View previous topic :: View next topic |
Author |
Message |
back2newbelf
Joined: 21 Jun 2005 Posts: 271
|
Posted: Wed Jan 21, 2009 6:43 pm Post subject: SRS as a predictor |
|
|
I just did a rather large test on point differential and SRS, how well they predict the winner of a game in all NBA seasons past. I don't have very interesting findings but figured it might be worth a thread. (spare someone else work, maybe)
What i did:
Start predicting the winner of a game, starting with the 1st of January of every season, using the data we gathered(this season) before the date of the game.
1st method: Point differential, pace adjusted, i also subtract that years' homecourt advantage for every home game and add it for every away game a team has played.
2nd: SRS. I tried messing with how far back i should go when i calculate the rating of a team. Example: for predicting games in February, i would calculate the SRS rating of a team using only games played in January and so far in February.
Findings:
SRS does(did) better than point differential but the difference is tiny.
Using only the last X days to calculate SRS rating does better than normal SRS, but again, tiny difference.
# of games that i tried to predict:27779
Correctly predicted by PD: 19103
Correctly predicted by SRS: 19124
Correctly predicted by SRS(using only the last 3 months to calculate a teams's SRS rating): 19158 |
|
Back to top |
|
|
Mountain
Joined: 13 Mar 2007 Posts: 1527
|
Posted: Thu Jan 22, 2009 3:16 am Post subject: |
|
|
Huge test, impressive.
Even when you didn't find earth-shattering results so far, better to check and know more.
Any difference in predictive accuracy when point differential is 0-5. 5-10, 10+ and if this in combination with home court matters?
Is your dataset and interest such that you could test for predictive accuracy when pace differential is 0 to x, x to y and y to z. etc. and if this in combination with home court matters?
Testing for significance of 4 Factor differentials might be interesting too. |
|
Back to top |
|
|
gabefarkas
Joined: 31 Dec 2004 Posts: 1313 Location: Durham, NC
|
Posted: Thu Jan 22, 2009 2:33 pm Post subject: |
|
|
When you say you adjusted for pace, do you mean you used their pace over the season as a whole or their pace only in games played up to that point, or their pace for that particular game? |
|
Back to top |
|
|
back2newbelf
Joined: 21 Jun 2005 Posts: 271
|
Posted: Thu Jan 22, 2009 3:48 pm Post subject: |
|
|
Mountain wrote: |
Any difference in predictive accuracy when point differential is 0-5. 5-10, 10+
|
Haven't tested this yet, but i would assume there is a difference. I'll have an answer in a couple of days
Quote: |
and if this in combination with home court matters?
|
I don't understand this part, sorry
Quote: |
Testing for significance of 4 Factor differentials might be interesting too. |
I have game results only, no boxscores
garbefarkas wrote: | When you say you adjusted for pace, do you mean you used their pace over the season as a whole or their pace only in games played up to that point, or their pace for that particular game?
|
I scale the outcome of a game to the average league pace.
Example: league average for points per game (both teams) is 200.
Team A wins against team B: 100-80, which is a difference of 20.
That particular game was slower than average league pace, so i use this instead:
20*200/180=22.2 |
|
Back to top |
|
|
Mountain
Joined: 13 Mar 2007 Posts: 1527
|
Posted: Thu Jan 22, 2009 3:59 pm Post subject: |
|
|
Any difference in predictive accuracy when point differential is 0-5. 5-10, 10+
Haven't tested this yet, but i would assume there is a difference. I'll have an answer in a couple of days
Sounds good.
and if this in combination with home court matters?
I don't understand this part, sorry
I meant does a point differential of 0-5, etc. after home court edge is included at home or away behave differently in terms of prediction success from same differential away.
Testing for significance of 4 Factor differentials might be interesting too.[/quote]
I have game results only, no boxscores
Ok. |
|
Back to top |
|
|
94by50
Joined: 01 Jan 2006 Posts: 499 Location: Phoenix
|
Posted: Thu Jan 22, 2009 8:26 pm Post subject: |
|
|
As long as we're discussing SRS, I am surprised by how often the predicted MOV by SRS is close or equal to the Vegas line. (It might be selective memory - I don't have hard data, just general observation.) |
|
Back to top |
|
|
Kevin Pelton Site Admin
Joined: 30 Dec 2004 Posts: 979 Location: Seattle
|
Posted: Fri Jan 23, 2009 2:29 am Post subject: |
|
|
Wouldn't it be more interesting to compare their performance relatively early in the season? Certainly the first week or so things are going to be random no matter how you go. However, it seems to me that November and December are going to be when you're going to see the biggest schedule disparities, which is what is accounted for by SRS.
I guess it doesn't surprise me that it ends up about the same as point differential later in the season, since SRS should generally match differential besides conference differences, no? |
|
Back to top |
|
|
back2newbelf
Joined: 21 Jun 2005 Posts: 271
|
Posted: Fri Jan 23, 2009 7:28 am Post subject: |
|
|
Kevin Pelton wrote: | Wouldn't it be more interesting to compare their performance relatively early in the season? Certainly the first week or so things are going to be random no matter how you go. However, it seems to me that November and December are going to be when you're going to see the biggest schedule disparities, which is what is accounted for by SRS.
|
I went back and did this for mid-November to end of December.
Total number of games: 12597
Games correctly predicted by PD:8413
Games correctly predicted by SRS:8419
A different version of SRS, where i limit the difference of the outcome of a game to a maximum of 20, correctly predicts 8434
I don't think i can start earlier than mid-November, since SRS needs a minimum number of games to converge
Quote: |
I guess it doesn't surprise me that it ends up about the same as point differential later in the season, since SRS should generally match differential besides conference differences, no? |
yes |
|
Back to top |
|
|
back2newbelf
Joined: 21 Jun 2005 Posts: 271
|
Posted: Fri Jan 23, 2009 8:46 am Post subject: |
|
|
predictive accuracy for different ranges of point differential(league average homecourt advantage factored in):
0-5 difference in average point differential: 57%
5-10 difference in average point differential: 71%
10+ in average point differential: 84% |
|
Back to top |
|
|
Mountain
Joined: 13 Mar 2007 Posts: 1527
|
Posted: Fri Jan 23, 2009 2:34 pm Post subject: |
|
|
Thanks for this followup. |
|
Back to top |
|
|
Harold Almonte
Joined: 04 Aug 2006 Posts: 616
|
Posted: Fri Jan 23, 2009 5:33 pm Post subject: |
|
|
I've tried an empirical formula, which I don't know the logical behind, but with good approachs: ( (teamA pythW% - teamB pythW%)/4)/10 +/- Home Adv.
Note: when an western team goes to east, the HA increase one extra point. |
|
Back to top |
|
|
Mountain
Joined: 13 Mar 2007 Posts: 1527
|
Posted: Fri Jan 23, 2009 6:27 pm Post subject: |
|
|
"(teamA pythW% - teamB pythW%)/4)/10 +/- Home Adv"
Harold tell me if I am interpreting this correctly
...
(edited, I misunderstood)
How well does this match with actual results?
Last edited by Mountain on Sun Jan 25, 2009 3:21 am; edited 1 time in total |
|
Back to top |
|
|
Harold Almonte
Joined: 04 Aug 2006 Posts: 616
|
Posted: Sat Jan 24, 2009 5:33 pm Post subject: |
|
|
No. It's not about prediction.
If you use whole percents, forget the 10 or the hundred.
75-50=25,
25/4=6.25
Team A will give about 9 points at home (to team B). Will give about 3 on the road.
The HA is not the same for all teams and situations, you can play with that, but I´ve obtained numbers very close to Vegas lines, even in college hoop (4.5 HA).
How the .... the division by 4 translates percents to points spread? I don't know, but it's strangely too coincidential. However, the Vegas line is just an about 68% straight win predictor like SRS. |
|
Back to top |
|
|
back2newbelf
Joined: 21 Jun 2005 Posts: 271
|
Posted: Sun Jan 25, 2009 7:22 am Post subject: |
|
|
Exponential (moving) average correctly predicts 27462 out of 40417.
Point differential: 27516. |
|
Back to top |
|
|
Mountain
Joined: 13 Mar 2007 Posts: 1527
|
Posted: Sun Jan 25, 2009 1:37 pm Post subject: |
|
|
So 70% appears to be the upper limit on predicting W or L by these methods. Maybe some hybrid or new approach does a bit better but there are going to be a share of surprises. |
|
Back to top |
|
|
|