Why no Wegmania?

Posted on by

A colleague asks:

When I search the web, I find the story [of the article by Said, Wegman, et al. on social networks in climate research, which was recently bumped from the journal Computational Statistics and Data Analysis because of plagiarism] only on blogs, USA Today, and UPI. Why is that? Any idea why it isn’t reported by any of the major newspapers?

Here’s my answer:

1. USA Today broke the story. Apparently this USA Today reporter put a lot of effort into it. The NYT doesn’t like to run a story that begins, “Yesterday, USA Today reported…”

2. To us it’s big news because we’re statisticians. [The main guy in the study, Edward Wegman, won the Founders Award from the American Statistical Association a few years ago.] To the rest of the world, the story is: “Obscure prof at an obscure college plagiarized an article in a journal that nobody’s ever heard of.” When a Harvard scientist paints black dots on white mice and says he’s curing cancer, that’s news. When Prof. Nobody retracts an article on social networks, that’s not so exciting. True, there’s the global warming connection. I think it’s possible the story will develop further. If these statisticians get accused of lying to Congress, that could hit the papers.

Basically, plagiarism is exciting to academics but not so thrilling to the general public if no celebrities are involved. I expect someone at the Chronicle of Higher Education

3. One more thing: newspapers like to report things that are clearly news: earthquakes, fires, elections, arrests, . . . If criminal charges come up or if someone starts suing, then I could see the court events as a hook on which to hang a news story.

Any other thoughts?

8 thoughts on “Why no Wegmania?”

  1. Claiming something is true when it is false or unproven [painting mice], is much more serious to the public than claiming something is true when it is true – you just didn't discover it [plagarism]

  2. Yah, good point. And the Harvard profs who get in the news for plagiarism tend to be people who are already somewhat famous.

    By the way, the Wegman incident is more serious than "merely claiming something is true when it is true – you just didn't discover it." The issue is that Wegman and his team presented themselves as experts, then this incident reveals that they're not experts in their claimed areas of expertise, that, at best Wegman has no control over what goes out under his name.

  4. This goes beyond plagiarism. There's also the question of failure to subject the paper to serious review. So the issues is not merely, "true but they didn't discover it," but also "not rigorously reviewed and the research itself looks shoddy." See Vergano's USA Today bit about what experts on social network analysis say about the quality of the paper:

    But how good was the study? We asked network analysis expert Kathleen Carley of Carnegie Mellon to take a look at whether the CSDA study, a "bibliometric" critique of publishing links between climate scientists, was any good in the first place. "I see this paper as more of an opinion piece," Carley says, by email.

    Carley is a well-established expert in network analysis. She even taught the one-week course that one of Wegman's students took before 2006, making the student the "most knowledgeable" person about such analyses on Wegman's team, according to a note that Wegman sent to CSDA in March.

    Since Wegman's work is frequently cited in the news media as proof that there's a big problem with Mann's paleoclimatology, it should be newsworthy when it's impeached.

  5. Not quite lying to congress but Wegman when testifying to Barton's committee said as he would not submit papers to journal which he was an editor.

    Wegman edits WIRES Computational Statistics which published a 2011 paper on Color Theory by Said&Wegman. It contains obvious plagiarism, e.g. googling this phrase "The disease is characterized either by the failure to synthesize pigment proteins" turns up the same text in the paper and a website named allexperts.com.

    Even worse it contains a howler where their source indictates the elderly have trouble distinguishing pairs of colours differing in blue-content such as blue-white, green-blue & red-purple.

    Wegman&Said misunderstand and convert these pairs into single colours: light blue, cyan and magenta – and say they the elderly struggle to distinguish these single colours!

  6. Dan Vergano owns this story. In your post, you pretty much hit all the main reasons why no other mainstream reporters have followed up. (I agree that they likely will be forced to if more news develops.)

    I'm going to add another factor that I suspect as well–and that is that Dan was willing to follow the lead of industrious bloggers. If Deep Climate and John Mashey don't do their own "auditing" of Wegman's papers, there is no story. Mainstream journos are reluctant to legitimize the work of bloggers, much less anonymous ones. But Vergano didn't rely on the bloggers–he just followed up on what they did, investigating and reporting all this on his own. The result is the series of Wegman stories he's done over the last year.

    Still, there is some irony in this passion play, given the central role of another blogger, Steve McIntyre, in fueling this story, to begin with, years ago. You might say we've come full circle.

  7. Vergano is clever and knows many people. I don't know if he knew of Kathleen Carley before, but:

    1) Wegman said in email to Elsevier that Denise Reeves had been sent by MITRE to take a short course at CMU with Carley, "an internationally recognized expert on social network analysis", so Wegman thought Reese the most SNA-knowledgeable in their group.

    2) Well, that certainly offered Vergano a hint of someone to call.

    SO, one is assembling a report for Congress, often likened by Barton, Whitfield or Wegman to an NRC report. See PDF Strange Scholarship in the Wegman Report (SSWR), p.49, 54, 55, 62 (where Judith Curry gets confused about NRC).

    It was often proclaimed as "independent, impartial, expert" work by a team of "eminent statisticians." SSWR p.1-4, p.24 for "eminent".

    3) SSWR pp.143-151 gave evidence that the Wegman team was not very familiar with real SNA, including the absurd :

    '[SHA2006, p.2], part of Wegman‘s reply to Rep. Stupak:
    "Of all the work that has been done on social networks, very few investigators have considered coauthorship network. Therefore, what we are about to observe in this paper is a brand new approach in this field."

    Of course, p.151, Garry Robins panned it, and I checked with another SNA person who did the same, didn't get a quote from him, as I thought the horse was dead.

    4) But I was completely astonished to see Wegman say that Reese was the most SNA-knowledgeable, mentioning only an employer-driven short course.

    I'd never been able to figure out what she'd done, and several others had some exposure to SNA and were using SNA tools.

    It is truly odd to get text from someone, having told them minimal citations for a report supposed to have scholarly weight. The WR had 80 references of which only 40 were cited, but many were irrelevant, grey-literature or downright bizarre).
    For SNA, one of the two key topics, consuming 13 pages, they had *zero* citations or references.

    It is odd to assume it's all original work, and use it as a general introduction (whose eyes had to glaze over at Dyads, and especially Triads, defined, but never used). But it does look impressive, and with no citations, maybe they invented this idea? (no)

    The level of incompetence was even higher than I'd thought.

Comments are closed.