Statistics (was `Out of India')

john robert gardner jgardner at
Thu Dec 12 15:03:55 UTC 1996

I would like to echo Lars Martin Fosse's sentiments re. discussions of
statistical Indological research.  The list's indulgence permitting, there
is much value in this line of discussion.  With our e-text resources, the
frontier of electronic research is wide open.  I am curiousif others have
worked along these lines and what methodological structures presented
themselves therefrom.  I have been loaned a copy of a Mac program called
GoldVarb, a linguistic analysis script-come-program for tracking
regressions--which, I understand thus far, amount to "error patterns."  Is
anyone familiar with this software and/or could suggest a known quanta in
the RV or ZB which might be tested along these lines?


At 08:42 PM 12/11/96 GMT, you wrote:
>V. Rao wrote in answer to Kishore Krishna:
>>[This thread may not be of any direct interest to most members of
>>Indology. I am posting this publically because I wish to
>>correct a potential misunderstanding which my previous post may
>>have created. I would suggest all purely statistical discussions be
>>switched to private e-mail.]
>Allow me to disagree. As long as we are discussing Indological statistics, I
>think the discussion should be available to everybody who cares to follow
>it. I believe it would be useful for people to know about the subject. It
>might also spare us the more naive attempts at using numbers to prove
>points. If the other netters don't want it, I suggest they give us a hint. 
>>The general idea is that when I start using something new, I try it
>>out in known situations first. If it works there, then I can think
>>about using it in situations where the answer is not known.
>This is sound method and really the only way to proceed. Only if you can
>show that statistical methods give good results in situations where you know
>the answer in advance you will be able to use them with any degree of
>confidence in situations where you don't know the answer.
>>In other words, I was not testing for interpolations in Mahabharata or
>>Kumarasambhava  etc., but I was testing the idea that statistical
>>differences in metrical patterns of anushtub (that is half-stanzas of
>>16 syllables, ending in LHLX, L=light, H=heavy, X=any) can indicate
>>differences in age or authorship.
>My own experience is that metrical patterns at best only would serve to
>separate a few very rather long historical periods from each other. You
>cannot use it to differentiate between texts by unknown authors. Or rather:
>Differences in metrical patterns may indicate that you are dealing with two
>different authors, but also that you are dealing with one author who changes
>his style. Stylistically, the young author and the old author are two
>different persons! In Sanskrit, you have the additional problem that writers
>knew thousands of shlokas by heart, and often consciously tried to imitate
>the style of previous centuries. I compared some samples from Somadeva with
>samples from the Ramayana and the Mahabharata (using linguistic criteria) -
>they were quite similar, at least as far as the criteria I used were
>concerned. Somadeva did a great imitation job! To put it succinctly: You can
>never be too careful when dealing with Indological statistics. 
>Best regards,
>Lars Martin Fosse
John Robert Gardner
Obermann Center for Advanced Studies
University of Iowa
Iowa City, IA  52242
jgardner at

More information about the INDOLOGY mailing list