On Wed, 17 Jan 2001, dennis roberts wrote:
> ... if the instructor is going to base my test grade on my percentile rank
> ... i could easily get a lower grade on test 2 than test 1 ...
>
> somehow, i think this is penalizing me for the fact that there is not and
> cannot be a perfect correlation between the two measures ...
You are not being penalized; your true ability might well be lower and
you were lucky the first time. Assume that both tests measure the same
ability with measurement error. This error is then the only reason why
the correlation is not perfect. The average score is then a best unbiased
estimate of your ability (assuming equal variances). YOU could in fact
score higher the second time, but most people will not. With errorfree
measumement, you will score the same both times.
> what happens to the ones at the bottom ... relative to what happens to me??
same thing in reverse for the same reason.
>
> as i have said before ... regression to the mean is a feature of relative
> position ... and not necessarily RAW scores ...
YES
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
