[Rasch] Logit scores

Agustin Tristan ici_kalt at yahoo.com
Wed Dec 21 07:41:29 EST 2005

Hello. We have the same problem in Latin American
Countries, where we use a traditional "scale" from
0-10, or 0-100. In these scales, it is common to say
that a passing score is 6 or 7 (60% or 70%). In this
scale a score of 5 (or 50%) is equivalent to fail, and
if our test has a normal distribution centered on the
scale, a mean of 50% confirms what the journalists in
our countries say: "we're loosers". In 95 we worked
changing the scores reported by the Ceneval in Mexico,
we adopted a scale from 700 to 1300, the mean centered
in 1000: Miracle! the journalists and other people
believed that 1000 is something like 10 (or 100%) and
some students even got better than that, and no one
was below 700 (or 7 or 70%)! we are not loosers since
then! At least the journalists stopped to publish
those articles concerning mean scores.
In El Salvador we suggested a national scale going
from 300 for first grade children, up to 2700 for
undergraduate, following an idea similar to Lexiles,
that permit to have a wide range scale.
In any case, I think we have to provide the with a
user's manual, otherwise the interpretation may be
erroneous for many people.
May I propose to have one day a general logit scale,
well accepted by everyone in all the world, with the
same meaning for all? It seems that the old dream by
Ben Wright (to have a ruler and a scale easy to
interpret) must become true as soon as possible.
Agustin Tristan

Mariano Jiménez 1830 A 
Col. Balcones del Valle 
78280, San Luis Potosí, S.L.P. México 
TEL (52) 44-4820 37 88, 44-4820 04 31 
FAX (52) 44-4815 48 48 
web page (in Spanish AND ENGLISH): http://www.ieesa-kalt.com

Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 

More information about the Rasch mailing list