to be treated with kid gloves

    Even if that charge were not factual, people like HAS should recognize that we alarmists, being in the grips of an ideology as we are believed to be by non-accepters, are motivated by our belief that the non-accepters are, in the obtuse recalcitrance to understanding that we believe of them, causing great harm to the human community and future community (that makes us comfortable, according to Brad), our belief that they are acting in bad faith and that that bad faith is producing highly negative consequences, our belief that they are denying science while denying that they are, our belief that they are claiming expertise and knowledge in science and a scientific outlook that they lack, at least in re climate science, our whole host of negative beliefs and attitudes toward them ... so really, given our beliefs that they know we have, they should not expect us to be nice ... it just wouldn't make sense psychologically.
  26. 362 izen
    See PDF @ Strange Scholarship..., especially p.142:

    'Different reconstructions cover different geographies, and in particular, those focused on (land-dominated) NH extratropics are expected to vary more than the entire NH, which in turn varies more than global.'

    Also, see p.158, where I quote Esper, et al (2002), supporting your comment:
    'This comparison suggests that MBH is not necessarily missing a MWP. Rather, it has a reduced expression of the LIA compared with RCS.'

    I have often argued that "spaghetti graphs" can be misleading, making people think there is more disagreement than there really is, as discussed on that page.
    a) Methods vary
    b) Non-identical proxies are used
    c) Geography matters a great deal
    d) Error bars matter

    MBH99 specified Northern Hemisphere (NH)
    Relative areas are, by A = 1 - sin(radians(lat)), I think:
    1.00 NH
    0.60 23.5degN Tropic of Cancer (~Moberg)
    0.50 30degN (Ljungqvist)
    0.36 40degN
    0.13 60degN

    Given distribution of land and ice/snow-albedo feedback, one has every reason to expect that a NH reconstruction would be jiggle more than a world (NH+SH) reconstruction. As one uses less and less of the NH, one would *expect* more jiggles.

    In addition, see Law Dome CO2, 1000-2000AD, showing the largest, steepest drop in CO2 in that time (much of which likely due to the ~50m person die-off in Americans and reforestration.) Add in volcanoes and Maunder later and you have a good recipe for an LIA. However, since polar amplification works both ways, one would expect areas around the snow line to show a steeper drop than those further South. [Skiers are familiar with the effect near the slopes.] UK, N. Europe, land around the N. Atlantic would be the most populated areas one would expect to exhibit an LIA drop.

    If someone just presents a graph, without the relevant information, either they do not understand this topic, or they are trying to fool people. Graphs are powerful tools for providing insight, but also in misleading.

    Once we get beyond that, one can evaluate the specific choice of {Moberg, Loehle, Ljungvist}, which curiously happen to be among those with the steepest drops, without mentioning the others that are not so steep.

    1) Compare Moberg(2005), p.614 proxy locations with those in MBH98, p.780. The former is more heavily-weighted with more Northern proxies, with only 2 just South of Tropic of Cancer MBH98/99 use more proxies and they are more dispersed. [This is not a criticism of Moberg, simply noting that geography matters, and NH extratropics is 50-60% of the entire NH, so they are different.]

    2) If the graph had Loehle(2007), it has issues issues, starting with being published in Energy&Environment.

    3) See this on Ljungqvist(2010).
    Ljunqvist was a "NH extratropic" reconstruction, 30degN-90degN, i.e., 50% of the NH.

    So, the graph shows a problematical curve and two that are extra-tropic,. The latter two are actually useful, IF one labels them properly and explains the differences.
  27. The just released report from the Yale Project on Climate Change Communication /George Mason University provides more evidence of link between political inclination and acceptance or rejection of climate science in the USA.
  28. Ian re: "On a different note why are so many at this site so annoyed with Steve McIntyre."

    Despite the fact that you and I are both apparently practicing molecular biologists I can't help feeling we don't share equivalent ethical universes.

    If we have some insight into historical events we’re probably not surprised that collateral damage ensues when unethical practices are used to pursue immoral outcomes. Despite the efforts by McIntyre and his mob to damage Michael Mann's reputation (in particular), the individuals so far most damaged by the distasteful circus are probably Ed Wegman and Yasmin Said. Maybe we shouldn’t spare too much sympathy for characters so willing to puff their status by jumping on the hounding bandwagon, but I expect they might have been interested to know that McIntyre’s pretence that the MBH method of processing proxy data resulted in marked “hockeysticks” from red noise, were based on inappropriate/incompetent choice of “red noise” data combined with a discarding of 99% of the data that least suited the pretence. They might at least have realised that blatant pursuit of political expediency by unethical misrepresentation would likely attract a spotlight from the ethical elements of the scientific enterprise.

    Sadly I expect Wegman and Said won’t be the only individuals damaged by the sort of devotion to unethical practices that seems deliciously irresistible to some minds.

    As practicing scientists we try to maintain standards of quality and scientific ethics. We send our graduate students on courses on biomedical ethics, give them insight in the potential problems of plagiarism and generally attempt to instil good practice by example and training. I would hope you might have similar ethical goals in your research ‘though apparently you don’t consider these should apply in other fields. Perhaps you are eyeing up the delightful prospect of gathering a group of disaffected biologists, enticing a mob of blog acolytes with misrepresentation of the research of scientists whose work you don’t like and settling down to the business of hounding these – MolBiolAudit perhaps?
  29. Dropping back by to see how to see how things are going I see Bernard J #337 (-snip-). What L. et al are saying in the piece he quotes is that “these results only apply to those who answered the questions”. Even in the quoted piece L. et al delightful leave open the interpretation that it is representative of those “who choose to get involved in the ongoing debate about one scientific topic, climate change”, and claims that “this group of people has demonstrable impact on society and understanding their motivations and reasoning is therefore of considerable importance”. We see no evidence for the claim that the sample has that characteristic, and it definitely isn’t representative of it.

    No conclusions can be drawn from it about those in the population that get involved in the debate or are having an impact on society thereby. So even in this narrow sense the study over-generalises.

    But wait there is more.

    Even had the sample been well drawn all that L. et al do is find some correlations in it. They would have developed a hypothetical model from it. To claim to the predictions etc that they do in their abstract and their conclusions, at a minimum they needed to either split their sample in half and test the model, or run the survey gain.

    (-snip-). Perhaps if you took your advice to me and read what was written and try to understand what is being said, you could break out of this frustrating loop you find yourself.

    Izen #338, (-snip-). The “single case” I referred to was this particular sample. Re-read and see if you now understand. My response to Bernard J might help.
    Moderator Response: Inflammatory snipped.
  30. @- HAS
    "The “single case” I referred to was this particular sample. Re-read and see if you now understand. My response to Bernard J might help."

    Of course it helps, but my intention was to elicit this clarification.
    It is always possible to claim the sample or data is unrepresentative of whatever the authors claim it might represent. Tree rings come to mind...
    But on what basis could you refute, or support, the claims made about what the sample might indicate about a larger number of people. There is of course a large literature on just this topic. There is also a lot of work in the same field using different methods that reveal result consistent with this paper.
    This isn't a lone hockey stick.

    That is one factor that makes the response to this paper so... Well entertaining to be honest.
  31. @Brad. Yes, I believe McIntyre's assumption when he started going into this paper is that he would declare it the result of fraud. This is not normal scientific practice as others have described.

    In any case, how does 83% vs. 86% change any conclusion in the paper??


    That is the real point. Let's assume that LOH forgot to document one small step in their analysis. Assume that causes the difference between their result and McIntyre's result. So what? That does not meaningfully change the result.

    The raw data is there -- it would be a much more valuable contribution to science and understanding if someone like McIntyre would analyze the data using his preferred method and publish and defend those results. What he is doing now has very close to zero scientific benefit... if anything, it is negative.
  32. Chris (-snip-)
    Moderator Response: Multiple inflammatory snipped. Posting comments at this site is a privilege not a right; a privilege which can and will be rescinded if you keep ignoring the requirement to comply with the Comments Policy by repetitively and repeatedly posting inflammatory comments about other participants. You will receive no further warnings in this matter.
  33. @Brad #371 - on conspiracy ideation: if people go to the extent of redefining meanings such that capitalists are 'evil leftists' and Soros is a 'banker' allows them to adopt that theory, it tends to prove what I mistakenly thought at the time was a frivolous point.
  34. izeb #366, I take it from your comments that you now agree that L. et al doesn't support the claims made.

    How might they have done better?

    Well they could have held out a proportion of their sample and tested the model developed from one half on the other. This would be standard procedure to get published in most disciplines. In fact it appears they had an even better option. They could have taken the model apparently developed in L. et al (2012) and test this sample directly against that.
  35. Brad #372 and #373 - Are those people you mentioned the sources of your opinions on 'climate science'? (I expect McIntyre would be somewhat taken aback at your categorisation of him as a 'socialist/leftie'.)
  36. To my knowledge Soros has never been a banker, although his investment fund may invest in banks along with other companies. Obviously he can be classified as a capitalist.

    Politically he favours liberal/progressive groups more than conservative from what I've read.

    He is also a philanthropist, donating to human rights, developmental aid, disaster recovery, arts, education programs etc.

    (His name also features prominently in many wacky conspiracy theories.)
  37. @Brad - I see where you are coming from - Monckton, Delingpole, Eschenbach, BishopHill etc. Thanks for that.
  38. The Kahn paper measured scientific literacy among the general public with a set of questions and found that, as it increased, concern about climate decreased.

    The assumption by the critics here seems to be that if the group of people sampled had been more scientifically literate than it proved to be, or if the questions had been more difficult, the correlation might have been reversed.

    Maybe. But I see absolutely no reason to assume that. A much more reasonable assumption is that the correlation would continue unperturbed at all educational levels. And besides, if you want to sample the general public, you don’t make previous selections by educational level.

    (-snip-). The skeptic sites rely on a few blogs. If in spite of this massive artillery that for the last few years has been bombarding the public ( -snip-), the alarmists still have failed to convince the public to their satisfaction, it might be a good idea for them to reflect why instead of blaming "big oil" or general illiteracy. They should entertain the possibility that people are detecting something is off from the sheer vehemence of the message. In any case, the notion that scientific illiteracy is correlated to an inability to get the message is wrong, and the Kahn paper only confirms it. People are not deaf, but people get tired of being though of as deaf when they hear the same thing shouted to them over and over and over. They’ve heard the alarmist message a thousand times more often than the skeptic message, and as it turns out, the more scientifically literate they are, the less prone they are to buy it. That’s the reality.
    Moderator Response: Inflammatory snipped.
  39. Francisco #381 is partly correct. Kahan et al concluded that it is not scientific illiteracy that is strongly correlated with rejection of climate science.

    Francisco missed the Kahan et al conclusion that rejection of climate science stems from a conflict of interest with a hierarchical, individualistic world-view. (And, like our Brad, seems oblivious to the fact that Kahan et al has an underlying assumption that there is no valid basis for rejecting climate science, which is likely what prompted them to research the phenomenon in the first place.)

    Would it be confirmation bias, motivated rejection or what that prompts some people to misconstrue the findings of Kahan et al - and causes them to protest so vigorously at Lewandowsky et al, in which the findings are not dissimilar.

    Or are they different shades of the same thing?
  40. "Peer review in scientific journals is good, he suggested, but it is limited and vulnerable to compromise. “There is far more independent due diligence on the smallest prospectus offering securities to the public than on a Nature article that might end up having a tremendous impact on policy.”"

    Interestingly, he's relying on misleading people about the scientific method, especially as it applies to policies derived from climate science. (Does this help answer Ian's question about why people don't like McIntyre's efforts?)

    Despite his claim to the contrary, "auditing" is just about the least powerful technique for finding issues with published scientific claims - especially when you write up your early claims and get them flashing around the blogosphere before they themselves can be tested, where they persist long after they have been shown to be flat out wrong, and even more so when you have a tendency to get some of the early claims wrong in a fashion that only ever seem to lean one way.

    He also appears to be referring to pre-publication peer review without taking into account the ongoing post-publication peer review of claims undertaken by the field, often using different methods to attack the same hypotheses.

    It's also incorrect that a single Nature article has a huge impact on policy all on its ownsome. No politician I have ever heard of reads Nature and jumps into action based on a single article. (Well, unless it's a "skeptical" politician touting the latest "final nail in the coffin of AGW" paper as outweighing all the rest of the evidence.)

    The IPCC was set up specifically to weigh all the evidence and summarise it for non-scientists. That includes weighing both the hypothetical "single paper" McIntyre touts along with any other evidence that may support or undermine it. And the irony is that that process itself is heavily peer-reviewed - including participation by McIntyre - so he knows better.
  41. Brad Keyes at #373, 08:43 AM on 25 September, 2012.

    Do you understand the serious logical fallacy that you committed with that post?
  42. "...There is far more independent due diligence on the smallest prospectus offering securities to the public..."

    Was that quoted on his Facebook page? :-?
  43. " (-snip-)"
    from wikipedia
    Moderator Response: Off-topic copy/paste snipped.
  44. Brad Keyes at #373, 08:43 AM on 25 September, 2012.

    Do you understand yet the serious logical fallacy that you committed with your post?
  45. This paper is interesting in the context of the discussion as a whole. (Not the matter of redefining inconvenient words so they mean what you want them to mean and vice versa. That's something else again IMO.) It's about research into how misinformation 'sticks' and the pros and cons of various methods of getting it 'unstuck'.  The paper indicates approaches vary in value, depending on why people might be thinking wrong facts are true in the first place, which I gather is not necessarily a straightforward matter.

    It looks as if the Debunking Handbook was based on research described in that paper.
  46. "I could hardly fail to notice Kahan et al.'s "underlying assumption," ...

    You did, however, either fail to notice that their underlying assumption entirely undermines your reason for citing the paper - or you noticed and went ahead with it anyway.

    And when called on it, you doubled down in comments that also pointed out that SCT was falsified by the paper, despite that only being possible if their underlying assumption undermines your reason for citing it.

    And after all of this explanation of the fallacy of claiming it supports your position, you still seem to be claiming or implying that it supports your claim.

    "...or the lengths they go to in order to reconcile their findings with it. "

    I don't see any such lengths. Their conclusions pretty straightforwardly flow from their results in combination with their well-justified assumption.

    You, on the other hand, appear to be engaged in ongoing great lengths to try and contort its findings to fit your claim.

    I find the level of projection here (and also here) rather - in your turn of phrase - entertaining.
  47. "They falsify the theory that climate non-alarmism can be put down to right-wing ideology or opposition to "any science that carries the inference that individual self-interest and avoidance of civic regulation will have to be sacrificed to prevent significant environmental damage.""

    Er, no, they don't - and Bernard has been trying to get you to think why not, with no success.

    But let's take a small diversion first: Monckton, as just one example, clearly demonstrates a strong right-wing political ideology, and a strong opposition to "any science that carries the inference..." etc.. (It would be smart to do a little independent research on the guy before you trot him out.)

    He would only be a data point that supports your claim if he did not exhibit either of those characteristics.

    Now to return to the main topic, consider that this is true even if he claims to be or is even widely acknowledged to be an environmentalist (a claim that is rather dubious in Monckton's case, but moot anyway).

    Have you figured out your (first) fallacy yet?
  48. #393 Speaking of fallacies (of the logic kind), look up false premise and strawman.
  49. Forget for the word "comfortable."


    That was flippant.

    Par for your course. You are not to be taken seriously, for the reasons I have laid out.
  50. James Delingpole and Richard Drake have both described McIntyre as a leftie.

    I really did laugh out loud at that! Very loudly! "James Delingpole described ..."! Well then!

Prev  1  2  3  4  5  6  7  8  9  10  11  12  Next

Comments Policy

Post a Comment

You need to be logged in to post a comment. Login via the left margin or register a new account.