Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Ranking derived from sports scores
From
Amir Sariaslan <[email protected]>
To
[email protected]
Subject
Re: st: Ranking derived from sports scores
Date
Thu, 6 Jan 2011 05:58:21 +0100
Jeff,
I don't know about statistical models that address ranking issues but
Stata will not have any problems handling 750,000 records. I've
recently run two-level Poisson regression models on ~ 2.9 million
observations in Stata 11 (Windows 7, quad-core processor and 6GB RAM)
without any problems.
/Amir
On Thu, Jan 6, 2011 at 3:36 AM, Jeff Davies <[email protected]> wrote:
> Thanks for the guidance, Austin and Phil.
>
> Are you aware of software that can take a database of scores (I have a tennis database with about about 750,000 records) composed of player 1, player2, date, games for, games against (+ some other miscellaneous data) and produce a ranking? If so, what type of anaylsis would be appropriate?
>
> If there is limited choice, are you aware of a suitable algorithm that I can use to create such software?
>
> Many thanks to anyone who can assist.
>
> I will be happy to share any new process with the list.
>
> Jeff
>
>
> On Jan 5, 2011, at 1:53 PM, Phil Schumm wrote:
>
>> On Jan 5, 2011, at 12:20 PM, Austin Nichols wrote:
>>> I think a better Wikipedia entry point is
>>> http://en.wikipedia.org/wiki/Elo_rating_system
>>> but I maintain that the Glickman refs and discussion I already linked to are a better starting point.
>>
>>
>> Indeed -- I simply took a quick look for a publicly accessible description of the Bradley-Terry model (i.e., Googled "Bradley-Terry"), and that's the first link that popped up. I just skimmed Glickman's "A Comprehensive Guide to Chess Ratings," and that includes a very nice description of the Bradley-Terry model and how it relates to the Elo rating system.
>>
>> Thanks for the correction.
>>
>>
>> -- Phil
>>
>> *
>> * For searches and help try:
>> * http://www.stata.com/help.cgi?search
>> * http://www.stata.com/support/statalist/faq
>> * http://www.ats.ucla.edu/stat/stata/
>
>
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/