Search found 237 matches

by AcrossTheCourt
Tue Oct 17, 2017 11:12 am
Forum: APBRmetrics
Topic: 2017-18 team win projection contest
Replies: 184
Views: 92588

Re: 2017-18 team win projection contest

CLE E 55.6 GSW W 68.0 MIL E 47.9 HOU W 58.5 TOR E 47.9 SAS W 52.9 BOS E 47.5 OKC W 52.0 WAS E 47.2 LAC W 50.9 CHA E 46.7 MIN W 49.8 MIA E 44.8 DEN W 46.5 DET E 35.2 NOP W 44.9 ORL E 33.3 UTA W 43.9 IND E 30.9 POR W 42.1 PHI E 30.3 MEM W 38.2 NYK E 28.4 DAL W 32.3 BKN E 28.0 LAL W 25.7 CHI E 26.2 PHX...
by AcrossTheCourt
Wed Apr 26, 2017 3:16 am
Forum: APBRmetrics
Topic: Playoff predictions?
Replies: 24
Views: 12683

Re: Playoff predictions?

So this post is not anything more than a table of facts, plus a question about what "home court advantage" means. It seems to be the point differential benefit for the team playing at home. In the playoffs, if you aren't at home, your opponent is at home; you not only lose the HCA, the opponent gai...
by AcrossTheCourt
Fri Apr 21, 2017 8:12 pm
Forum: APBRmetrics
Topic: Playoff predictions?
Replies: 24
Views: 12683

Re: Playoff predictions?

Ignoring games is silly. You can just weigh those odd games more so it's even:
https://ascreamingcomesacrossthecourt.b ... yoffs.html
by AcrossTheCourt
Sun Apr 16, 2017 2:09 am
Forum: APBRmetrics
Topic: Can anyone make sense of 538's ELO ratings?
Replies: 10
Views: 5712

Re: Can anyone make sense of 538's ELO ratings?

It's recency based, but they do use the full season. Cleveland was so awful in the last chunk of the season that they collapsed.

https://fivethirtyeight.com/features/ar ... nderrated/
by AcrossTheCourt
Thu Apr 13, 2017 9:10 pm
Forum: APBRmetrics
Topic: 2016-17 Team Win Projection Contest / Discussion
Replies: 213
Views: 137492

Re: 2016-17 Team Win Projection Contest / Discussion

What's SMRE?

And how do the rankings change with Pythag wins?
by AcrossTheCourt
Thu Feb 23, 2017 6:57 am
Forum: APBRmetrics
Topic: A case where PER is NOT "good enough" to use
Replies: 32
Views: 33698

Re: A case where PER is NOT "good enough" to use

A bit of analysis of PER vs PER2.0 for 2016-2017 data: On average guys 20 or higher on PER are 21.4% higher on PER2.0 for an average gain of 5 points. Guys 15-20 on PER only gain 6.7% or a bit more than 1 point on average. Guys 10-15 on PER lose an average of 8.4% or about 1 point. Guys below 10 on...
by AcrossTheCourt
Fri Feb 10, 2017 7:41 pm
Forum: APBRmetrics
Topic: A case where PER is NOT "good enough" to use
Replies: 32
Views: 33698

Re: A case where PER is NOT "good enough" to use

I think you missed the point there, and I'm surprised you're defending PER at all. Did you notice I was ignoring FTs too? The point was showing how the metric responds to points and FG%. And I don't think you read that close enough: "Kobe assists" are already factored in because missed shots have an...
by AcrossTheCourt
Tue Jan 31, 2017 10:23 pm
Forum: APBRmetrics
Topic: 2016-17 Team Win Projection Contest / Discussion
Replies: 213
Views: 137492

Re: 2016-17 Team Win Projection Contest / Discussion

No, they often share samples of the minutes projections, and they're usually really solid. I think they just overfit the similarity/age curve. Look at MIN's projection again, which did not factor in Thibs -- they were over the optimistic Vegas line by a good distance. They assumed some incredible de...
by AcrossTheCourt
Thu Jan 05, 2017 2:55 am
Forum: APBRmetrics
Topic: 2016-17 Team Win Projection Contest / Discussion
Replies: 213
Views: 137492

Re: 2016-17 Team Win Projection Contest / Discussion

I was doing similarity measures and I noticed Ryan's entries are extremely similar to Nathan's blend, which he posted on twitter and uses Vegas numbers. They're similar to the point where it's unlikely they're his own. But I can't tell if he stole Nathan's blend with one tweak or what.
by AcrossTheCourt
Wed Jan 04, 2017 3:52 pm
Forum: APBRmetrics
Topic: 2016-17 Team Win Projection Contest / Discussion
Replies: 213
Views: 137492

Re: 2016-17 Team Win Projection Contest / Discussion

Are you allowed to use Vegas lines in the prediction? I thought you weren't.
by AcrossTheCourt
Sat Dec 31, 2016 6:36 pm
Forum: APBRmetrics
Topic: 2016-17 Team Win Projection Contest / Discussion
Replies: 213
Views: 137492

Re: 2016-17 Team Win Projection Contest / Discussion

How is 538 doing? You can choose preseason predictions:
https://projects.fivethirtyeight.com/20 ... edictions/
by AcrossTheCourt
Thu Dec 29, 2016 3:18 pm
Forum: APBRmetrics
Topic: A case where PER is NOT "good enough" to use
Replies: 32
Views: 33698

Re: A case where PER is NOT "good enough" to use

Lowry typically crushes him in on/off or adjusted +/-. It's not something to be written off. It's a pattern. Metrics like BPM or RPM have team adjustments, at least indirectly, where the collective rating equals the team's rating. If you do the same kind of adjustment BPM does with Philly, Embiid's ...
by AcrossTheCourt
Sat Dec 03, 2016 10:39 pm
Forum: APBRmetrics
Topic: 2016-17 Team Win Projection Contest / Discussion
Replies: 213
Views: 137492

Re: 2016-17 Team Win Projection Contest / Discussion

RMSE is a traditional, common measure of model fit. It's been utilized in many fields. You can find answers of why squared errors are used pretty easily on google and it's taught (or at least I hope it is) in early statistics classes. http://stats.stackexchange.com/questions/48267/mean-absolute-erro...
by AcrossTheCourt
Wed Nov 30, 2016 3:21 pm
Forum: APBRmetrics
Topic: 2016-17 Team Win Projection Contest / Discussion
Replies: 213
Views: 137492

Re: 2016-17 Team Win Projection Contest / Discussion

Analytics-based projections liked Houston because they saw that Howard was overrated, Nene is always loved by advanced stats, their defensive issues were overblown, and people put too much emphasis on their 2016 season and not 2015.