From: Patrick Ryan
Message: 43388
Date: 2006-02-13
----- Original Message -----From: mkelkar2003Sent: Sunday, February 12, 2006 5:29 PMSubject: [tied] Re: pre-Nostratic *male[:]k?xa, 'milk (vb.)'<snip>
Statistical tests cannot be invoked *selectively* while denying the
link between IE and other familes. Some known IE langauges also fail
to meet the statistical tests prposed by Ringe (1996).
"Renfrew, Colin (2000), "At the Edge of Knowablitlity: Towards a
Prehistory of Languages," Cambridge Archaeological Journal, 10:1, 7-34.
<http://www1.cs.columbia.edu/~traub/sloan/RenfrewXPM.pdf>
Msg# 74880 on IC.
"One wonders, for example the statistical tests proposed by Ringe
(1996) would admit Albanian, Armenian, Tocharian and Sinhalese to the
same language family while few linguists today would doubt that all
belong to the Indo-European family (Renfrew 2000, p. 10)."
m. kelkar
***Patrick:Ah, we are going to play 'Ringe around the rosie' again.I hope we have a few people on the list who are better at statistics than I am but the last time I saw this thrashed out by people who appeared to know better than I do, Ringe did not fare well.***