APBRmetrics

AcrossTheCourt wrote:Any way you can do a 1.5 year RAPM? 2014 and 2015 up to the break, of course.

EvanZ wrote:It was easy enough for me to run this. This is just based on the past 1.5 years:

https://docs.google.com/spreadsheets/d/ ... 1655629432

J.E. wrote:You can now find pure multi-year RAPM at that same link http://stats-for-the-nba.appspot.com/ra ... _2015.html

I am a little confused at the difference between the two of these sets. My assumption is that these are two different things.

JE's link is 2015 RAPM informed by a 2014 prior (which is in turn informed by 2013, and so on...)

Evan's link is 2014+2015 RAPM with no prior.

Am I correct or are they both the same dataset with different dates and lambda?

JE's regression is going to weigh 2015 more heavily (I assume). My regression treats all years equally.

EvanZ wrote:

AcrossTheCourt wrote:Any way you can do a 1.5 year RAPM? 2014 and 2015 up to the break, of course.

It was easy enough for me to run this. This is just based on the past 1.5 years:

https://docs.google.com/spreadsheets/d/ ... 1655629432

Nene's in there twice as Nene and Nene Hilario.

And I feel stupid for this ... but which NBA player is Mike Malone? It's not matching with any of my stuff.

Ah, coaches (Mike Malone) can appear in play-by-play when they get technicals or ejected. I usually account for this, but must have slipped by me!

This would include playoffs. I don't have to, of course.

I believe only one of the Nene's has major minutes in my data set, but I'd have to double check.

Yeah I wasn't sure because I saw no other coach in there and Michael/Mike is a popular name so I thought I was just blanking on someone.

Related problem: two players for this season have two playerIDs on stats.NBA.com. It's just an annoying little issue to deal with when grabbing their data.

This 1.5 year RAPM looks like the sum of the previous year's RAPM and this years' resulting values... Or there's something wrong with the lambda.

Any updates 80% into the season?

I ran offensive + defensive splits last week:

https://docs.google.com/spreadsheets/d/ ... 1783210900

Evan, just wondering if the sheet has been updates again. I was talking on RGM with lorak and it came up, so we were both just checking .

Here are off + def splits I did a few days ago:

https://docs.google.com/spreadsheets/d/ ... 1783210900

EvanZ wrote:Here are off + def splits I did a few days ago:

https://docs.google.com/spreadsheets/d/ ... 1783210900

Thanks, that answered our question!

So I've come to the understanding that I was mistaken earlier, the set that JE posted in this thread was 2015 multi-year RAPM, not "pure" (15 informed by 14) RAPM.

Is there a prior-informed 2015 set out there? GotBuckets.com had been posting talkingpractice's PI sets from 08-14, but both sites have yet to update for 2015 (we haven't seen IPV for this year either).

sideshowbob wrote:So I've come to the understanding that I was mistaken earlier, the set that JE posted in this thread was 2015 multi-year RAPM, not "pure" (15 informed by 14) RAPM.

Is there a prior-informed 2015 set out there? GotBuckets.com had been posting talkingpractice's PI sets from 08-14, but both sites have yet to update for 2015 (we haven't seen IPV for this year either).

I really doubt that there'll be any significant differences between
a) 2015 RAPM informed by 2014 (which, in turn, is informed by 2013 etc)
b) Multiyear RAPM that uses data from 2015, 2014, etc and gives less weight to older seasons

If anything, b) makes more sense - at least in my mind

J.E. wrote:

sideshowbob wrote:So I've come to the understanding that I was mistaken earlier, the set that JE posted in this thread was 2015 multi-year RAPM, not "pure" (15 informed by 14) RAPM.

Is there a prior-informed 2015 set out there? GotBuckets.com had been posting talkingpractice's PI sets from 08-14, but both sites have yet to update for 2015 (we haven't seen IPV for this year either).

I really doubt that there'll be any significant differences between
a) 2015 RAPM informed by 2014 (which, in turn, is informed by 2013 etc)
b) Multiyear RAPM that uses data from 2015, 2014, etc and gives less weight to older seasons

If anything, b) makes more sense - at least in my mind

Appreciate the response

Has that set been updated? I believe it was using data up to mid-January.

sideshowbob wrote:

J.E. wrote:

sideshowbob wrote:So I've come to the understanding that I was mistaken earlier, the set that JE posted in this thread was 2015 multi-year RAPM, not "pure" (15 informed by 14) RAPM.

Is there a prior-informed 2015 set out there? GotBuckets.com had been posting talkingpractice's PI sets from 08-14, but both sites have yet to update for 2015 (we haven't seen IPV for this year either).

I really doubt that there'll be any significant differences between
a) 2015 RAPM informed by 2014 (which, in turn, is informed by 2013 etc)
b) Multiyear RAPM that uses data from 2015, 2014, etc and gives less weight to older seasons

If anything, b) makes more sense - at least in my mind

Appreciate the response

Has that set been updated? I believe it was using data up to mid-January.

Haven't updated since, but will definitely update after the playoffs end