Polar Bears, Inadequate data and Statistical Lipstick


A recent paper Internet Blogs, Polar Bears, and Climate-Change Denial by Proxy by JEFFREY A. HARVEY and 13 others has been creating somewhat of a stir in the blogosphere. The paper’s abstract purports to achieve the following:

Increasing surface temperatures, Arctic sea-ice loss, and other evidence of anthropogenic global warming (AGW) are acknowledged by every major scientific organization in the world. However, there is a wide gap between this broad scientific consensus and public opinion. Internet blogs have strongly contributed to this consensus gap by fomenting misunderstandings of AGW causes and consequences. Polar bears (Ursus maritimus) have become a “poster species” for AGW, making them a target of those denying AGW evidence. *Here, focusing on Arctic sea ice and polar bears, we show that blogs that deny or downplay AGW disregard the overwhelming scientific evidence of Arctic sea-ice loss and polar bear vulnerability.* By denying the impacts of AGW on polar bears, bloggers aim to cast doubt on other established ecological consequences of AGW, aggravating the consensus gap. To counter misinformation and reduce this gap, scientists should directly engage the public in the media and blogosphere.

Reading further into the paper we find that this seems to be yet another piece of  propaganda to push a Climate Change agenda. In line with the high standards of climate science “communication”, there are over 50 occurences of various forms of the derogatory labels “denier” or “deny” in a mere five pages of text and two pages of references. Such derogatory language has become commonplace in the climate change academic world and reflects badly on the authors who use it.

The paper offers nothing new in terms of scientific research on polar bears or on any other topic, so to justify publication, it includes a superfluous “study” of the views held on the subject within blogs and academic papers. My concern is with the accompanying data and statistical analysis providing the “scientific” veneer for their discussion.

The “lipstick” on the paper’s Figure 2 is perhaps one of the best examples of creating a misleading aura of “real science” that I have encountered in some time.



The closely bunched points massed together in the circled groups create an impression that the data from which it was generated must be based on a set of carefully crafted “measurements” capable of representing in-depth rigorous scientific assessments of a set of papers and blogs. To understand what it actually represents and how it came to be, we start by examining the methodology described in the paper for creating an appropriate data set:

As natural and social scientists, we grounded our study in Nisbet’s (2014) typology of frames used by science policymakers and journalists and provide full context and statistical analysis with objective interpretation.

Say what? In order to make sense of what this might mean we look at the Nisbet reference referred to in the above quotation. I found the following indicating what “framing” can be used for.

(From Nisbet, p.43):
Scientists can use framing to motivate greater interest and concern; to shape preferences for policies informed by or supportive of science; to influence political or personal behavior; to go beyond polarization and unite various publics around common ground; to define policy choices or options; and/or to rally fellow scientists around shared goals or strategy.

OK. Got it. Translation: We need to produce some climate science propaganda so we will design the method for collecting our data with that in mind.

Next step:

We conducted a content analysis to categorize how blogs presented evidence of or opinions on AGW to explain the current and future effects of AGW on Arctic ice extent and polar-bear status (Braun and Clarke 2006). On the basis of statements regarding the current and future status of Arctic sea-ice extent and polar-bear populations, we entered keywords, including global warming, climate change, polar bear, and Arctic ice, into Google’s search engine. From the blogs, we identified common positions on Arctic ice extent (1–3) and polar-bear status (4–6) and methodically coded each entry’s stated positions from the 90 blogs using a constant comparative approach, ensuring that no additional codes were required (Kolb 2012).

No wonder they needed 14 authors to create this paper! “Methodical coding” of this type must require a lot of work.

From Kolb, p.1:
In grounded theory the researcher uses multiple stages of collecting, refining, and categorizing the data (Strauss & Corbin). As identified in the literature, making constant comparisons and applying theoretical sampling are necessary strategies used for developing grounded theory.

The constant comparative method “combines systematic data collection, coding, and analysis with theoretical sampling in order to generate theory that is integrated, close to the data, and expressed in a form clear enough for further testing” (Conrad, Neumann, Haworth, & Scott, 1993, p. 280).

That sounds impressive! Using the above “guidelines”, we searched for some hot button key words on blogs to produce some data which we can then code and interpret.

Continuing with the data-gathering process:

Each blog was coded for stated positions on these two topics (Arctic ice extent and polar-bear status). The six codes identified were the following: (1) sea-ice extent is on average declining rapidly in the Arctic; (2) seaice extent is decreasing only marginally, is not decreasing significantly, or is currently recovering in the Arctic; (3) changes in sea-ice extent in the Arctic are due to natural variability, and it is impossible to predict future conditions; (4) polar bears are threatened with extinction by present and future AGW; (5) polar bears are not threatened with extinction by present and future AGW; and (6) polar bears will adapt to any future changes in Arctic ice extent whether because of AGW or natural variability. We also collected every peer-reviewed scientific paper that we could find that investigated both polar bears and sea ice in our search process (92 papers) and scored their positions for the same six statements. The scores for both blogs and papers were analyzed, and a principle component analysis was used to visualize their relations.

After all this heavy lifting, we have six binary variables. This does not appear to be sufficient for any sort of robust statistical analysis. There is no description of any intermediate procedures used in examining the blogs or papers nor any further information in the data set to demonstrate that any “multiple stages of collecting, refining, and categorizing the data” or anything else was used to categorize the data in a formal scientifically valid fashion.

Furthermore, the language of several questions seems to be opposite sides of the same question. The “codes” (1) and (2) are different sides of the same concept. The second of these conflates three possibilities (although to me it looks like “decreasing only marginally” and “not decreasing significantly” are really pretty much the same). These might be better posited as a single variable with three or more ordinal categories providing some nuance to an ill-conceived design.

The same criticism obviously applies to aspects (4) and (5). Nobody would answer “yes” for both of these simultaneously (except a person who may simultaneously hold two contradictory ideas previously known only to exist in the mind of a certain psychology professor) so a better choice here could have been to combine them two as a single question with three choices, “yes”, “no” and “don’t know” (or “doesn’t say”). Unfortunately, their methods lead to a very large number (154) of “missing values” in the resulting data set thereby strongly interfering with the robustness of subsequent statistical analyses. These missing values are due not to some unforeseen inability to access the required information, but to the poor design for collecting and coding the information.

From looking at the data released by the authors, I am guessing that an explicit indication that either (4) or (5) be true might have been required for for a “yes” to be selected for each of these. However, dealing with the missing values separately is still both clumsy and distorts the analysis.

Note that the above quote states

We also collected every peer-reviewed scientific paper that we could find that investigated both polar bears and sea ice in our search process (92 papers) and scored their positions for the same six statements.

One of the variables in the data is code which identifies individual blogs and papers.  The papers have values which go from paper_4 to paper_165 with intermittent gaps in within the sequence.  From this one can deduce the fact at least 165 papers were initially considered and subsequently reduced to the 86 AGW == Pro and 6 Skeptic == Contra papers used in the final study.  I did not find any real explanation of either the methods or the reasons used to remove the missing papers.

A much greater problem was the lack of diversity in the authorship of the Pro papers.  As noticed  elsewhere, three persons (two authors of this paper, Steven Amstrup and Ian Stirling, along with Andrew Derocher) were either lead or co-authors of 60 Pro papers.  It is not surprising that the data gleaned from these papers might be virtually identical given that the same people are beating the same drum repeatedly.

But we are not quite there yet. From the paper’s Supplement document:

Citation of Susan Crockford was also recorded. Blogs were assigned ‘science-based’ and ‘denier’ categories on the basis of their positions taken relative to those drawn by the IPCC on global warming (e.g. whether it is warming or not and the anthropogenic contribution).

The possible mislabeling of several blogs which is unavoidable due to the lack of proper information about them has been noticed by others. I won’t address this issue because it does not contribute to the salient point of Figure 2.

The creation of a seventh binary variable – whether a paper or a blog references Dr. Crockford actually gets to the raison d’etre of the whole exercise:

Although the effects of warming on some polar-bear subpopulations are not yet documented and other subpopulations are apparently still faring well, the fundamental relationship between polar-bear welfare and sea-ice availability is well established, and unmitigated AGW assures that all polar bears ultimately will be negatively affected. Indeed, credible estimates suggest that the entire Arctic may be ice-free during summer within several decades (Snape and Forster 2014, Stroeve and Notz 2015, Notz and Stroeve 2017), a process that, as has been suggested by both theoretical and empirical evidence, will drastically reduce polar-bear populations across their range (Amstrup et al. 2010, Stirling and Derocher 2012, Atwood et al. 2016, Regehr et al. 2016).

It appears that the paper is meant as a hit piece on Dr. Susan Crockford who has done work on bears and presents some of her results on her blog . She maintains that polar bears are currently doing reasonably well and this seems to have bothered the authors of the paper. Interestingly enough, they reluctantly admit the polar bears ARE doing well enough now, and seem to be upset that others may not be totally convinced that the projected catastrophe will occur as scheduled or that the bears might be able to adapt as they have for centuries.

Merely discussing or even citing what Dr. Crockford has written is sufficient grounds  for being declared true “deniers” by the authors of this paper.  That the future is certain and the polar bears will all suffer is the only allowable belief.

We are now ready to tackle the “statistical lipstick” which adds that dollop of “science” to this propagandistic diatribe.

As we have seen, the data on which the plot is ostensibly based is a set of 182 vectors each consisting of 7 binary elements, i.e. each element can only be one of two possible responses: yes or no, in this case. That means that the data can at best distinguish between a maximum of 128 different cases. Missing values create a third possibility but, as indicated earlier, this is a self-inflicted detriment to a proper analysis because it interferes with the analytic procedures. Infilling the missing data is not the same as structuring the information properly and affects the end result according to how the infilling is implemented.

The actual situation is much worse. A simple check leads to the fact that there are only 25 unique vectors among the 182 observations. Furthermore, only 7 of those 25 do not contain missing values.

Using the coding: 0 = Missing,    1 = No,    2 = Yes.      Contra = Skeptics.     Pro = AGWers

  1. citation of Susan Crawford;
  2. sea-ice extent is on average declining rapidly in the Arctic;
  3. sea-ice extent is decreasing only marginally, is not decreasing significantly, or is currently recovering in the Arctic;
  4. changes in sea-ice extent in the Arctic are due to natural variability, and it is impossible to predict future conditions;
  5. polar bears are threatened with extinction by present and future AGW;
  6. polar bears are not threatened with extinction by present and future AGW;
  7. polar bears will adapt to any future changes in Arctic ice extent whether because of AGW or natural variability.

For the Contra group (45 Blogs and 6 Papers):

1002122 1111122 1112101 1112122 1122102 1122122 1211020
1 1 1 1 7 2 2
1212102 2110102 2120102 2120201 2122102 2122122 2212122
1 1 2 1 23 7 1

For the Pro group (45 Blogs and 86 Papers):

1001201 1200200 1200201 1200211 1201201 1210201 1210211
1 1 6 2 1 4 2
1211200 1211201 1211211 1211221
2 63 47 2

The values underneath each sequence represent the frequency of responses for that sequence.  You will note that there is NO overlap between these two sets of answers.

Blogs were selected from the internet by simplistic criteria  guaranteed to separate the subject matter  into two disjoint groups, Pro and Contra.  The data lacks any capability for discriminating among various levels of acceptance or rejection of the statements above so every blog and paper is automatically identical to all others within the same group.  The lack of diversity in the Pro Group is very apparent in that only two answer sequences account for 84% of the “scientific” papers and blogs.  The Contra group has almost 73% of the group sharing only three different answers.

I have had undergraduate students who have done more professional work designing a study  such as this after taking a single elementary statistics course.

Why do we need the following gratuitous high-powered statistical method mentioned in the Supplementary document to see if the groups are separable?

Blogs were assigned ‘science-based’ and ‘denier’ categories on the basis of their positions taken relative to those drawn by the IPCC on global warming (e.g. whether it is warming or not and the anthropogenic contribution). The assignment was confirmed by creating a distance matrix from the scores using absolute distance (Manhattan distance) and performing a hierarchical cluster analysis on the result (Ward.D2 method from R 3.3.3, R Core Team, 2017). Both methods yielded two large clusters with identical content.

Identical content indeed! Clusters consisting of blogs and papers with pretty much identical classifying variables as explained above which have been pre-binned into two groups by some nebulous criteria for evaluating their “scientific” attitude status. One could more easily demonstrate this using simple cross-tabulations tables, but then it would draw attention to the poorly done data gathering.

The next step was to perform a principal component analysis of the data from which the graph above was plotted.  Again from the Supplementary document:

A broad keyword search on the internet and the ISI Web of Science database yielded 90 blogs (described above) and 92 peer reviewed papers reporting on both Polar bears and arctic ice. Author’s positions in papers were scored in in same “position space” defined by binary answers to the six statements formulated in the main papers and citation of Dr. Susan Crockford as an expert. Missing values were replaced by zero after scaling and centering to minimize the influence of the replacement. The final data matrix contained the sources in the rows and the scores in the columns. The PCA was conducted using the prcomp routine from R 3.3.3 (R Core Team, 2017). Papers were classified as controversial when they evoked critical comments and discussion in the peer reviewed literature., blogs were colour coded using the results of a hierarchical cluster analysis (Ward.D2 method from R 3.3.3, R Core Team, 2017). Datapoint[s] were slightly jittered to improve visibility of overlapping points.

The 182 vectors each consisting of the seven scaled and infilled and scaled again answers were passed through a sophisticated mathematical procedure to calculate a pair of coordinates for plotting each point on the graph. This should generate 192 points, right? Well, yes and no. Principal components have the property that if all of the answers are identical for two blogs or papers, then the coordinates for those sources will be exactly the same and one point will cover the existence of the other when plotted.  Since there are only 25 distinct sets of answers, only 25 points will actually show on the plot.  I have added a fifth category consisting of several points which were shared by Pro blogs and Pro papers.


So how did the authors create the plot near the top of the post.  The last line of the quoted text provides the answer for that question . “Datapoint[s] were slightly jittered…” For those not familiar with this concept, “jittering” is the addition of random amounts to each coordinate of overlapping points  for the purpose of causing a slight separation . I would suggest that in this case “slightly” is in fact a gross understatement.   The relatively large amounts added to each coordinate create a very different impression of a data set with sufficient information and discriminatory power to justify being  real  “science”, something that clearly is not the case for this data.  Furthermore, it appears that all of the points were treated in this fashion including the ones that were not covered by any of their neighbors and therefore should have been left alone.

Figure 1 also has some problems, but this post is long enough.

The data and the statistical aspects of this paper  are lame lipstick for a propaganda attack on everyone who does not share the beliefs of the authors.  It is sad that cursory peer review persists in the climate change world allowing  incompetent papers to pass through over and over again.

The supplementary paper can be found here.

The data for the paper is here.



  1. eloris
    Posted Dec 18, 2017 at 12:54 PM | Permalink | Reply

    “Internet blogs have strongly contributed to this consensus gap by fomenting misunderstandings of AGW causes and consequences.”

    True – for instance, “Internet blogs” pretended for years that MBH 1998 was serious science, including a major internet blog at http://www.ipcc.ch . Once you figure out what actually went on, you realize that something like that slipped through every stage of the process, and you realize that they went on pretending for years and years and years that it didn’t, and in a lot of ways they still are so pretending… then yes, there grows a “gap” between what any sensible person believes and what comes out of their mouths.

    Other than that, it seems like this paper proved that warmists believe that polar bears are endangered and non-warmists don’t. In other news, polar bears execute #2 on the melting ice floes. The rest is just tendentious labeling (warmists are “science-based”).

  2. Curious George
    Posted Dec 18, 2017 at 1:29 PM | Permalink | Reply

    Instead of a correct term “principal component analysis”, authors use a “principle component analysis”. The rest of the paper is equally reliable.

    • Martin A
      Posted Dec 20, 2017 at 4:10 AM | Permalink | Reply

      “Principle” Teehee

      • dca
        Posted Dec 21, 2017 at 3:32 PM | Permalink | Reply

        When I googled principal vs principle, I found:

        principal – Chief, main, premier, leading, first
        principle – Rule, Axiom, Precept, Doctrine, Moral

        I believe the really did mean “principle”.

  3. joe
    Posted Dec 18, 2017 at 2:15 PM | Permalink | Reply

    “I have had undergraduate students who have done more professional work designing a study such as this after taking a single elementary statistics course.”


    Regarding the criticism of Susan Crockford because she hasnt had any “peer Reviewed research ” on poar bears. – I am a CPA that has been called as a witness to rebut “expert opinions” in court. While I am not an “expert” or “peer reviewed expert” on any of the topics, The courts have always accepted the logic and math erros I have pointed out based on a “general knowledge of the subject matter. I would suspect that Susan crockford’s level of knowledge is at least at the level of general knowldege, which makes her more than qualified to point out the errors.

    The last point – Skeptical science ran this article Nov 30th. The focus of the article was science denial, not on the actual science.

  4. Paul Courtney
    Posted Dec 18, 2017 at 2:41 PM | Permalink | Reply

    Sounds like they just bought a “principle [sic] components analysis” app for their iphones, and had already used it to re-organize all their closets and pantry shelves (avoiding “denialist” organizing methods of course). Maybe they wanted to attack Dr. Crockford (they did), but maybe they just wanted to show off the new app!

  5. joe
    Posted Dec 18, 2017 at 2:44 PM | Permalink | Reply

    One observation from the warmists – They acknowledge the polar bear numbers are up over the last 30-40 years, but they point out that there has been an observed decrease in weight/body fat of the polar bears, hence a reduction in habitat and food supply. That is also a common occurance when there is an overpopulation problem. While not knowing the cause, (if in fact true), the warmists do not address this issue and instead revert to the obligitory “climate change culprit”

    • Posted Dec 21, 2017 at 2:29 AM | Permalink | Reply

      It’s possible the milder winter allows skinnier bears to survive, this causes a skinnier population average of a larger population. (Medium Confidence).

      • Jeff Norman
        Posted Dec 24, 2017 at 12:57 PM | Permalink | Reply

        I was thinking the same thing.

    • mpainter
      Posted Dec 21, 2017 at 4:21 AM | Permalink | Reply

      One would need detailed information on the methods employed by researchers in obtaining weight data. Younger bears weigh less. Females weigh less. As do aged bears. As do all bears in the spring before they have gorged on too many seal pups. It would be easy to rig resultz to achieve an alarmist talking point.
      And right, I am very skeptical of what passes for science amongst the warmers.

  6. Don Keiller
    Posted Dec 18, 2017 at 5:53 PM | Permalink | Reply

    Are Harvey et al trying to emulate Lewandowski for outright mendacity?
    Is there a “Climate Science” prize for the most puerile work published?
    How on Earth does this rubbish get published?

    • Posted Dec 18, 2017 at 9:38 PM | Permalink | Reply

      lewandowsky, is one of the authors.

      • eloris
        Posted Dec 19, 2017 at 7:47 AM | Permalink | Reply

        Of course he is.

      • Don Keiller
        Posted Dec 19, 2017 at 11:30 AM | Permalink | Reply

        That is a surprise!

  7. Posted Dec 18, 2017 at 6:51 PM | Permalink | Reply

    Reblogged this on ClimateTheTruth.com.

  8. observa
    Posted Dec 18, 2017 at 7:05 PM | Permalink | Reply

    I can see only one way to settle this science is a democracy debate with their fuzzy numbers. They need to interview the polar bears for their opinions. The proxies for yes and no answers to the multiple choice questions should be of great interest to us all and the betterment of science.

  9. Peter Roessingh
    Posted Dec 18, 2017 at 7:51 PM | Permalink | Reply

    I am interested in the conclusion that people here would draw from the graph without jitter. What is the message of this graph?
    Does it differ form the original in a meaningful way?

    A lot of critical remarks are made about the methods, but not a single conclusion beyond “this is really bad” is drawn.
    If it all is so wrong and so bad, how would the true graph look? What would the message be? And for those who do not like complicated methods, what is the message of a simple plot of the raw counts?

    Is there anybody who can provide an analysis that shows how all the “mistakes” lead to a different conclusion? What would that be?
    I am going on holiday and will not respond here anymore, but I am really amazed by the apparent inability to look at the larger picture.


    • Posted Dec 19, 2017 at 12:44 AM | Permalink | Reply

      Peter, I think the implied criticism is that the categorization offers no room at all for subtlety or the real nature of a genuine scientific debate. There are other errors that are slanderous, such as categorizing blogs as “denialist” when they accept the fundamentals of the greenhouse effect. This paper is not about science at all, its about smearing Susan C. and those who dare to cite her.

    • RomanM
      Posted Dec 19, 2017 at 9:38 AM | Permalink | Reply

      The graph without jitter tells you that the data on which it is based lacks the ability to discriminate between positions taken on blogs and in papers because there is insufficient information in the data set to make it possible. All of the 192 observations have been shoehorned into a very small number of categories due to the poor design and limited breadth of the data collection process.

      You do realize that the authors would have created the “Actual Figure 2” plot before deciding that it did not fit their message. The amount of jitter is controlled by a parameter in the procedure which was chosen by them for the desired effect that the underlying data was not several peas in a proverbial pod. If they had wanted to show the “true graph” reflecting the data as it actually was, they could have plotted the 25 points with symbol size proportional to the frequency of the points as show in the blog post – a much truer picture.

      In the Supplementary document, the authors state “Blogs were assigned ‘science-based’ and ‘denier’ categories on the basis of their positions taken relative to those drawn by the IPCC on global warming (e.g. whether it is warming or not and the anthropogenic contribution).” It is amazing that ALL of the 45 “Skeptic Blogs” took exactly the same positions and all of the AGW blogs and papers were identical in theirs. My blog world experience has been that there is a broad spectrum of views which the authors simply ignored because they did not want to see the “larger picture”. This isn’t science – it’s propaganda.

    • Richard S J Tol
      Posted Dec 19, 2017 at 1:16 PM | Permalink | Reply

      With jitter, Fig 2 suggests that there are many, nuanced positions.

      Without jitter, Fig 2 reveals that there are only a few, stark positions.

      On a topic as complex as this, there are of course many, nuanced positions. The jitter thus conceals the poor quality of your data.

    • hanserren
      Posted Dec 20, 2017 at 12:26 AM | Permalink | Reply

      Of course you can use a cannon to kill a mosquito, the question here is is not that PCA works, but if you should use PCA in the first place on such a trivial dataset.

    • joe
      Posted Dec 20, 2017 at 2:20 PM | Permalink | Reply

      Peter – what is my take on the larger picture – As a layman, I recognize climate science is quite complex, lots of math, lots of statistics, etc. We are asked to accept a tremendous amount of the science based on the quality of the scientists work. To what extent should relience be place on the complex issues when it is easy to poke holes on the quality of the easy stuff.

    • Posted Dec 21, 2017 at 2:32 AM | Permalink | Reply

      Conclusion: Crockford has the proof she needs to sue the authors for slander.

    • Posted Dec 22, 2017 at 7:00 AM | Permalink | Reply

      Peter Roessingh: thank you for coming to comment here at this scientific (or ‘science-based’) blog, where I’m sure you will be treated with respect and courtesy. I’m a non-statistician and I think your question is a fair one. When I looked at your Fig 2 I noticed that there were many green symbols bunched close together. I assumed there must be be some differences between them. But I now learn that they mostly represented a single point but had been shifted so that each was separately visible. As an environmental scientist I’m used to graphs on which data points are plotted as precisely as possible, so I was indeed misled by the jittering, which for me was an unfamiliar procedure until Roman explained it. But now I know that jittering is an accepted practice in sociological publications I’ll be on the look out for it in future. In this case it made little difference: the paper still tells me nothing about polar bears or hazards thay may face. But I don’t think that was its purpose.
      Regarding the big picture: the overall impression I get is that polar bears are doing pretty well in their icy wastes. During the last half-million years they’ve survived several glacials (which must have been really tough) and several interglacials.
      Enjoy the holiday! I look forward to your next comment here.

  10. golf charlie
    Posted Dec 18, 2017 at 8:05 PM | Permalink | Reply

    One of the intentions of Harvey et al 2017 was to demonstrate the reliability of the Blogosphere.

    The Climate War has developed, not necessarily to Mann’s advantage.

    As Peer Review by Hockey Team Consensus Experts has been so poor, assessing Harvey et al 2017 could be used as a Basic Test of Professional Competence, for any Red Team or Blue Team, taking part in a future debate.

  11. Posted Dec 18, 2017 at 8:10 PM | Permalink | Reply

    Reblogged this on Climate Collections.

  12. Posted Dec 18, 2017 at 8:48 PM | Permalink | Reply

    Figure 2 is a smoking gun. No rational group of scientists discussing a topic as like bear populations would have such a tight grouping. #NotScience The green triangles piled on top of each other show that consensus, not science reign in the land of polar bear studies.

    • Posted Dec 18, 2017 at 9:53 PM | Permalink | Reply


      Especially considering that the only reason those green triangles are not just a few triangle positions where all of the green triangles stack, Steve found where Harvey et al identifies those data points as having been “jittered”, in order to separate their plotted position.

      As Steve points out,

      “For those not familiar with this concept, “jittering” is the addition of random amounts to each coordinate of overlapping points for the purpose of causing a slight separation.
      I would suggest that in this case “slightly” is in fact a gross understatement.
      The relatively large amounts added to each coordinate create a very different impression of a data set with sufficient information and discriminatory power to justify being real “science”, something that clearly is not the case for this data.
      Furthermore, it appears that all of the points were treated in this fashion including the ones that were not covered by any of their neighbors and therefore should have been left alone”

      A truly bad lipstick job.

      • RomanM
        Posted Dec 20, 2017 at 4:14 PM | Permalink | Reply

        Not Steve. 😉

        • Posted Dec 20, 2017 at 7:24 PM | Permalink

          My error Roman.

          Later on, I was reading Susan Crockford’s site when I discovered my error there. Realizing that I needed to get back to Climate Audit and apologize.

          My sincerest apologies!

          Excellent analysis and elucidation, RomanM!

      • Streetcred
        Posted Dec 21, 2017 at 11:49 PM | Permalink | Reply

        Theo, another reason the green triangles are so closely grouped is because the majority of them are written by the same cabal of authors … must have required a lot “jittering” to separate those papers on the graph !

      • jackbenimble
        Posted Jan 1, 2018 at 11:05 AM | Permalink | Reply

        The reason all the triangles stack is the vast majority of them were all written by the same very small group of authors.

  13. AntonyIndia
    Posted Dec 18, 2017 at 9:14 PM | Permalink | Reply

    What was Micheal E. Mann’s contribution here? He is one of the 14 co-authors.

    • DaveS
      Posted Dec 19, 2017 at 7:19 AM | Permalink | Reply

      His statistical expertise, obviously 🙂

      • S. Geiger
        Posted Dec 20, 2017 at 3:31 PM | Permalink | Reply

        or, lead graphics ‘trick’ designer, perhaps.

    • eloris
      Posted Dec 19, 2017 at 12:56 PM | Permalink | Reply

      Of course he is.

  14. Jeff Alberts
    Posted Dec 18, 2017 at 9:25 PM | Permalink | Reply

    “or that the bears might be able to adapt as they have for centuries.”

    Or even for a couple million years…

  15. cRR Kampen
    Posted Dec 19, 2017 at 8:31 AM | Permalink | Reply

    “Or even for a couple million years…” – https://en.wikipedia.org/wiki/Polar_bear#Taxonomy_and_evolution
    Facts be damned, eh.

    • Posted Dec 19, 2017 at 12:48 PM | Permalink | Reply

      The polar bear is a white grizzly, hardly a different species. Just like you, I suspect, are a white African.

      • mpainter
        Posted Dec 19, 2017 at 2:34 PM | Permalink | Reply

        Actually, the brown bear. DNA studies are not fully conclusive whether polar bears are a species distinct from Brown bears. It really depends on how the principle of “variation within the species” is applied and this application is simply a judgment call. Polar bears can legitimately be viewed as a specialized race of brown bear. The two mate and produce sexually viable offspring. Susan Crockford believes them to be separate species.

        • tty
          Posted Dec 25, 2017 at 7:27 PM | Permalink

          That two species can hybridize and have viable offspring does not mean that they are not separate biological species, unless they actually do bybridize to a significant extent, which grizzlies and polar bears don’t.

          An example: all large falcons (peregrine, gyr, prairie, aplomado, saker, jugger etc) can hybridize and have fertile offspring, as proven by falcon breeders, but they never, or extremely rarely, do so under natural conditions. The same is true for e. g. geese and Anas ducks.

        • mpainter
          Posted Dec 25, 2017 at 7:45 PM | Permalink

          I don’t disagree with that; however, geographical isolation prevents hybridization of polar bears and Brown bears. Genetic studies indicate such hybridization in the past, however, according to i-net sources. Presumably this occurred during a warmer interglacial than our present, when their habitats overlapped. Let the polar bears and the brown bears tell us if they they are different species. I do not hybridize with Yakuts, but that doesn’t mean we are different species.

        • mpainter
          Posted Dec 25, 2017 at 9:07 PM | Permalink

          But geese and ducks? That I do not believe.

        • tty
          Posted Dec 26, 2017 at 12:51 PM | Permalink

          I didn’t mean that geese hybridized with ducks, but essentially all geese can hybridize with all other geese, even Branta geese with Anser geese, thought in these particular cases the offspring is usually sterile. In the same way essentially all Anas ducks can hybridize with each other.

          And as a matter of fact goose/duck hybrids apparently do occur in rare cases:


      • barn E. rubble
        Posted Dec 20, 2017 at 9:41 AM | Permalink | Reply

        RE: “The polar bear is a white grizzly, hardly a different species.”

        Really? Perhaps you should try and get a polar bear to jump thru a hoop, ride a bike, or better, try and wrestle one. Choose wisely, as you’re unlikely to get a second chance. They’re just not into it. Polar bears are not ‘Gentle Bens’ by any stretch of the imagination. The term, ‘Too Tuff To Tame’ comes to mind. Altho I must admit they do look especially cuddly.

    • hanserren
      Posted Dec 20, 2017 at 12:29 AM | Permalink | Reply

      Remko wat was exactly your contribution to the publication?

  16. Clifford Eddy
    Posted Dec 19, 2017 at 10:32 AM | Permalink | Reply

    Susan J Crockford. Her recently issued book on Polar Bears is well illustrated and well documented [15 pages of references]. The clarity and beauty of her writing should be a goal for all others who write about science.
    The polar bear population has remained at about 25,000 to 30,000 for the past few decades. They survived warmer [ medieval warm period] and colder [little ice age] periods. Her book is so clear and so well documented that no one has, so far, questioned her science. However in characteristically pusillanimous form, warmers have attacked her without any basis, Can anyone doubt the e,,l nature of her attackers?

  17. golf charlie
    Posted Dec 19, 2017 at 11:21 AM | Permalink | Reply


    “Co-author Peter Roessingh, researcher at the UvA Institute for Biodiversity and Ecosystem Dynamics (UvA-IBED) in the research department Evolution & Population Biology, contributed to the statistical analysis. He explains: ‘Although it seems almost silly to apply statistics to a dataset with such a clear signal as this, we thought it was important to stay as objective as possible in this highly ‘polarised’ field. A large fraction of the information available to the general public has no scientific basis. The main message of the paper therefore is that scientists should get more vocal in the public domain and directly counter misinformation.’ ”

    Does Harvey et al 2017 counter misinformation?

    • Paul Courtney
      Posted Dec 22, 2017 at 7:02 PM | Permalink | Reply

      I join in thanking Peter Roessingh for asking, and hope he at least returns to see the answers provided. He indicates that he will not return for comment, but I hope he reconsiders and returns to answer charlie’s legitimate and respectful question. And please just one more: what is the message of the chart in your article, with jitters?

    • ABaum
      Posted Jan 1, 2018 at 2:25 PM | Permalink | Reply

      As a non-scientist, I really failed to see the point of the paper beyond stating the obvious, warmists believe in warming and “deniers” don’t. Singling out citation of one particular author as evidence of anything seems a bit unbalanced, especially considering citation is not the same as endorsement.

      Also, how could the warmists possibly be “more vocal in the public domain” than they already are? “An Inconvient Truth” gave them a huge voice but, in their haste to drum up funds for their carbon trading schemes, they presented doomsday scenarios that did not materialize and completely undermined their own narrative. Since that didn’t work, it now sounds like what they’re really aiming for is to be the only voice.

  18. Richard S J Tol
    Posted Dec 19, 2017 at 1:29 PM | Permalink | Reply

    First complete draft of my comment http://economicsofclimate.blogspot.co.uk/2017/12/lipstick-on-bear.html

    • RomanM
      Posted Dec 19, 2017 at 2:40 PM | Permalink | Reply

      Nice job, Richard! Very succinctly put in a more “academic” style.

      I especially liked the plot which indicates the actual values along with the frequency of the value.

      • Richard S J Tol
        Posted Dec 19, 2017 at 3:06 PM | Permalink | Reply


        • Posted Dec 20, 2017 at 11:23 AM | Permalink

          My comment failed to post at your blog. So I’ll leave it here:

          There is an inconsistency regarding common papers. You write, “Of the 86 “majority view” papers, 39 were authored by Steven Amstrup, Rascha Nuijten or Ian Stirling… Another 13 were authored by Andrew Derocher…” While Shub wrote, “Of the remaining 86, 60 are authored or co-authored by Stirling or Amstrup, or Derocher.”

        • Richard S J Tol
          Posted Dec 20, 2017 at 1:59 PM | Permalink

          Thanks Harold.

          I note that my numbers are indeed somewhat different from Shub’s and Roman’s. Will double-check.

        • RomanM
          Posted Dec 20, 2017 at 4:04 PM | Permalink

          There is no inconsistency here.

          I (and probably Richard as well) counted the papers as they were given in the data set. I used a procedure in R to count the number of papers in which one or more of the three names were listed as authors of the papers and got a total of 52. However, a number of papers had only one or two names followed by an “et al.” designation so I then went to the Supplementary paper which provided a more complete author list. These produced eight more papers in which the Big Three were listed for a total of 60.

          My guess was that Shub counted them directly from the Supplement document so he did not have an intermediate figure.

    • Posted Dec 19, 2017 at 2:59 PM | Permalink | Reply

      You can go to their code and set jitter to 0.01 or some suitable value to see the same effect as shown above. There’s no position or a range of view, only a tiny focused dot.

    • Posted Dec 24, 2017 at 11:17 AM | Permalink | Reply

      Richard, further on your comment:

      You write, “One variable denotes citation of Susan Crockford. This is recorded as a binary variable, that is, no distinction is made between mentioning her work in passing, criticizing her work, and uncritically adopting her position.” I think this is not correct.

      The paper alludes to this variable in the statement “Approximately 80% of the denier blogs cited here referred to one particular denier blog, Polar Bear Science, by Susan Crockford, as their primary source of discussion and debate
      on the status of polar bears.”

      This is suggestive that the binary variable is whether the authors consider Crockford’s work to be the blog’s primary reference with respect to polar bears. Looking at their data set, of the 45 blogs with position evaluated as “contra”, 35 are coded as “yes” for the Crockford variable, 10 as “no”. That’s close to 80%, so it seems to cement that interpretation.

  19. mpainter
    Posted Dec 19, 2017 at 2:17 PM | Permalink | Reply

    From the abstract:

    ” To counter misinformation and reduce this gap, scientists should directly engage the public in the media and blogosphere.”

    ### ### ###

    Blogosphere? Slim chance of that. It would go very badly for the Cause. They have no rebuttal for Crockford’s science.

    This paper is a transparent attempt to revive the fallen polar bear icon. Their cause is foundering and they desperately need to boost it. One can expect more of these sort of thinly disguised propaganda pieces.

    • Streetcred
      Posted Dec 21, 2017 at 11:55 PM | Permalink | Reply

      Indeed, it seems clear that Mikey Mann is changing horses and climbing onto the Polar Bear boondoggle.

  20. Posted Dec 19, 2017 at 2:23 PM | Permalink | Reply

    Reblogged this on Quaerere Propter Vērum.

  21. mpainter
    Posted Dec 19, 2017 at 2:50 PM | Permalink | Reply

    One falsehood on figure 2 : “sea ice declining”
    In fact the decline in Arctic season’s end sea ice extent ended in 2007, as now has become apparent. The last ten years have seen a fluctuation of this extent about a new mean. “Declining sea ice extent” is another climate myth that is perpetuated by studies such as the above.

  22. Chuck L
    Posted Dec 19, 2017 at 6:30 PM | Permalink | Reply

    This reminds me strongly of Cook’s “97%” paper. Anyone else think so?

    • joe
      Posted Dec 19, 2017 at 6:57 PM | Permalink | Reply

      There is 97% concensus among those of us who agree with us.

  23. hanserren
    Posted Dec 20, 2017 at 1:12 AM | Permalink | Reply

    I don’t know if this already has been mentioned but the argument of Crockforf in fact goes like this: arctic summer ice is behaving worse than the worst case IPCC scenario, but this low ice has no measurable effect on the polar bear population, it is thick spring fast ice that has a detrimental effect. All blogs that cite Crockford, however, share the opinion that the trend in summer ice has lessened, hence the blogs that cite Crockford don’t agree with Crockford on the ice status.

  24. mpainter
    Posted Dec 20, 2017 at 8:25 AM | Permalink | Reply

    From the head post:

    In line with the high standards of climate science “communication”, there are over 50 occurences of various forms of the derogatory labels “denier” or “deny” in a mere five pages of text and two pages of references.

    ### ### ###

    Including one instance in the title of the study and in three of the seven sentences of the abstract. Thus the fourteen co-authors convince themselves of the worthiness of their arguments.

    • Caligula Jones
      Posted Dec 20, 2017 at 4:18 PM | Permalink | Reply

      Yes, reminded me of the book “Lies: And the Lying Liars Who Tell Them” by someone named Al Franken. Whatever happened to him?

  25. golf charlie
    Posted Dec 20, 2017 at 10:05 AM | Permalink | Reply

    Crockford and Polar Bears demonstrate resilience, that exceeds the Consensus poorly Peer Reviewed Pre-Determined Conclusions.


    Crockford, S.J. and Geist, V. 2018. Conservation Fiasco. Range Magazine, Winter 2017/2018, pg. 26-27. Pdf here.


    Richard Tol notes that BioScience do not require the attribution from the “authors”, but Mann takes credit for the “Serengeti Strategy”.

    The “Polar Bear Expert Strategy” is one that more Climate Science Experts should be encouraged to use.

    • Streetcred
      Posted Dec 21, 2017 at 11:58 PM | Permalink | Reply

      For his sake, I hope that Mann is not trying to usurp my Wildebeest Principal … it also originates from the Serengeti … mind you, my Wildebeest Principal is supported by Mann’s behaviours through qualitative research methods.

  26. Luke Warmer
    Posted Dec 20, 2017 at 10:46 AM | Permalink | Reply

    I don’t get it. There was graph and official statistical terms and all that and they paper had lots of authors and heck, everybody knows the denialists are wrong. Why is this not a robust sciencey application of data?

  27. golf charlie
    Posted Dec 20, 2017 at 11:55 AM | Permalink | Reply

    Luke Warmer, Polar Bear Experts trusted Climate Science Experts and vice versa. They united the 97% Consensus to test the extent of Confirmation Bias and Conspiracy Ideation, and provided Peer Reviewed evidence to support their conclusion.

    The Law of Unintended Consequences has a new Legal Precedent, that will entertain Politicians, Scientists and Lawyers.

    The robustimess of Climate Science remains unchanged

  28. golf charlie
    Posted Dec 20, 2017 at 12:55 PM | Permalink | Reply

    Luke Warmer, with Lewandowsky’s help, Harvey et al decided to prove the extent of Confirmation Bias and Conspiracy Ideation that exists within all 97% Peer Approved Consensus led Blogs and MSM.

    Result? 100% gullible.

  29. JEM
    Posted Dec 20, 2017 at 3:38 PM | Permalink | Reply

    There were 13 of them, and Lewandowsky.

    There’s no ‘climate science’ in this, no ursine biology, no arctic anything. This is a couple guys sitting around doing google searches and fiddling with spreadsheets until they come up with something that only stinks a little bit.

    It smells, as geoff said, like our friend the roaming Australian. And why would anyone put their name on something like this without a pre-commitment from some journal editor that he’ll publish whatever – literally whatever – you give him?

    • tty
      Posted Dec 25, 2017 at 7:37 PM | Permalink | Reply

      And also promises to use reviewers who don’t know how to spell “principal component analysis”.

  30. nvw
    Posted Dec 20, 2017 at 7:01 PM | Permalink | Reply

    I’m not questioning the statistical analysis, the jitter of the PCA and the like presented in this post. The paper is junk. There are many ways to identify a poorly designed and implemented analysis and I confess my statistical skills are less than others, but in much the same way Justice Stewart replied about pornography that “I know it when I see it” my ah-ha moment when it was pointed out the Harvey SI list of blog sites supporting AGW included the York Blog. So what is the York blog? It is the site for the York Daily Record a local newspaper in Pennsylvania. And what is the connection of the community of York, PA with polar bears? Well, it turns out that the local youth hockey team are called the York Polar Bears.
    So 14 authors diligently analyzing the PCA of arctic ice and polar bears think the Yorkblog.com is relevant. And this is peer-reviewed science.

  31. Kozlowski
    Posted Dec 20, 2017 at 10:00 PM | Permalink | Reply

    I’ve noticed that anything from Lewandowski or Oreskes is essentially political theater. Made-to-order “science” specifically designed to have a political impact. Always look at the timing of these papers for discovering the underlying goal of what they hope to accomplish.

    • bitchilly
      Posted Dec 23, 2017 at 12:28 PM | Permalink | Reply

      “political theatre” . that is an interesting way of saying total crap kozlowski. if nothing else lewpaper and oresekes are consistent.

  32. hanserren
    Posted Dec 21, 2017 at 12:16 PM | Permalink | Reply

    Apparently the url for yorkblog in the supplementary infirmation is incomplete
    It should be this: http://www.yorkblog.com/hot/

    This is a so called “community blog”

    Community blogs are written by members of the York County community who are not staff members of the York Daily Record/Sunday News, or, in some cases, staff members writing outside of their Daily Record/Sunday News affiliation.

    • mpainter
      Posted Dec 21, 2017 at 3:33 PM | Permalink | Reply

      Thanks, Hans, for the link. Now we can guage what the authors consider to be an AGW blog, very instructive.
      Indeed, it is the York community blog that one Keith Peterman has used for posting some alarmist diatribes.
      An excerpt from his December 15 post:

      “Consider the increase in number and intensity of Atlantic hurricanes. Harvey, Irma, and Maria ravaged Texas, Florida, Puerto Rico, and numerous islands. We can expect this to be the ‘new normal’.”

      Peterman seems to post about two or three times a month. None have prompted comments. Perhaps these posts are ignored by the faithful of York, Pennsylvania. And elsewhere.

      • D. J. Hawkins
        Posted Jan 12, 2018 at 8:55 PM | Permalink | Reply

        It is not that his blog does not attract comments, it is that commenting is turned off. One shouldn’t read too much into that I suppose. Moderating comments can be a real time suck. I mean, it’s not like someone is trying to avoid having his world view challenged by facts, right? 😉

  33. golf charlie
    Posted Dec 22, 2017 at 8:32 AM | Permalink | Reply

    “Fresh” analysis now released


    But the reason for the rush through Peer Review to attack Crockford remains unclear


  34. hanserren
    Posted Dec 22, 2017 at 11:43 AM | Permalink | Reply

    Still puzzled why zero publications by Greg Thiemann were included in the consensus.

    • Posted Dec 22, 2017 at 12:32 PM | Permalink | Reply

      Hans –
      I count 9 papers by Thiemann in their database, all pro-consensus.

      • hanserren
        Posted Dec 22, 2017 at 12:47 PM | Permalink | Reply

        I stand corrected

  35. joe
    Posted Dec 22, 2017 at 2:00 PM | Permalink | Reply


    More humor – A science blog is one that says the arctic ice is decreasing since the 1970’s

    A denier blog is one that says the arctic ice is decreasing since the the 1970s with flat/holding relatively steady or slightly increase over the last 5-6 years.

    • hanserren
      Posted Dec 22, 2017 at 2:50 PM | Permalink | Reply

      Where does Susan Crockfird fit in when she says that 2007 and 2012 was unprecedented decreasing ice with no effect on polar bear numbers?

      • mpainter
        Posted Dec 22, 2017 at 4:24 PM | Permalink | Reply

        Dr. Crockford fits into one of the red (stop signal red) triangles with the downward pointing tip (as in thumbs down), whereas the consensus views fit into the green (as in go) triangles with the upward pointing tips (thumbs up). The denier blogs are Amber (caution light Amber) squares.

        This comment should not be taken as a joke; I do not believe that the color scheme and symbol selection is by accident. Testimony by a psychologist who specializes in marketing studies could point all of this out to a court, authoritatively.

  36. John F. Hultquist
    Posted Dec 23, 2017 at 6:01 PM | Permalink | Reply

    A much greater problem was the lack of diversity in the authorship . . . papers might be virtually identical given that the same people are beating the same drum repeatedly.

    I’ll use an unrelated subject and an old (late 1960s) publishing series to confirm this. I am well acquainted with a researcher, Full Professor, and eventual university president that used one research endeavor and has about 2 dozen articles published from that one activity. Grad students at the time made up a bunch of similar titles and made a 40 page addition to the person’s resume. At the yearly Christmas party funny gifts were given to the profs (think rose colored glasses; cheap wine to the connoisseur, and so on). The augmented resume was presented to the Prof. to “save you time doing it yourself.”
    [I, of course, had nothing to do with any of this.]

  37. MrPete
    Posted Dec 24, 2017 at 9:09 AM | Permalink | Reply

    Roman, your unjittered plot would be even more informative if you could tie the size and/or color transparency of the icons to their frequency (aka weight.)

    As given, the plot suggests that each icon carries the same weight. Of course, all but two “pro” and three “contra” icons would fade to insignificance if their weights were displayed.

    Such fun 🙂

  38. John M
    Posted Dec 24, 2017 at 11:33 AM | Permalink | Reply

    I saw this linked at RetractionWatch.


    “But my impression of a lot of research misconduct is that the researchers in question believe they are acting in the service of a larger truth, and when they misrepresent data or exaggerate conclusions, that they feel they’re just anticipating the findings that they already know are correct.”

    Legal disclaimer: This comment is simply an interesting observation based on the subject matter. Any resemblance to persons living or dead is a crying shame.

  39. RomanM
    Posted Dec 24, 2017 at 11:40 AM | Permalink | Reply

    This has already been done by Richard Tol on his web site and referenced above in his comment on Dec 19.

    As you suspected, the planned lack of ability for discriminating between subjects within the data set is clearly evident.

  40. RomanM
    Posted Dec 24, 2017 at 2:37 PM | Permalink | Reply

    This is a comment which I have posted on Bart Verheggen’s blog:

    The views expressed in my post on ClimateAudit still stand – this supposedly scientific “study” of the differences between Skeptic blogs and papers versus those advocating the Consensus narrative is a sham not worthy of publication in any selfrespecting journal. Had it been done properly, the methods for extracting the necessary information would have been sufficiently broad to examine the nuances of the views held within each group.

    Skeptic blogs are not identical in how the individuals from those blog perceive the Consensus doctrine. Many blogs discuss published scientific literature on specific aspects of the climate focusing on the interests and capabilities of their informal membership. The views espoused on a blog may vary on how much warming is taking place, on the amount possibly attributable to human activity or how the this may play out in the future. None of this is reflected in the data set because the way the data was gathered and coded made it impossible to do so. Similar criticism applies to the resultant data for the Consensus group unless the blog denizens and authors of the papers considered actually do form a monolithic collection of identically minded individuals repeating a narrow gospel. Richard’s plot above shows how narrowly both sides were shoehorned into narrowly prescribed positions.

    So why didn’t the authors of the paper actually do a proper job showing this diversity? The answer is that they intentionally did not wish to. First, this would require more work to carry out than was justified in creating a “scientific” veneer for the paper. Secondly, and most importantly, it would destroy the capability for using the phrase “denier blog[s]” 20 times in the short propaganda paper. If one is a “denier” of [fill in the blank], there is no need to pay attention to their argument – a popular debating ploy in climate discourse. Argument over…

    • Geoff Sherrington
      Posted Jan 1, 2018 at 5:18 AM | Permalink | Reply

      With inferential statistics, one tries to analyse a subset of a population.
      Can someone wiser than me explain what the main population is, in this paper? Thanks Geoff.

      • RomanM
        Posted Jan 1, 2018 at 11:48 AM | Permalink | Reply

        As far as I can tell, the closest that the authors get to specifying a “population” is in the abstract:

        Here, focusing on Arctic sea ice and polar bears, we show that blogs that deny or downplay AGW disregard the overwhelming scientific evidence of Arctic sea-ice loss and polar bear vulnerability.

        By implication, that population would be “blogs that deny or downplay AGW”. Of course, there are also the “scientific blogs” and the polar bear papers which need to be included in the mix as well so determining the exact population(s) is an exercise left to the reader.

        However, the question seems to be irrelevant since all of the data is gathered in an ill-described convenience sampling manner and none of the statistical analysis in the paper is of an inferential nature. Cluster analysis and PCA are used descriptively and no scientific conclusions should be drawn from them.

        The phrase “we show that” is a gross exaggeration under the circumstances.

  41. RomanM
    Posted Dec 24, 2017 at 2:41 PM | Permalink | Reply

    A second comment posted on Bart Verheggen’s blog:

    There is one more thing I have not mentioned earlier because with inadequate data it would have been a moot point. Principal Component Analysis (PCA) is a least squares based method which is useful for continuous measurement data and possibly count data, but not generally appropriate for categorical data. All of the data on which that procedure was used is categorical. Recoding it using numbers does not make it numeric so other procedures must be used. Rather than be accused of just being negative, I thought it might be helpful to provide some information to the authors on how a proper analysis might be done should they wish to redo the paper.

    When all of the variables are binary (i.e. two-valued), a suitable analytic methodology is Logistic PCA. It provides PCs, fitted and predicted values of similar sort as the PCA does for numeric data. The method is available in the R package logisticPCA. It is easy to implement and easy to work with the results.

    Unfortunately, the seven variables in the paper are not all binary due to the coding style used. In that case, one can use a more general procedure, Multiple Correspondence Analysis (MCA). This allows for more general categorical variables to be analyzed in a reasonable fashion with results such as those in PCA. The method is implemented in R in at least five different libraries. I ran the function MCA in the FactoMineR package and found it was also fairly easy to use. However, as in PCA, neither of these methods can correct for the lack of discriminatory power of the data from the paper in question.

    • joe
      Posted Dec 24, 2017 at 10:28 PM | Permalink | Reply

      here is statement posted at Skeptical science by bart Verheggen: https://www.skepticalscience.com/how-blogs-distort-sci-info-polar-bears-arctic.html#commenthead

      “Whatever your preference, the conclusion drawn from these figures is the same: there is a clear gap between the consensus in the scientific literature and science-based blogs on the one hand, and contrarian blogs on the other hand. We thank Roman Mureika and Richard Tol for underscoring the validity of our conclusion.”

      His statement doesnt reconcile/square with the statements by either Richard Tol or Roman Mureika

      Am i missing something in his response?

      • Taylor Pohlman
        Posted Dec 25, 2017 at 8:59 AM | Permalink | Reply

        Two things:
        1. Given that most of the ‘science-based’ papers were written by the same small set of authors, it’s not surprising that there is a gap, and
        2. Is the conclusion of the paper as he describes it (the ‘gap’) so trivial as to negate any rationale for publishing this in the first place? I can’t wait for the next ‘jittered’ plot of the wetness of water …

      • RomanM
        Posted Dec 25, 2017 at 11:19 AM | Permalink | Reply

        The existence of differences between the Skeptics and the Consensus is not in question. Climate Skeptics by definition are usually not in agreement with at least some of the conclusions posited by the the CC advocates while possibly accepting other parts of the Consensus as reasonable. Many discussions on the blogs show that this is indeed the case.

        On the other side,as Taylor has pointed out, the papers are centered around a small handful of leaders in a tightly knit group. De facto, they would also control research funding which induces other researchers to have views in accordance with the leadership and not to question the Consensus. The “Science” blogs merely repeat verbatim what they hear so there are no added differences there.

        The “clear gap” in the paper is a result of intentionally not gathering any real information about the two groups and and classifying them as (surprise, surprise) two distinct groups. The whole effort is just “lipstick” on a propaganda diatribe meant to demean Dr. Crockford and anyone who dares to listen to her.

        • mpainter
          Posted Dec 25, 2017 at 12:04 PM | Permalink

          It bears pointing out that this study is the work of “consensus” scientists (fourteen of them). It is a fair exemplar of what passes as peer reviewed “consensus” science, for which example skeptics are quite pleased to have.

          It also gave the authors the opportunity to use the word “denier” and its variants about fifty times, in the approved fashion of right thinking “consensus” types. One senses that these ganged up against Dr. Crockford in this way because there was nothing else for them to do.

          Bottom line: Consensus science pounds the floor and chews the carpet in angry frustration.

        • joe
          Posted Dec 25, 2017 at 2:38 PM | Permalink

          Roman _ I concur with the basic premise that the so called study is a combination of a hatchet job on S Crockford and consensus argument in favor of the “AGW science”

          My question is in reference to
          A) that you and R Tol “underscored the validity of their conclusion”

          That statement does not square with your response to the Harvey/Venheggen study

        • RomanM
          Posted Dec 25, 2017 at 3:59 PM | Permalink

          No, our statement doesn’t underscore the ***validity*** of their conclusion because their methods never properly assessed what the real differences might be. They were designed to produce as large a separation as possible between two narrowly defined groups. Our graphs merely emphasized how their “richly informative” graph was not what it seemed to be.

        • hanserren
          Posted Dec 25, 2017 at 5:52 PM | Permalink

          It’s simply their list who is naughty and nice.

          Merry christmas to you all,

      • Richard S J Tol
        Posted Dec 27, 2017 at 10:33 AM | Permalink | Reply

        Joe: This is rank dishonesty by Verheggen. He knows full well that neither Roman nor I underscore the validity of their study. We do the exact opposite.

        • joe
          Posted Dec 27, 2017 at 6:07 PM | Permalink

          Thanks Richard & Roman for the response – That was exactly my conclusion – couldn’t figure out why Verheggen would make that statement.

          Richard – I also saw your response at SkS. Counting 10, 9, 8 7 …. before you get banned. (or before your factually accurate statement gets erased)

  42. jeff Id
    Posted Dec 27, 2017 at 10:15 AM | Permalink | Reply

    I saw this thing earlier – couldn’t bother to read it. Hilarious analysis though.

  43. Posted Dec 28, 2017 at 10:29 AM | Permalink | Reply

    ‘…rank dishonesty by Verheggen.’

    It’s a form of tunnel vision. Bart and Peter are both afflicted by it.

    The technique employed in the paper is a Lewandowsky special. The primary difference PC1 between the so-called majority-view and skeptics is the very disagreement between each other. Of course, the two ‘positions’ will be opposed to one another. How would skeptics be skeptics if they believed everthing were skeptical about? The special form of reasoning is the conversion of this tautology into apparent data-based insight. As the authors admit, and as their PCA shows, there is a clear range of views on the survivability of polar bears, i.e, PC2 even in the self-selecting sample of polar bear literature. In other words, what action there is, is in PC1 and the differences in PC1 cannot be otherwise.

    There is another contradiction. Lewandowsky and colleagues attack skeptics for disagreeing with the purported majority-view and simultaneously charge them with using a ‘keystone domino’ strategy against polar bears in attempting to knock down its status in the global warming debate. If skeptics are to use a attack the keystone strategy, how would they do it if they completely agree with the ‘majority-view,’ as Bart Verheggen alleges they ought to?

    The simple point is that critics of science, and criticism of science cannot be defeated by argument from authority. If Harvey et al were concerned about the viewpoints of Susan Crockford, they should have taken up her arguments and addressed them directly, point-by-point, instead of attempting to ‘show’ and ‘prove’ that she completely disagrees with Stirling and Amstrup.

  44. ccscientist
    Posted Jan 2, 2018 at 10:35 PM | Permalink | Reply

    The claim, even if true, that Susan Crockford has not published much is irrelevant to the truth of her conclusions. If only well-published people could be believed, then young scientists could never get established.
    I was involved in editing a polar bear paper contra some of the authors listed in the paper Roman is criticizing–I was threatened that I should never let the paper in question get published. They called major newspapers to stir up trouble and reporters called me.

    • joe
      Posted Jan 3, 2018 at 10:35 AM | Permalink | Reply

      “I was involved in editing a polar bear paper contra some of the authors listed in the paper Roman is criticizing–I was threatened that I should never let the paper in question get published.”

      Somewhat similar story – A client of mine is research scientist dealing with a uncommon human eye disease. The bulk of animal research is done on mice. His research showed rabbits were a better species to experiment on for this particular disease. That research community behaved in similar fashion to anyone who disagreed with the consensus.

  45. Posted Jan 13, 2018 at 3:29 AM | Permalink | Reply

    Government benefits from climate alarm. So scientists in its pocket duly preach whatever supports it. This built-in bias is what causes the ‘consensus gap’.

    • Posted Jan 13, 2018 at 2:34 PM | Permalink | Reply

      I don’t think it’s that simple at all. It seems clear to me that scientists have their own political aims and goals. Global warming was a potential threat and, regardless of the strength of the scientific evidence, they wanted people, therefore, governments to act on it. This has all kinds of side (or not so side) benefits like pushing political (renewables, “saving the planet/environment”), financial (grant revenue), and personal (reputation and status) goals. Of course, you’ll find it difficult to get anyone to act (or give you money) when you can’t produce a credible threat so the “consensus gap” has been built around providing it. This is essentially what the late Steven Schneider laid out in his “famous” interview (the means justified the ends) and the hyping of results to get attention and benefits is nothing new to science.

      It’s also worth pointing out that while the governments hold the purse strings, it is usually panels of scientists that are responsible for deciding who gets that money, together with what gets published.

8 Trackbacks

  1. […] “Polar Bears, Inadequate data and Statistical Lipstick“ (18 Decemeber 2018, RomanM writing at ClimateAudit) […]

  2. […] figure of the same data as produced by RomanM at ClimateAudit, without information on sample […]

  3. […] figure of the same data as produced by RomanM at ClimateAudit, without information on sample […]

  4. By Klimaatkosten - on Dec 23, 2017 at 5:17 PM

    […] gelijk probeert te halen. Wij weten thans hoe verschrikkelijk mis de heren intriganten zaten. Zie hier, hier en […]

  5. […] https://climateaudit.org/2017/12/18/polar-bears-inadequate-data-and-statistical-lipstick/#more-23602 […]

  6. […] RomanM, December 28, 2017 in McIntyre […]

  7. […] Roessingh and Bart Verheggen gracefully shared data and code. I borrowed freely from comments by Roman Mureika and Shub Niggurath. Marco NN had useful comments on an earlier […]

  8. […] science pounds the floor and chews the carpet in angry frustration.” [mpainter, 25 December […]

Post a Comment

Required fields are marked *


%d bloggers like this: