APBRmetrics

Any high level takeways having worked on this for a while? Looks like you've tried out a lot of different staking strategies.

shadow wrote: ↑Tue Jul 23, 2019 2:56 pm Would you be able to share any insight as to how you used Regular Season RAPM as a prior?

Basically the same process as a SPM prior. Adjust the possession expectation based on the player's priors, run the regression, and then add the priors back in at the end.

The number in the player name is their ID from stats.nba.com. There's going be some confounding influences in here for sure, some of which could probably be handled. Taking a guess at Chandler, his playoff possessions come from his seasons where he is close to his prime (Age 22-32) and the bulk come...

1998-2018 Playoff RAPM that uses Regular Season RAPM as a prior. It's only single component so there's no O/D split-out. Here's the top/bottom 30 changes from regular season to playoffs with 8000 playoff possessions: Top https://i.imgur.com/YXM5hAy.png Bottom https://i.imgur.com/iG1QWjx.png https://...

To do this project, I have worked with an NBA team (special thanks to them!) to develop an improved RAPM basis. This basis provides average RAPM over 6 year eras, and handles aging/role changes via a Bayesian prior. These shorter eras allow a far better coverage of outliers (like LeBron). Can you g...

I think the right answer is whatever ends up being best out-of-sample. I do number #1 - however, to get the right SPM blend I use cross validation with each of the seasons within data set. So you'll get the following for a 2000-2018 data set: Multi-Year RAPM 2000-2018 (- 2000) + Box Score 2000-2018 ...

jgoldstein34 wrote:I do print money haha yes. 73% 2 years ago, 70% last. 68% this year, but based off analysis I expect it to regress up to ~69-70%.

But no, not really much I can talk about because of NDAs and agreements with partners.

In-sample results? Using actual minutes/possessions for players?

Here are mine:
GSW 66.3
HOU 56.4
CLE 54.3
SAS 53.7
OKC 51.9
BOS 49.5
MIN 48.5
WAS 47.5
TOR 47.2
MIL 46.6
LAC 45.7
DEN 45.5
CHH 44.9
MIA 43.1
POR 41.5
NOP 41.3
UTA 40.9
DET 37.1
MEM 37.1
PHI 36.0
DAL 33.8
ORL 33.4
IND 31.9
LAL 30.5
NYK 30.1
BKN 28.1
PHX 28.0
ATL 27.5
CHI 25.9
SAC 25.9

Does anyone have any player minutes they'd like to generously share?

GSW 69.1
CLE 57.2
SAS 55.5
LAC 51.0
BOS 50.6
TOR 50.3
UTA 48.4
OKC 45.4
POR 45.3
HOU 45.3
DET 42.8
CHA 42.3
IND 41.2
WAS 41.1
ATL 40.9
CHI 39.8
MIN 39.6
MEM 39.1
DAL 37.7
ORL 36.8
DEN 36.5
SAC 35.4
NOP 35.4
NYK 35.1
MIA 34.6
MIL 33.0
PHX 28.8
LAL 24.3
BKN 23.9
PHI 23.8

Gracias

Much appreciated Kevin. Any way you're updating these minutes like last year?!

So, @newdatasports Vantage's tout service that was attached to this paper started publishing fully transparent picks after the games began. It lasted 4 days.

They went 11-19 in their published plays and now the Twitter account is deleted.

https://twitter.com/vantagesports/statu ... 9526905856

Damn, I bought it last night from createspace. $5 more and shipped to me 10 days later.

These two links will get you going:
http://www.goldenstateofmind.com/2011/1 ... ats-primer
http://godismyjudgeok.com/DStats/2011/n ... ilization/