- I am taking a second try at this question from dmr -
On 17 Jul 2001 15:23:29 -0700, [EMAIL PROTECTED] (dennis roberts) wrote:
> At 04:08 PM 7/17/01 -0400, Rich Ulrich wrote:
>
> >But, so far as I have heard, the league MEANS stay the same.
> >The SDs are the same. There is no preference, that I have ever
> >heard, for records to be set by half-season, early or late, team
> >or individual. My guess is that association between "talent"
> >and "winning" (or hitting, or pitching, etc.) remains the same.
dmr >
> but, individuals are not half tests ... and, the mean # of homers in the
> second half is not the same (except by coincidence) to the # of home runs
> in the second half ... the original post was not about TEAM stats ... which
> are fixed in the sense that if one team loses alot ... another team wins
> alot ...
>
> every individual player could get better the 2nd half of the season ... or,
I think I see your concern. I should say, the TEST is parallel, but
one player (or many) certainly can perform differently, from
one time to the next.
If EVERY player performed differently - hitting twice as many
homers as before? - that would make it hard to respect records
over the history of the game. That happens *very slowly* over
seasons, and it draws attention. Is the ball livelier? In the
1920s, Babe Ruth hit home runs when no one else did. But
those are differences across generations, not across half-seasons.
In general, the same players are at the top of the league, from
year to year, and neither their numbers nor the overall league
numbers are apt to change dramatically, from year to year.
There is correlation; and there is a constancy of grand means.
This is, after all, the big value of 'parallel forms' in research:
When you see a change, you want to know that it is not just
random. If the person (or group) has learned something, then
the True-score becomes something greater than it was at the
first test.
I think DMR wants to say, Bonds might *not* be expected to
regress to his lifetime average (we were saying he would).
Why not, regress to his first-half of the year average? Why
couldn't it be that he might be hitting so well because he
has put on muscle, and he has learned to hit harder?
- *I* believe weight-training does explain some of the recent
homers.
But can it explain a *record* high number? Only, I think,
as part of the statistical fluke, which still insists that his
expected production for the second half of the season
should be much lower than 38.
Part of the implicit argument against Bonds doing so much
better, suddenly, is that he already has a long history. If
he DOES change his life-time propensity, maybe it DOES
stand as more proof for what McGwire made us wonder --
is it in the steroid supplements?
<does Bonds have that as history?>
Baseball observers don't think that ballplayers make sudden,
late-in-life improvements. Also, the statisticians don't see
that there are hot-streaks that should be invoked; the
existing records do seem to exist by virtue of *random*
fluctuations of the typical performances, of the spectrum
of players.
--
Rich Ulrich, [EMAIL PROTECTED]
http://www.pitt.edu/~wpilib/index.html
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
