I agree that it is an interesting comment by John Kukla that the Monte
Carlo simulation by  Fraser Nieman was “skimmed” by “most historians.”  I’m
not sure what “skimmed” means but I suspect it means they didn’t understand
it. The William & Mary Quarterly published this article without peer review
and I am not aware of any one who has followed Fraser’s methodology to
determine exactly what it was he did. As to the reliance on the study, I
think it is fair to assume that those who read the Quarterly believed it
had the imprimatur of that publication. As Steve Corneliussen points out,
Richard Bernstein cited the study as one of the three legs of his
acceptance of Jefferson’s paternity. He made no distinction between the
Monte Carlo simulation and the raw data and in fact defended on SHEAR the
quantitative work by Fraser. In the recent book by Francis D. Cogliano, he
cites the Fraser study as authority. More importantly, the study first
appeared in the original committee report from Monticello, and it is
certainly reasonable to assume that anyone who read the report would
believe that this is a valid statistical methodology. It is interesting to
note that Fraser commented in his study that if one believes the paternity
hypothesis is “false on other grounds,” then his study would be of no
consequence. I guess the obverse of that is if you first believe the
paternity story, then you can rely on Fraser’s study. 

Richard E. Dixon
Editor, Jefferson Notes
Thomas Jefferson Heritage Society
4122 Leonard Drive
Fairfax, Va 22030
703-691-0770 fax 703-691-0978


> [Original Message]
> From: Steven T. Corneliussen <[log in to unmask]>
> To: <[log in to unmask]>
> Date: 2/25/2009 1:39:58 PM
> Subject: Re: [VA-HIST] A modest proposal re the DNA debate
>
> Thanks very much, Mr. Kukla, especially for the encouragement about the 
> essay. (In this case, I've left your note that I'm responding to 
> undeleted at the bottom.)
>
> But there's an important point to be made about a misunderstanding that 
> I perceive as embedded in the following snippet from what you wrote. I 
> believe this point confronts a good portion of the history profession 
> and deserves a serious answer from both historians and scientists. (And, 
> in case I need to add this: I believe the point is not justly 
> categorizable as merely another example of tedious re-hashing of 
> Hemings-TJ debate in this forum.) You wrote:
>  > ... if you have Fraser Neiman's monte carlo computations in
>  > mind, I think you'll find that most historians skimmed that part
>  > of his WMQ piece . . . but what historians did find pertinent
>  > was the 'raw data' - birth dates and computed conception
>  > dates he presented.
>

______________________________________
To subscribe, change options, or unsubscribe please see the instructions at
http://listlva.lib.va.us/archives/va-hist.html