On this week’s show: The curious incident of Edward Wegman, and the copied report, the non-significance of the hockey stick, Cuccinelli and the witch, CRU cleared again, exploding deniers, and the importance of coherence.
Irregular Climate is now accepting donations.
Feedback is always appreciated.
The Curious Incident of Edward Wegman, and the copied report
It has been key prop of climate anti-science ever since. It was promoted to Congress by Representatives Joe Barton and Ed Whitfield as ―independent, impartial, expert‖ work by a team of ―eminent statisticians.‖ It was none of those.
A Barton staffer provided much of the source material to the Wegman team. The report itself contains numerous cases of obvious bias, as do process, testimony and follow-on actions. Of 91 pages, 35 are mostly plagiarized text, but often injected with errors, bias and changes of meaning. Its Bibliography is mostly padding, 50% of the references [are] uncited in the text. Many references are irrelevant or dubious. The team relied heavily on a long-obsolete sketch and very likely on various uncredited sources. Much of the work was done by Said (then less than 1 year post-PhD) and by students several years pre-PhD. The (distinguished) 2nd author Scott wrote only a 3-page standard mathematical Appendix. Some commenters were surprised to be later named as serious ―reviewers.‖ Comments were often ignored anyway. People were misused.
The Wegman Report claimed two missions: #1 evaluate statistical issues of the ―hockey stick‖ temperature graph, and #2 assess potential peer review issues in climate science. For #1, the team might have been able to do a peer-review-grade statistical analysis, but in 91 pages managed not to do so. For #2, a credible assessment needed a senior, multidisciplinary panel, not a statistics professor and his students, demonstrably unfamiliar with the science and as a team, unqualified for that task. Instead, they made an odd excursion into ―social network analysis,‖ a discipline in which they lacked experience, but used poorly to make baseless claims of potential wrongdoing.
In retrospect, the real missions were: #1 claim the ―hockey stick‖ broken and #2 discredit climate science as a whole.
All this was a façade for a PR campaign well-honed by Washington, DC ―thinktanks and allies, under way for years.
Cuccinelli and the witch
In the suit Cuccinelli states that:
[Mann] knew or should have known [that the published papers] contained false information, unsubstantiated claims, and/or were otherwise misleading. Specifically, but without limitation, some of the conclusions of the papers demonstrate a complete lack of rigor regarding the statistical analysis of the alleged data, meaning the result reported lacked statistical significance without a specific statement to that effect.
So in other words, if you publish a result that might turn out to be statistically weak or with understated error bars – even if this was in no way deliberate and regardless if you were aware of it at the time – Cuccinelli thinks that is equivalent to fraud. And any grant that you apply for that even cites this paper would therefore be a false claim under the statute. Cuccinelli is specifically not stating that deliberate scientific misconduct must have occurred, all you need to have performed is an inadequate (according to him) statistical treatment or you made an unsubstantiated claim… this would clearly open up pretty much the entire literature to ‘fraud’ investigations since one can almost always improve on the statistics. You didn’t take temporal auto-correlation into account in calculating the trend? Cuccinelli thinks that’s fraud. You didn’t fully characterise the systematic uncertainty in the “unknown unknowns”? That too. You weren’t aware of the new data that showed an older paper was incomplete? Too bad. This is not just an attack on Mike Mann, it is an attack on the whole scientific enterprise.
CRU cleared again
The importance of Coherence