21.059 how to use Chi-square correctly

                Humanist Discussion Group, Vol. 21, No. 59.
       Centre for Computing in the Humanities, King's College London
  www.kcl.ac.uk/schools/humanities/cch/research/publications/humanist.html
                        www.princeton.edu/humanist/
                     Submit to: humanist_at_princeton.edu

   [1] From: Norman Gray <norman_at_astro.gla.ac.uk> (24)
         Subject: Re: 21.035 how to use Chi-square correctly?

   [2] From: "Juliana Tambovtseva" <jultamb_at_yandex.ru> (11)
         Subject: how to calculate Sign test?

--[1]------------------------------------------------------------------
         Date: Wed, 30 May 2007 06:57:38 +0100
         From: Norman Gray <norman_at_astro.gla.ac.uk>
         Subject: Re: 21.035 how to use Chi-square correctly?

Juliana, greetings,

On 2007 May 21 , at 06.45, Humanist Discussion Group (by way of
Willard McCarty <willard.mccarty_at_kcl.ac.uk>) wrote:

> Date: Mon, 21 May 2007 06:37:13 +0100
> From: "Juliana Tambovtseva" <jultamb_at_yandex.ru>
> >
>
>Dear Humanist colleagues, the discussion about reviewing process is
>quite on time. My article was turned away because the reviewer wrote
>that I use the Chi-square criterion in the way it was used 30 years
>ago. I am a linguist but I guess that the calcilation of the
>Chi-square should be the same then and now.

I don't believe anything has changed in the way that chi-squared is
defined or used. Nor has much changed (unfortunately) in the way and
extent that it is abused.

If you'd like to send me a copy of your data off-list, I'm sure we
can work out what the correct chi-squared should be, and post some
summary to the list afterwards.

Best wishes,

Norman

-- 
------------------------------------------------------------------------ ---
Norman Gray  :  http://www.astro.gla.ac.uk/users/norman/
Physics and Astronomy, University of Glasgow, UK
--[2]------------------------------------------------------------------
         Date: Wed, 30 May 2007 06:59:38 +0100
         From: "Juliana Tambovtseva" <jultamb_at_yandex.ru>
         Subject: how to calculate Sign test?
Dear Humanist colleagues, nobody answered how to calculate the
Chi-square in the modern way. So, I think that the old way is quite
all right. I mean the reviewer who claimed to know the modern way was
joking. Actually, do you know how to compare two numbers with the
help of the Sign Test? Can you exactly tell me about two numbers 76
and 48 ? The Chi-square gives 6.30 which is greater 3.84 at the level
of 0.05. It means these two numbers are statistically different. What
about the Sign Test in this case? Please, teach me to calculate it.
Looking forward to hearing from you soon to
<mailto:yutamb_at_mail.ru>yutamb_at_mail.ru Be well, remain sincerely and
cordially Yuri