View previous topic :: View next topic |
Author |
Message |
Italian Stallion
Joined: 04 Mar 2009 Posts: 112
|
Posted: Mon Dec 06, 2010 10:29 am Post subject: Probability of a team winning |
|
|
Is there any way to calculate the approximate probability of a team winning based on the records of the two teams?
I can't seem to intuit the formula and math and don't know it.
Assuming everyone had an equal schedule.
If two .500 teams face each other, it would obviously be .500 and .500
If a. 600 team faced a .500 team, the .600 should win .600
But how the heck do you calculate a .400 team vs. a .600 team etc.... The .600 team should win more than .600 because of the below average competition, but I don't see the formula. (I think I'm getting old). |
|
Back to top |
|
|
DSMok1
Joined: 05 Aug 2009 Posts: 602 Location: Where the wind comes sweeping down the plains
|
Posted: Mon Dec 06, 2010 10:58 am Post subject: Re: Probability of a team winning |
|
|
Italian Stallion wrote: | Is there any way to calculate the approximate probability of a team winning based on the records of the two teams?
I can't seem to intuit the formula and math and don't know it.
Assuming everyone had an equal schedule.
If two .500 teams face each other, it would obviously be .500 and .500
If a. 600 team faced a .500 team, the .600 should win .600
But how the heck do you calculate a .400 team vs. a .600 team etc.... The .600 team should win more than .600 because of the below average competition, but I don't see the formula. (I think I'm getting old). |
Convert to Z scores: Normsinv(0.6) = 0.253. Normsinv(0.4) = -0.253.
Normsdist(0.253-(-0.253)) = 0.693 or 69.3%. _________________ GodismyJudgeOK.com/DStats |
|
Back to top |
|
|
Italian Stallion
Joined: 04 Mar 2009 Posts: 112
|
Posted: Mon Dec 06, 2010 11:19 am Post subject: Re: Probability of a team winning |
|
|
DSMok1 wrote: | Italian Stallion wrote: | Is there any way to calculate the approximate probability of a team winning based on the records of the two teams?
I can't seem to intuit the formula and math and don't know it.
Assuming everyone had an equal schedule.
If two .500 teams face each other, it would obviously be .500 and .500
If a. 600 team faced a .500 team, the .600 should win .600
But how the heck do you calculate a .400 team vs. a .600 team etc.... The .600 team should win more than .600 because of the below average competition, but I don't see the formula. (I think I'm getting old). |
Convert to Z scores: Normsinv(0.6) = 0.253. Normsinv(0.4) = -0.253.
Normsdist(0.253-(-0.253)) = 0.693 or 69.3%. |
Did I ever tell you I love you. |
|
Back to top |
|
|
bbstats
Joined: 25 Apr 2010 Posts: 38
|
|
Back to top |
|
|
Ed Küpfer
Joined: 30 Dec 2004 Posts: 785 Location: Toronto
|
Posted: Mon Dec 06, 2010 1:43 pm Post subject: Re: Probability of a team winning |
|
|
Italian Stallion wrote: | But how the heck do you calculate a .400 team vs. a .600 team etc.... The .600 team should win more than .600 because of the below average competition, but I don't see the formula. (I think I'm getting old). |
The poster above gave the log5 formula -- you can see there's a whole literature about it. I compared it to a regression model a long long time ago here. _________________ ed |
|
Back to top |
|
|
bbstats
Joined: 25 Apr 2010 Posts: 38
|
|
Back to top |
|
|
Italian Stallion
Joined: 04 Mar 2009 Posts: 112
|
Posted: Tue Dec 07, 2010 12:48 am Post subject: |
|
|
Thanks guys. |
|
Back to top |
|
|
|