"Out of India"

[Girish Beeharry]

Hi,

Thanks for the responses.

Vidhyanath Rao wrote:
>In cluster analysis, the aim is to study how the different variables
>or different subjects group together. The results can be displayed
>as a tree diagram. Closest neighbors are grouped together
>and joined to a single vertex. Something not more closely related to
>some compared to the others is left as an isolated twig. Then this
>process is repeated with each group obtained at this stage. This is the
>kind of diagram that is found in write-ups of the `African Eve' theory,
>for example.

>As to the theory behind how `closeness' is measured, I don't quite
>follow it myself.

Thanks for the above explanation. I too have difficulty in understanding how
to 'measure' the 'distance' between 'neighbours': I don't understand how to say
when subjects and variables are close enough. However, this is the heart of the
whole analysis. 

>It may be worthwhile if Indology courses did require a course in
>understanding statistics. For example, a rank correlation test on
>the different attempts to arrange the books of Rgveda in a
>chronological sequence would be eye opening.

May be Indologist might consider talking to mathematicians! :-) 

Lars Martin Fosse wrote:
>It should be added that there are several algorithms for cluster analysis
>that yield somewhat different results. It would be foolhardy simply to
>produce a cluster analysis and accept the result as authoritative, several
>attempts with different sets of criteria and different algorithms would have
>to be done. 

This adds another item to the list of 'I don't understand'; which algorithms 
are more 'objective'? Has non-parametric statistics (eg maximum likelihood)
been used in this area?

Bye,

Girish Beeharry