This is Google's cache of viewtopic.php?t=2646&sid=973003ec5ea7d8b3d2e0d299ee4ebd95. It is a snapshot of the page as it appeared on Mar 19, 2011 01:42:48 GMT. The current page could have changed in the meantime. Learn more

Text-only version
These search terms are highlighted: win probability  
APBRmetrics :: View topic - Monte Carlo Simulation for individual games
APBRmetrics Forum Index APBRmetrics
The statistical revolution will not be televised.
 
 FAQFAQ   SearchSearch   MemberlistMemberlist   UsergroupsUsergroups   RegisterRegister 
 ProfileProfile   Log in to check your private messagesLog in to check your private messages   Log inLog in 

Monte Carlo Simulation for individual games

 
Post new topic   Reply to topic    APBRmetrics Forum Index -> General discussion
View previous topic :: View next topic  
Author Message
inkt2002



Joined: 10 Oct 2009
Posts: 8

PostPosted: Wed Oct 13, 2010 10:44 am    Post subject: Monte Carlo Simulation for individual games Reply with quote

Hi gang,
I was wondering if anyone has and shared a nice spreadsheet that simulates each game or comes up with a win probability for each team for a given game?
Back to top
View user's profile Send private message
back2newbelf



Joined: 21 Jun 2005
Posts: 260

PostPosted: Wed Oct 13, 2010 11:42 am    Post subject: Reply with quote

I have a python script that comes up with win probabilities if that helps you.
Back to top
View user's profile Send private message
DSMok1



Joined: 05 Aug 2009
Posts: 602
Location: Where the wind comes sweeping down the plains

PostPosted: Wed Oct 13, 2010 12:04 pm    Post subject: Re: Monte Carlo Simulation for individual games Reply with quote

inkt2002 wrote:
Hi gang,
I was wondering if anyone has and shared a nice spreadsheet that simulates each game or comes up with a win probability for each team for a given game?


I've got several Excel version lying around, not Monte Carlo though. I have one that calculates full playoff probabilities directly, given team's efficiency differentials.
_________________
GodismyJudgeOK.com/DStats
Back to top
View user's profile Send private message Send e-mail Visit poster's website
acollard



Joined: 22 Sep 2010
Posts: 56
Location: MA

PostPosted: Wed Oct 13, 2010 12:36 pm    Post subject: Reply with quote

Sorry if this is a basic question, but I've wondered this for a while now. Do efficiency differentials predict win-loss better than average point differential? I would think that you would have to multiply efficiency by pace for a more accurate prediction.

This feeling is based on the fact that: A slow paced team with a efficiency differential of +2 but a pace of 50 would have an average margin of victory half of a fast paced team with the same differential and a pace of 100. The slow paced team provides more opportunity for chance to create losses, whereas the fast paced team gives itself a bigger sample (and a bigger average cushion) to eliminate some of the problem

Is this logic flawed?
Back to top
View user's profile Send private message
inkt2002



Joined: 10 Oct 2009
Posts: 8

PostPosted: Wed Oct 13, 2010 1:03 pm    Post subject: Reply with quote

back2newbelf wrote:
I have a python script that comes up with win probabilities if that helps you.


Yes that would be awesome and greatly appreciated!!
Back to top
View user's profile Send private message
inkt2002



Joined: 10 Oct 2009
Posts: 8

PostPosted: Wed Oct 13, 2010 1:04 pm    Post subject: Re: Monte Carlo Simulation for individual games Reply with quote

DSMok1 wrote:
inkt2002 wrote:
Hi gang,
I was wondering if anyone has and shared a nice spreadsheet that simulates each game or comes up with a win probability for each team for a given game?


I've got several Excel version lying around, not Monte Carlo though. I have one that calculates full playoff probabilities directly, given team's efficiency differentials.

Does it test individual game probabilities as well? Would love to take a look.
Back to top
View user's profile Send private message
DSMok1



Joined: 05 Aug 2009
Posts: 602
Location: Where the wind comes sweeping down the plains

PostPosted: Wed Oct 13, 2010 2:19 pm    Post subject: Re: Monte Carlo Simulation for individual games Reply with quote

inkt2002 wrote:

Does it test individual game probabilities as well? Would love to take a look.


I have 1 here:https://docs.google.com/leaf?id=0Bx1NfCUslJwxOTRkYmJhYTEtMTNhNC00NjViLWE1ODctYzk3ZDI1MzllOTUz&sort=name&layout=list&num=50

It was from last season, before playoff time: the first sheet took regular SPM for the team from the season and adjusted it for a playoff rotation (and allowed me to pull out players that were hurt). Then, the second page takes the team efficiency differential (calc'd from the SPM) and calculates the odds first of each game and then of each possible series outcome. It doesn't do all of the playoffs in series (to give each team a odds of winning the title), just each series with the teams you choose. I just used the Pythagorean on team efficiency differential, which does (yes, it does) give the best odds of who wins.
_________________
GodismyJudgeOK.com/DStats
Back to top
View user's profile Send private message Send e-mail Visit poster's website
Display posts from previous:   
Post new topic   Reply to topic    APBRmetrics Forum Index -> General discussion All times are GMT - 5 Hours
Page 1 of 1

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum


Powered by phpBB © 2001, 2005 phpBB Group