the Air Vent

Because the world needs another opinion

Wegman and the ?

Posted by Jeff Id on May 21, 2011

Roman M, famous blogger and oft published professor, cursed in the eyes of cheerleaders for being afflicted with an unfortunate statistical ability, ;) has posted on the retraction of an 8 page 3 reference statistics paper by Edward Wegman.

Wegman and the Ankle-Biters

24 Responses to “Wegman and the ?”

  1. Jeff Id said

    I think readers should pay attention to the intent letter during submission. The paper was intended to take a baby step toward looking into a serious issue – biased peer review. In climate science, unlike biology, the result of a mistaken paper has little bearing on an individual life — except financially through means we have little control over.

    There is a missing feedback for bad work to the scientists, the result is a slap on the back for every warming result, and a punch for a non-warming one. En masse, it’s like adding a flame to a volume of gas.

  2. kuhnkat said

    Love the title Roman!

  3. kim said

    It’s doing the engineering on their boiler relief valves using ginormous computer programs evaluating heat and not pressure.
    ==============

  4. kim said

    Heh, Deep Climate is deeply not even wrong.
    =======

  5. Ted said

    With regards to the Wegman report.

    The concerted effort by the CAGW community to discredit Prof. Wegman continued until it seems to have resulted in the withdrawal of the social networking paper due to charges that some material in the paper was not properly referenced.

    (This to any sane human being is molehill made into a mountain by a desperate warming community)

    I believe this oversight can be simply rectified by addressing and crediting the material that represents a very small portion of the report, then resubmitting the Wegman report which is still valid.

    This lack of accreditation does not change the main premise or scientific facts, that there was questionable behavior and data massaging by Mann and company with the presentation of the hockeystick graph as toted by the IPPC/Gore and still defended today by the die-hard alarmist to this day!

    Nonetheless, nobody has demonstrated that the science in the paper has been faulty and, regardless of its demise, the fact stands that the original report and its conclusions regarding the flawed hockey stick cannot be impacted by this is any way.

  6. Jeff #1,
    I think readers should pay attention to the intent letter during submission.
    This “intent letter” seems to have been an email from Wegman to his friend the editor. There’s no indication of that intent to the reader. Here is the relevant journal contents page. It is presented as just a regular research paper listed under:
    Section II: Statistical Methodology for Data Analysis.

  7. Jeff #1,
    “The paper was intended to take a baby step…”

    Here is the Acknowledgement:
    “The work of Dr. Yasmin Said was supported in part by the National Institutes on Alcohol Abuse and Alcoholism under grant 1 F32 AA015876-01A1. The work of Dr. Edward Wegman was supported in part by the Army Research Office under contract W911NF-04-1-0447. The work of Dr. Said and Dr. Wegman was also supported in part by the Army Research Laboratory under contract W911NF-07-1-0059. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institute on Alcohol Abuse and Alcoholism or the National Institutes of Health.”

    I wonder if they conveyed to the sponsors that intent?

    I note “The content is solely the responsibility of the authors”, which sharpens the question – who are the authors?

  8. Duster said

    The pathetic part is that the published paper seems to have been bitten by the very same issues of “peer” review it proposed to analyze. Back in the day, it was not at all unusual for professors to take credit for a graduate student’s work – the reasoning apparently being the prof had taught the student everything the student knew. If lucky the student might get credit as a second author. An irritated student (or one who was convinced of the seriousness of AGW) might well set a professor up for a fall in just this manner, if the student was confident of gaining a degree before the “deadfall” was triggered.

  9. Jeff Id said

    Nick,

    I don’t think anyone is giving Wegman or Said a pass here on anything but I believe the copied info was from their improperly cited report to congress into this paper. It was also on the general background info. I’m sure you are also aware that grad students often aren’t coauthors. I was treated far better, and was coauthor of a paper as an undergrad student. It was actually a paper I never read until after publication.

  10. Jeff,
    On the recurring proposition that
    “It was also on the general background info”
    Well, Roman says:
    “The indication is clear that the paper is intended to present a simple application of the methodology to the wider statistical audience.”
    It’s a paper written with federal funding in a research journal. People are claiming credit for it. For what exactly? Its exposition?

    Well, example. Here’s Said et al:
    “The shape of the social network helps determine a network‘s usefulness to its individuals. Smaller, tighter networks can be less useful to their members than networks with lots of loose connections (weak ties) to individuals outside the main network. More “open” networks, with many weak ties and social connections, are more likely to introduce new ideas and opportunities to their members than closed networks with many redundant ties.. See Granovetter (1973).”

    And here’s Wiki 2006:
    “The shape of the social network helps determine a network’s usefulness to its individuals. Smaller, tighter networks can be less useful to their members than networks with lots of loose connections (weak ties) to individuals outside the main network. More “open” networks, with many weak ties and social connections, are more likely to introduce new ideas and opportunities to their members than closed networks with many redundant ties. In other words, a group of friends who only do things with each other already share the same knowledge and opportunities….”
    The Wegman report continued lifting from Wiki, though Said et al stopped there.

    They’ve added a reference, but that’s not where the text comes from. This is not just basic information – it’s exposition and argument. And they are claiming credit for it.

  11. Jeff Id said

    Nick,

    I think now, if you look back to the congressional report, you’ll find the wording is very close. I’m not interested in going back over it myself but my recollection is that it was text lifted from their previous work which was poorly cited so that in this paper, it is misreferenced.

    And that does read like background info to me.

    You know as well as I that this paper was published precisely because it was easy and often the number of publications a person has determines their value. They slapped together 8 pages and published a nothing –blah.

  12. “They slapped together 8 pages and published a nothing –blah.”
    Yes, I agree that this paper was not of high significance. But the same text that caused its withdrawal is in the Wegman report, only more so. So:
    “They slapped together 92 pages and published a nothing –blah.”?

  13. Jeff Id said

    Nick,

    Are there any specific statements in this paper you disagree with?

  14. RomanM said

    Nick #10

    “The indication is clear that the paper is intended to present a simple application of the methodology to the wider statistical audience.”

    It’s a paper written with federal funding in a research journal. People are claiming credit for it. For what exactly? Its exposition?

    Yes, for its exposition. If the application does not have sufficient novelty, it can be rejected. If it forms part of the research conducted by a researcher under a specific grant, then I see nothing wrong with the fact that the grant money is used.

    You seem to have a strange idea that only scientific material which is is acceptable to Nick can carry the label “research”. The main impetus for allowing such papers (often as shorter “notes”) was to include the work of applied statisticians who were outside of the academic environment. These were people who are not likely to publish Nick-approved style papers, but whose work and the technical problems they face can be innovative and interesting and worth learning about. In particular, such work could provide stimulus to new ideas for the hardcore researchers and ammunition for people teaching in the classroom. Is it worthwhile? I think so.

  15. RomanM said

    Nick #12

    Yes, I agree that this paper was not of high significance. But the same text that caused its withdrawal is in the Wegman report, only more so. So:

    “They slapped together 92 pages and published a nothing –blah.”?

    Good one, Nick! Social networking ~15 pages. All of the rest ~77 pages. You are rapidly morphing yourself into a common troll.

  16. Jeff Id said

    Roman,

    It is just his style. Nick likes to take the opposite side on most things. It’s no fun agreeing and Nick is doing the lawyer thing; looking for tiny keyholes to slip logic through that throws off the jury. I enjoy it sometimes because at least he can make you think. You’ll note he didn’t answer my question #13 — it was a lawyer style question. He knows full well the paper is accurate, yet likes to play the foil enough that he will write the rest.

    In my job, my role has become understanding and working with a wide range of personalities. IMHO the very fact that Nick is not a lawyer is an oxymoron.

    My guess was that he would find some nit-picky thing that he can disagree with in the paper, but who knows. Maybe we’ll see a whole deconstruction of the fiveish equations.

  17. Mark T said

    Such behavior is a pretty good indicator of his true character, Jeff. I’m not sure why he gets any respect at all.

    Mark

  18. Well, Jeff #16, as so often, is pretty much right. I am comfortable arguing a minority viewpoint, and am frequently in a minority here. But tAV isn’t the world, and the fact is that the paper has been withdrawn. So it’s not such an eccentric view.

    And Roman’s right (#14) in identifying that this kind of paper is not my cup of tea. It’s too subjective – I can’t see that anything has actually been proved. Would anyone like to suggest what has been proved?

    My preference doesn’t have to rule, but I think it is shared by readers of Stats journals. There’s about 2 pages with some maths, but I can’t see how it connects with the rest. Any help here? Then there’s all the black-square diagrams. That might be of some interest if it was shown that the patterns were actually representative of the groups described, but that is where the poor account of methodology fails. Let alone defining how people are allocated to those groups.

    I noted in Roman’s post where he said that the inadequate data description was OK, because it was developed in the Report. But that was only one of the four datasets.

    My point about raising Roman’s description of the paper as expository is that it is exactly the exposition that has been part-plagiarized. Folks say that the essence is untouched, but if you take that away, there’s little left.

    Then there’s that last bit about the fact that a paper warning of possible decline in peer review was really not reviewed at all. That might sound like point-scoring, but when you are struggling with a lot of subjective judgmental stuff, and such a clear contradiction is there, it’s hard to take seriously.

  19. Chuckles said

    Nope, just tedious.

  20. Jeff Id said

    Nick,

    Yup. I can’t disagree with any of that, well I could but don’t. No clue how the letters match the numbers. Easy review, little to conclude and some irony. A little Fe-ny for the skeptics. Like a well done steak, a bit of A1 sauce may be in order to make it palatable.

  21. Ruhroh said

    Jeff;

    With regard to
    ” In my job, my role has become understanding and working with a wide range of personalities. ”

    here’s an intriguing website about personalities.
    The good thing is they approach it all without the need to pathologize normal human variation.
    It took me awhile to accept the whole subselves model, but now I like it.

    http://sfhelp.org/gwc/if/letter.htm

    An amazingly crosslinked altruistic website.

    One other great resource for comprehending difficult people is the books at newharbinger.com .
    Basically, they have a ~$20 book for just about any syndrome, and it is usually pretty up-to-date with what will happen at $150 counseling sessions with a ~SOTA psych pro…
    The newharbinger search function is very weak, so you have to flog it more than is reasonable. Recently, to find the right book for a colleague whose teenbb had OCD issues, I had to separately explore adult (for which they had The OCD Workbook, and an outline of scripted visits for psych pros. Under ‘children’, they had ‘Helping Your Child with OCD’, and under Teens, they had ‘Breaking Free of OCD’.
    Anyway, I’ve had remarkable satisfaction in guiding co-workers to frameworks of understandings of familial issues…
    Best,
    RR

  22. stan said

    Nick makes a point at Roman’s that I think is likely wrong and ought to be examined much more closely. He tries to argue that Nature likely subjected Mann’s original paper to rigorous peer review because he was a nobody at the time. I call BS.

    Mann was responding to a plea from the big dogs in the cult that someone needed to find a way to get rid of the MWP. He delivered what they were looking for. Given how poor the work, Nature’s review couldn’t have been too tough. I suspect that there were a lot of people who were happy to see the MWP disappear and were anxious to see the paper get published. The celebration of Mann and the paper after publication demonstrates that.

    Also, Judy Curry has pointed out that she is curious how Mann became so influential in the IPCC as such a junior scientist. My own personal theory is that the hockey stick was Mann’s version of Wales (perhaps the movie could be titled “A Mann for All Seasons”). In any event, the history would seem to indicate that Nick’s assertion of rigorous peer review is unlikely.

  23. RomanM said

    Re: stan (May 23 09:26),

    I have replied to Nick’s comment at my site also.

  24. Kan said

    Interesting, the issue of plagiarism appears to have become a go to tool of politics. Following similar lines as the Wegman issue:

    In Colorado, the leading Republican candidate for Governor, Scott McInnis, was taken out of the race by an accusation of plagiarism last Aug.

    He was brought up on ethics charges before the state Attorney Regulation Counsel (he is a lawyer). Last Friday, the Attorney Regulation Counsel declined to discipline him due to a lack of “clear and convincing evidence” that he knew that the contents of a paper he authored for a foundation was a cut and paste job (lifted from the writings of a judge) by his paid researcher. The researcher had claimed he believed the text was in the public domain given

    The foundation claimed at the time that they did not know that he had engaged a researcher. However, it has come to light that Mr. McInnis did inform them, in writing, of the researcher, prior to taking the job. In addition, the researcher had been notified , in writing, that the work need to be original.

    Its a nasty game.

    http://www.scribd.com/fullscreen/56016081

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

 
Follow

Get every new post delivered to your Inbox.

Join 140 other followers

%d bloggers like this: