On 17 Mar 2001 16:10:59 GMT, [EMAIL PROTECTED] (EugeneGall)
wrote:
>>Subject: RE: On inappropriate hypothesis testing. Was: MIT Sexism & sta
>>From: [EMAIL PROTECTED] (Simon, Steve, PhD)
>>Date: 3/16/2001 7:23 PM Eastern Standard Time
>>Message-id: <E7AC96207335D411B1E7009027FC2849F87184@EXCHANGE2>
>>
><Snip>
>>Also, has anyone looked at a log transformation of the data? The > "huge"
>difference doesn't look so huge on a log scale.
>
>I posted this link to log transformed plots >1 month ago:
>
>http://www.es.umb.edu/edg/ECOS611/iwflnfigs.pdf
>
>I also posted the data from the IWF report at:
>http://www.es.umb.edu/edg/ECOS611/mit-iwf.zip
>
>These data were copied from the IWF report
>and are provided in Excel and SPSS format.
>The data in support of gender differences in
>grant support weren't provided in the IWF report.
>
>Gene Gallagher
Gene, what you didn't post was any rationale for the ln
transformation. An inappropriate log transform can
always make differences between groups look less
imposing if one group contains a set of, say, Nobel
Prize winners or very high performers (as the senior
male Biology faculty at MIT) while the female group
does not (as at MIT).
The analogous example is given in my Yankee-Tiger
example, in which by "log transforming" the home run
data, one might superficially be misled into thinking that
the huge difference in home run hitting between the Yanks
(Maris, Mantle, Berra) and Tigers (Colavito, Kaline, Bruton)
in 1961 did not exist.
Yanks Tigers
----- ------
61 45
54 19
22 17
--------------
137 81
Any baseball historian will tell you that, over the 162 game
season in 1961, the Yankee outfielders showed a huge
performance advantage in home run hitting over their
Tiger counterparts. Two people Maris and Mantle,
had "superstar" seasons in terms of their home
run hitting exploits.
Now, let's ln- transform the data.
Yanks Tigers
----- ------
4.11 3.81
3.99 2.94
3.09 2.83
--------------
The ln transform helps to "eliminate" the performance
difference between Mris, Mantle, and the Tigers.'
If you are a Tiger Fan, this may make you feel much better.
But why stop there? Why not log-transform them with the base10
logarithm. That makes things look even better!
Yanks Tigers
----------------------
1.79 1.65
1.73 1.28
1.34 1.23
----------------------
And, of course, a log16 transform could "do even better"!
We can now "see" that the Yankees hardly outhomered the
Tigers at all in 1961!!
Nonlinear transforms can do "marvelous things" in the
service of disinformation. Their use requires a rationale.
You never provided any rationale, let alone a careful
one.
Care to comment?
Best regards,
Jim Steiger
--------------
James H. Steiger, Professor
Dept. of Psychology
University of British Columbia
Vancouver, B.C., V6T 1Z4
-------------
Note: I urge all members of this list to read
the following and inform themselves carefully
of the truth about the MIT Report on the Status
of Women Faculty.
Patricia Hausman and James Steiger Article,
"Confession Without Guilt?" :
http://www.iwf.org/news/mitfinal.pdf
Judith Kleinfeld's Article Critiquing the MIT Report:
http://www.uaf.edu/northern/mitstudy/#note9back
Original MIT Report on the Status of Women Faculty:
http://mindit.netmind.com/proxy/http://web.mit.edu/fnl/
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================