Re: Estimating the number of signs in a writing system from a sample text (was: Phaistos Disk)

From: Herman Rubin (hrubin_at_odds.stat.purdue.edu)
Date: 07/17/04 

Date: 16 Jul 2004 20:11:42 -0500

In article <337ae51f.0407130359.314eba74@posting.google.com>,
grapheus <grapheus@www.com> wrote:
>hrubin@odds.stat.purdue.edu (Herman Rubin) wrote in message news:<ccumde$22h2@odds.stat.purdue.edu>...
>> In article <668d6151.0407112339.65f5746a@posting.google.com>,
>> mb <azythos2@hotmail.com> wrote:
>> >grapheus@www.com (grapheus) wrote

                         .................

>> >Also, the transformations by Faucounau are not explicited, in fact
>> >they are not reported at all.

>> Also, text does not consist of independent items.

>I believe that you havve COMPLETELY MISUNDERTOOD the little
>J.Faucounau has written about his Statistical approach of the problem
>!...
>So, my question : Where have you read, in what he has published, that
>he talked about the "Gausian Law" or the "Poisson Law" as an other
>thing than an "APPROXIMATION for LARGE samples"?...

For ideograms, the Poisson approximation may well be better
for fairly large samples than the normal law. The approach
to normality is quite slow for even independent items which
are not in the neighborhood of half the total. What is the
highest proportion of times a character occurs?

Nor can one distinguish between frequent and rare unless there
is essentially a drop in total occurrences, such as few symbols
occurring between 5 and 8 times compared to those at 9 or 10.

>grapheus

>PS : Please know that if I am not a mathematician (but just an admirer
>of J.F.'s work), J.F. is, and many members of his family too. 

-- 
This address is for information only.  I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Department of Statistics, Purdue University
hrubin@stat.purdue.edu         Phone: (765)494-6054   FAX: (765)494-0558

Relevant Pages

  • Re: "Statins caused my kidney failure"
    ... but not the relevant information. ... I do not claim that these views are those of the Statistics Department or of Purdue University. ...
    (sci.med.cardiology)
  • Re: Induction of statistical models
    ... There is no basic disagreement between Bayesian inference ... are those of the Statistics Department or of Purdue University. ... Herman Rubin, Department of Statistics, Purdue University ...
    (sci.stat.math)
  • Re: "Statins caused my kidney failure"
    ... but not the relevant information. ... I do not claim that these views are those of the Statistics Department or of Purdue University. ...
    (sci.med.nutrition)
  • Re: More about things, was: Re: Look whos rooting for Obama (Naomi Ragen)
    ... only learn at a limited rate, or limited amounts, to the ... the extent of their abilities. ... Herman Rubin, Department of Statistics, Purdue University ...
    (soc.culture.jewish.moderated)
  • Re: Put your babies on statins
    ... About half of the 25 male rats fed the ... >> are those of the Statistics Department or of Purdue University. ... I do not claim that these views are those of the Statistics Department or of Purdue University. ...
    (sci.med.cardiology)