Free Republic
Browse · Search
General/Chat
Topics · Post Article

To: JohnnyZ

How I computed my final standings:

Games won + f(r) (calculated wins of remaining games) = total games won.

f(r) (calculated wins of remaining games= (162-r)X ((sqrt (Win percentage X Win percentage last ten games))+ f(e)(%Error of win percentage total)).

f(e)(%Error of win percentage total))= 1.29 X sqrt((Win percentage X Los percentage)/(total games played-1)).




427 posted on 09/25/2005 10:47:36 AM PDT by Perdogg
[ Post Reply | Private Reply | To 424 | View Replies ]


To: Perdogg

GIGO


429 posted on 09/25/2005 11:18:40 AM PDT by JohnnyZ ("I believe abortion should be safe and legal in this country" -- Mitt Romney)
[ Post Reply | Private Reply | To 427 | View Replies ]

To: Perdogg
The games won totals are not independent -- last10 is a dubious predictor at best -- if you're going to try to model the outcomes of the last 8 games of a season, the actual teams and pitchers and hitters involved have so much more to do with it than season W%, L10, or anything else.

Given the variables involved, might as well just use informed judgement, and besides most guesses, or models, or anthing, are going to be within 1 or 2 W or L of the actual outcome with so few games remaining.

Essentially you "computed" that since the Yankees have a better L10 record, they're going to win the division. That's a valid opinion, but it has nothing to do with computation.

430 posted on 09/25/2005 11:30:09 AM PDT by JohnnyZ ("I believe abortion should be safe and legal in this country" -- Mitt Romney)
[ Post Reply | Private Reply | To 427 | View Replies ]

Free Republic
Browse · Search
General/Chat
Topics · Post Article


FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson