Re: [S] The Torah Code

John Maindonald (
Tue, 4 Aug 1998 11:39:07 +1000 (EST)

Dave Krantz wrote
> I guess the mention of the Torah-code bunkum qualifies this
> as statistics-related: the editors of Statistical Science
> accepted one of the bunkum articles back in 1994; and perhaps
> the S language could be or has been used to implement some of
> the minimum-distance searches involved in bunking and
> debunking the Torah codes. (I'll refer you to Brendan Mckay
> at ANU for statistical de-bunk-tails; he and Maya Bar-Hillel
> have convinced me thoroughly--not that my priors were ever
> appreciably above zero, but it is nice to learn the details
> of the scam.)

Perhaps a reference may be helpful in the attempt to close off this
discussion. The best article on this that I know is:
Bar-Hillel, Bar-Natan and McKay: "The Torah Codes; Puzzle & Solution",
in Chance 11, no. 2, pp.13-19, 1998.
(It's ironic that an authoritative commentary on the Statistical
Science article should appear in `Chance'.)
See also:
and perhaps

Unfortunately there is a lot of mainstream science where theory grows
like a weed without too much check from the critical use of data,
and that would yield far more easily to less rigorous criticism
than has been focused on the Torah-code claims.

Statistical software quality does influence the quality of published
data analysis. I hold strongly to the view that writers of
statistical software have a responsibility to provide forms of output
and documentation that will promote good statistical practice. Does
this form part of MathSoft's mission statement?

John Maindonald email :
Statistical Consulting Unit, phone : (6249)3998
c/o CMA, SMS, fax : (6249)5549
John Dedman Mathematical Sciences Building
Australian National University
Canberra ACT 0200
This message was distributed by To unsubscribe
send e-mail to with the BODY of the
message: unsubscribe s-news