Re: Grading Intelligence Tests

From: Doug Goncz (dgoncz_at_aol.com.bat.exe)
Date: 06/26/04 

Date: 26 Jun 2004 23:49:33 GMT

IQ = the age of tested population at which 50% of those tested get the same
score the subject got or higher, and the other 50% gets the same score or
lower, divided by the subject's chronological age, times 100.

With tested populations numbering in thousands at least, maybe millions.

And replacing the figure 50% by a figure like 49.9% or 49.99%, appropriate to
the size of the tested population.

Something like that....

>From: Ioannis morpheus@olympus.mons

>median should (?) be around 25/50, nobody (from a sample of
>30 people) got any higher than 17/50.

You're the one who said you made it a hard test. Do you clearly understand the
difference between median score and random guessing score? That is, if it were
a true/false test, and everybody guessed randomly, then, yes, the median
"should be" 25/50, but you can't count on everybody guessing randomly.

Was it even a true/false test?

Yours,

Doug Goncz ( ftp://users.aol.com/DGoncz/ )

Read about my physics project at NVCC:
http://groups.google.com/groups?q=dgoncz&scoring=d
 plus "bicycle", "fluorescent", "inverter", "ultracapacitor", etc.
Student member SAE for one year.