Page 10 of 18
Re: 2024-25 team win projection contest
Posted: Thu Jan 16, 2025 2:36 pm
by Mike G
Teemo pulls ahead, and dtka takes the RMSE lead (barely).
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 5.95 8.3 .54 eExp 6.98 8.9 .54
avgA 6.01 8.3 .51 24pr 7.01 9.6 .35
bpmW 6.09 8.2 .52 Crow 7.09 9.1 .49
WShr 6.22 8.6 .48 emin 7.13 9.5 .44
dtka 6.23 8.1 .55 eWin 7.64 9.8 .32
DQin 6.45 8.7 .50 24py 7.79 10.9 .35
KPel 6.55 8.1 .58 perW 7.91 10.1 .29
medi 6.55 9.3 .47 bmgm 8.50 11.3 .36
vegas 6.57 8.7 .51
UPDATE Jan. 18
Wisdom of the Crowd takes the (miniscule) lead.
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
avgA 5.77 8.1 .54 Crow 6.89 8.8 .51
TmTj 5.77 8.1 .56 emin 6.95 9.3 .47
dtka 5.95 7.9 .58 eExp 6.97 8.7 .56
bpmW 6.02 8.1 .56 24pr 7.01 9.6 .37
WShr 6.17 8.5 .51 eWin 7.54 9.7 .34
DQin 6.23 8.4 .54 24py 7.64 10.7 .37
medi 6.40 9.1 .49 perW 7.73 9.9 .32
vegas 6.41 8.5 .53 bmgm 8.23 11.0 .38
KPel 6.47 8.0 .60
Season low errors for avgA, dtka, and vegas. ('Season' now defined as 'since Dec. 1').
The past 4 days have also seen low/best errors for medi, and season worst for KPel and eExp. Unusual to see highs and lows on the same days.
KPel and others using his minutes are all falling away.
Checking every exponent, there are 3 lead changes between avgA and TmTj
Code: Select all
e = .10 e = 1.30 e = 1.85 e = 6.50
3.20 avgA 6.52 TmTj 7.59 dtka 12.2 KPel
3.34 TmTj 6.53 avgA 7.76 KPel 12.7 dtka
3.69 KPel 6.56 dtka 7.77 bpmW 13.5 eExp
3.74 WShr 6.66 bpmW 7.77 avgA 13.9 bpmW
3.83 medi 6.91 DQin 7.78 TmTj 13.9 TmTj
They are tied at 1.1, 1.6, and 3.5
UPDATE Jan. 21
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
avgA 5.86 8.2 .54 emin 6.97 9.3 .47
dtka 5.98 7.9 .57 eExp 7.01 8.8 .56
TmTj 6.02 8.3 .55 Crow 7.02 8.9 .51
bpmW 6.07 8.2 .54 24pr 7.11 9.7 .36
WShr 6.24 8.6 .49 eWin 7.57 9.8 .33
DQin 6.34 8.5 .53 perW 7.73 10.0 .32
vegas 6.48 8.6 .52 24py 7.80 10.9 .36
KPel 6.51 8.0 .58 bmgm 8.41 11.2 .37
medi 6.60 9.3 .48
UPDATE Jan. 24 -- Teemo roars back.
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 5.92 8.3 .54 eExp 6.80 8.8 .55
avgA 6.03 8.3 .52 medi 6.82 9.4 .46
bpmW 6.13 8.2 .53 emin 6.91 9.3 .46
dtka 6.19 8.1 .55 Crow 7.13 9.0 .50
DQin 6.36 8.6 .52 24pr 7.20 9.8 .33
WShr 6.55 8.7 .47 eWin 7.42 9.8 .33
vegas 6.62 8.7 .51 perW 7.71 10.0 .30
KPel 6.69 8.1 .57 24py 8.07 11.1 .33
. bmgm 8.63 11.4 .35
Re: 2024-25 team win projection contest
Posted: Sat Jan 25, 2025 4:08 pm
by Crow
SOS may affect projections some but BRef projections are that the top 4 in each conference with have a lower win rate for rest of season compared to season to date and the bottom 5s will all do better with one exception.
Will be interesting to see how it plays out. I have a copy of BRef current projections. Might be right in some cases but I think likely to be wrong as least as much or more often, especially with very bottom. "Wrong" modestly more often than not over last 10 games. Short term changes from season to date are more likely than longer term ones.
Re: 2024-25 team win projection contest
Posted: Sun Jan 26, 2025 2:28 pm
by Mike G
After a night when 28 of 30 teams were in action, and many blowout decisions, contestants averaged .09 better MAE; but with a wide range of effects.
Negative is better in this list:
Code: Select all
since y'day
vegas -.30
Crow -.22
medi -.21
dtka -.19
emin -.18
24pr -.13
avgA -.12
TmTj -.09
KPel -.07
eExp -.06
DQin -.05
24py -.03
bmgm .00
perW .02
eWin .04
WShr .07
bpmW .10
Season low errors for vegas and eminence; worst day for Win Shares.
The BPM entry's lead over Vegas went from .50 to .10
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 5.78 8.2 .55 eExp 6.70 8.7 .56
avgA 5.92 8.2 .53 emin 6.75 9.2 .47
dtka 6.02 8.0 .56 Crow 6.93 8.9 .51
bpmW 6.24 8.2 .53 24pr 7.04 9.7 .34
DQin 6.32 8.5 .53 eWin 7.43 9.8 .33
vegas 6.34 8.5 .53 perW 7.72 10.0 .30
KPel 6.52 8.0 .58 24py 8.00 11.0 .34
medi 6.58 9.3 .47 bmgm 8.59 11.3 .36
WShr 6.64 8.7 .47
The tiers have largely evaporated.
Re: 2024-25 team win projection contest
Posted: Sun Jan 26, 2025 7:12 pm
by Crow
Couple more days like yesterday would do a lot.
Re: 2024-25 team win projection contest
Posted: Tue Jan 28, 2025 2:33 pm
by Mike G
MAE changes in the last week. Less is better.
Code: Select all
since 1/21 since 1/21
eExp -.37 DQin .00
TmTj -.30 KPel .01
emin -.25 dtka .06
vegas -.25 avgA .10
eWin -.20 bpmW .10
Crow -.16 bmgm .21
24pr -.09 24py .24
4141 -.01 medi .30
perW -.01 WShr .36
UPDATE Jan. 31 -- Teemo is running away with it.
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 5.77 8.1 .57 WShr 6.73 8.8 .47
avgA 6.11 8.3 .54 medi 6.73 9.2 .48
dtka 6.22 8.1 .56 emin 6.91 9.2 .47
bpmW 6.30 8.3 .53 Crow 6.91 8.9 .52
vegas 6.37 8.6 .53 24pr 7.02 9.8 .35
DQin 6.45 8.6 .53 eWin 7.47 9.9 .33
KPel 6.49 8.0 .55 perW 7.85 10.2 .30
eExp 6.63 8.7 .57 24py 8.08 10.9 .35
. bmgm 8.64 11.2 .37
UPDATE Feb. 2
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 5.92 8.2 .55 medi 6.82 9.4 .46
avgA 6.39 8.3 .51 WShr 6.87 8.8 .45
dtka 6.43 8.2 .54 24pr 7.10 9.7 .34
bpmW 6.44 8.3 .51 emin 7.15 9.4 .45
KPel 6.55 7.9 .56 Crow 7.21 9.1 .49
eExp 6.55 8.7 .56 eWin 7.43 9.9 .32
vegas 6.64 8.7 .50 perW 7.85 10.1 .29
DQin 6.67 8.7 .51 24py 8.08 11.0 .34
. bmgm 8.56 11.3 .36
Worst error of the season for WS.
Yesterday, KPel had his worst error, and today his highest ranking since Dec.
Two weeks ago he had separated by .63 from his sidekicks at espn. Now they are
exactly tied, but only at e = 1.00
I notice he was up at 3 AM writing about something or another...
UPDATE Feb. 7
Now seeing largest avg error for the field, and individually for bpm, KP, WS, Crow, and 24pr
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 6.19 8.4 .53 DQin 7.01 8.9 .49
dtka 6.59 8.3 .53 WShr 7.06 9.0 .42
avgA 6.60 8.4 .50 emin 7.21 9.3 .46
bpmW 6.64 8.5 .49 24pr 7.27 9.8 .32
eExp 6.76 8.8 .56 Crow 7.35 9.2 .48
KPel 6.78 7.9 .55 eWin 7.53 9.9 .31
vegas 6.79 8.8 .50 perW 8.03 10.2 .27
medi 6.83 9.5 .45 24py 8.35 11.2 .32
. bmgm 8.79 11.5 .34
Last year around this time, medi hit their biggest lead at 1.43 better than anyone else.
Teemo was ~.50 ahead of the pack a few days ago and has slipped just a bit since.
Re: 2024-25 team win projection contest
Posted: Fri Feb 07, 2025 3:36 pm
by Crow
24py, last year's Pythagorean Wins, is doing very poorly. Worth some thought. It is a lot about coaching behavior and not a pure / reliable measure of "true" strength. Generally in that direction but not exactly or equally.
Re: 2024-25 team win projection contest
Posted: Fri Feb 07, 2025 8:31 pm
by Mike G
Yeah, this year I haven't even included actual 2024 wins, because I guessed we had enough dummies in the mix. But it seems that is sometimes a better predictor than pyth Wins. Something about winning and losing cultures, perhaps.
The 24pr seems like a convenient baseline, offering no insights regarding rookies, trades, etc. You may just suppose Orlando is on the rise, or the Clippers are shaky, and up/down-grade them from last season.
The 50% regressed version is also devoid of any updates, and yet our own (regressed?) predictions don't automatically beat it. Randomness rules!
Re: 2024-25 team win projection contest
Posted: Sat Feb 08, 2025 2:30 pm
by Mike G
The avg of all our errors is highest since Dec. 2; and the spread (from #1 to PER) is smallest in that same interval.
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 6.30 8.5 .52 DQin 7.02 8.9 .49
bpmW 6.62 8.5 .48 WShr 7.04 9.1 .42
dtka 6.66 8.3 .52 24pr 7.26 9.8 .31
avgA 6.67 8.5 .49 emin 7.36 9.4 .45
eExp 6.80 8.8 .55 Crow 7.41 9.2 .47
KPel 6.84 8.0 .54 eWin 7.49 9.9 .30
medi 6.90 9.5 .45 perW 8.00 10.2 .27
vegas 6.91 8.9 .48 24py 8.44 11.3 .31
. bmgm 8.89 11.6 .33
Teemo's lead grew steadily from his recapture around Jan. 22 to Feb. 2; narrowing from .51 to .32 since.
BPM now in 2nd with nearly its biggest error of the season. Parity is coming!
KP owns RMSE (and any power >1.5). Below 0.4 it's medi.
Feb 9.
11 days ago, we (as a group) had our lowest avg error since mid Dec; eminence and Vegas hit their season best.
Since then we've all gotten worse -- by the amounts shown:
Code: Select all
since 1/29 now
.07 bmgm 8.74
.14 medi 6.81
.18 eWin 7.50
.26 eExp 6.82
.28 24py 8.33
.30 24pr 7.25
.37 KPel 6.82
.37 perW 8.09
.39 WShr 6.98
.39 bpmW 6.56
.47 dtka 6.55
.49 DQin 6.86
.49 Crow 7.37
.50 TmTj 6.21
.57 avgA 6.54
.62 emin 7.34
.62 vegas 6.88
Not that long ago, TmTj had the worst guess on the Lakers, and now it looks like the best.
And I had the worst-looking guess for the Blazers; now back to best.
UPDATE Feb. 12
Most of us are having biggest or near-biggest errors of the season.
Leaders at some exponents:
Code: Select all
e = .10 e = .25 e = .84 e = 4.00
4.07 eWin 4.76 medi 6.11 TmTj 10.68 KPel
4.28 medi 4.78 TmTj 6.39 avgA 11.15 dtka
4.36 avgA 4.80 eWin 6.44 bpmW 12.02 TmTj
4.44 eExp 4.84 avgA 6.46 dtka 12.04 bpmW
4.46 TmTj 4.95 eExp 6.57 medi 12.11 eExp
Re: 2024-25 team win projection contest
Posted: Sun Feb 16, 2025 11:19 pm
by Mike G
AllStar Break.
15 teams are still entirely above or below all our guesses. Ten are in the West.
Code: Select all
w Atl w Bos w Brk w Cha w Chi w Cle w Det w Ind
44 pW 62 em 37 KP 34 pW 35 WS 65 b-r 42 b-r 48 pW
41 WS 61 DQ 34 WS 33 em 35 bW 52 dt 33 eW 47 mr
41 dt 61 mr 31 eW 31 Cr 34 eW 50 mr 33 pW 47 Cr
41 bW 60 dt 30 pW 31 eW 34 pW 51 KP 32 TT 47 KP
39 DQ 59 Cr 30 b-r 30 DQ 32 b-r 50 Cr 32 bW 46 dt
39 eW 59 b-r 29 bW 30 WS 32 KP 49 em 32 WS 45 b-r
39 b-r 57 TT 29 DQ 29 KP 31 TT 48 DQ 29 KP 44 em
38 mr 57 WS 26 dt 29 dt 30 dt 48 TT 28 em 44 TT
37 TT 56 bW 26 mr 28 bW 29 Cr 46 WS 28 dt 43 bW
35 Cr 52 pW 24 TT 26 TT 28 DQ 46 bW 27 Cr 43 WS
34 em 52 KP 23 em 24 mr 27 em 45 eW 26 DQ 42 DQ
32 KP 52 eW 18 Cr 23 b-r 25 mr 44 pW 26 mr 41 eW
w Mia w Mil w NYK w Orl w Phl w Tor w Was
47 em 50 dt 58 em 49 Cr 55 mr 34 KP 34 eW
45 KP 49 DQ 53 Cr 48 mr 53 eW 32 pW 33 pW
45 eW 48 em 53 b-r 46 dt 52 pW 32 WS 28 WS
43 bW 48 Cr 50 TT 44 WS 51 TT 32 em 28 bW
43 dt 47 KP 50 dt 44 KP 47 DQ 32 bW 24 KP
43 WS 45 pW 48 mr 43 DQ 47 dt 30 eW 21 dt
42 mr 45 TT 45 KP 43 TT 46 WS 30 dt 19 em
42 DQ 44 mr 44 WS 42 em 46 Cr 30 b-r 19 Cr
42 TT 44 b-r 43 DQ 41 bW 46 bW 29 mr 18 mr
41 pW 44 bW 43 bW 39 b-r 45 KP 29 DQ 16 b-r
40 Cr 44 WS 41 eW 39 eW 43 em 29 TT 15 TT
40 b-r 43 eW 38 pW 34 pW 32 b-r 25 Cr 14 DQ
w Dal w Den w GSW w Hou w LAC w LAL w Mem w Min
56 DQ 53 em 52 Cr 51 b-r 47 b-r 47 b-r 54 b-r 57 em
53 pW 53 b-r 49 DQ 47 eW 45 DQ 45 TT 51 KP 55 DQ
52 eW 51 mr 49 TT 46 mr 44 WS 44 Cr 49 Cr 53 eW
52 TT 51 dt 48 mr 45 bW 40 bW 44 dt 48 em 52 mr
51 Cr 51 eW 47 em 44 TT 40 dt 43 DQ 45 DQ 51 Cr
50 KP 49 pW 46 bW 44 Cr 36 KP 42 em 43 dt 50 WS
50 bW 49 DQ 45 dt 44 WS 36 TT 41 KP 43 eW 50 bW
47 WS 49 Cr 45 KP 43 pW 35 mr 39 mr 43 mr 50 dt
47 dt 47 KP 44 WS 40 KP 35 pW 39 bW 42 pW 48 TT
47 mr 47 WS 43 b-r 38 dt 33 Cr 38 WS 41 bW 47 b-r
45 b-r 47 bW 41 eW 36 DQ 32 em 37 pW 41 TT 46 pW
43 em 46 TT 40 pW 33 em 31 eW 36 eW 34 WS 43 KP
w NOP w OKC w Phx w Por w Sac w SAS w Uta
49 mr 66 b-r 51 TT 33 b-r 50 Cr 38 em 33 pW
49 em 62 mr 50 mr 33 KP 49 KP 37 pW 32 eW
48 Cr 61 DQ 49 dt 31 eW 49 bW 37 b-r 32 WS
45 DQ 59 TT 48 Cr 28 pW 48 pW 36 eW 31 mr
44 bW 58 em 48 pW 27 bW 47 eW 36 bW 29 KP
44 pW 55 WS 47 bW 26 Cr 47 DQ 34 WS 29 DQ
44 TT 54 bW 47 WS 26 WS 47 TT 34 TT 29 dt
44 WS 54 Cr 46 em 26 DQ 47 dt 34 KP 29 bW
44 eW 54 dt 45 KP 24 TT 46 WS 31 DQ 28 em
42 dt 54 KP 45 eW 24 mr 44 em 31 dt 27 TT
42 KP 52 pW 43 DQ 23 em 42 mr 31 mr 26 Cr
21 b-r 49 eW 37 b-r 22 dt 41 b-r 29 Cr 22 b-r
In the last 3 days before the break, almost all hit or approached our worst errors of the season. (Exceptions: medi, DQ, vegas)
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 6.38 8.6 .52 WShr 7.16 9.2 .43
dtka 6.68 8.4 .53 emin 7.42 9.5 .45
avgA 6.69 8.7 .49 24pr 7.44 10.0 .33
bpmW 6.78 8.8 .49 Crow 7.47 9.4 .47
medi 6.92 9.7 .45 eWin 7.76 10.2 .30
DQin 6.93 8.9 .50 24py 8.33 11.3 .33
KPel 6.95 8.3 .56 perW 8.36 10.5 .26
vegas 7.06 9.2 .47 bmgm 8.72 11.6 .34
eExp 7.07 9.2 .54
Re: 2024-25 team win projection contest
Posted: Mon Feb 17, 2025 12:16 am
by Crow
PER wins next to worst.
BetMGM might be strategically off to affect betting. Either that or they might be in for big losses?
Re: 2024-25 team win projection contest
Posted: Mon Feb 17, 2025 1:50 am
by DQuinn1575
Mike G wrote: ↑Sun Feb 16, 2025 11:19 pm
AllStar Break.
15 teams are still entirely above or below all our guesses. Ten are in the West.
Code: Select all
w Atl w Bos w Brk w Cha w Chi w Cle w Det w Ind
44 pW 62 em 37 KP 34 pW 35 WS 65 b-r 42 b-r 48 pW
41 WS 61 DQ 34 WS 33 em 35 bW 52 dt 33 eW 47 mr
41 dt 61 mr 31 eW 31 Cr 34 eW 50 mr 33 pW 47 Cr
41 bW 60 dt 30 pW 31 eW 34 pW 51 KP 32 TT 47 KP
39 DQ 59 Cr 30 b-r 30 DQ 32 b-r 50 Cr 32 bW 46 dt
39 eW 59 b-r 29 bW 30 WS 32 KP 49 em 32 WS 45 b-r
39 b-r 57 TT 29 DQ 29 KP 31 TT 48 DQ 29 KP 44 em
38 mr 57 WS 26 dt 29 dt 30 dt 48 TT 28 em 44 TT
37 TT 56 bW 26 mr 28 bW 29 Cr 46 WS 28 dt 43 bW
35 Cr 52 pW 24 TT 26 TT 28 DQ 46 bW 27 Cr 43 WS
34 em 52 KP 23 em 24 mr 27 em 45 eW 26 DQ 42 DQ
32 KP 52 eW 18 Cr 23 b-r 25 mr 44 pW 26 mr 41 eW
w Mia w Mil w NYK w Orl w Phl w Tor w Was
47 em 50 dt 58 em 49 Cr 55 mr 34 KP 34 eW
45 KP 49 DQ 53 Cr 48 mr 53 eW 32 pW 33 pW
45 eW 48 em 53 b-r 46 dt 52 pW 32 WS 28 WS
43 bW 48 Cr 50 TT 44 WS 51 TT 32 em 28 bW
43 dt 47 KP 50 dt 44 KP 47 DQ 32 bW 24 KP
43 WS 45 pW 48 mr 43 DQ 47 dt 30 eW 21 dt
42 mr 45 TT 45 KP 43 TT 46 WS 30 dt 19 em
42 DQ 44 mr 44 WS 42 em 46 Cr 30 b-r 19 Cr
42 TT 44 b-r 43 DQ 41 bW 46 bW 29 mr 18 mr
41 pW 44 bW 43 bW 39 b-r 45 KP 29 DQ 16 b-r
40 Cr 44 WS 41 eW 39 eW 43 em 29 TT 15 TT
40 b-r 43 eW 38 pW 34 pW 32 b-r 25 Cr 14 DQ
w Dal w Den w GSW w Hou w LAC w LAL w Mem w Min
56 DQ 53 em 52 Cr 51 b-r 47 b-r 47 b-r 54 b-r 57 em
53 pW 53 b-r 49 DQ 47 eW 45 DQ 45 TT 51 KP 55 DQ
52 eW 51 mr 49 TT 46 mr 44 WS 44 Cr 49 Cr 53 eW
52 TT 51 dt 48 mr 45 bW 40 bW 44 dt 48 em 52 mr
51 Cr 51 eW 47 em 44 TT 40 dt 43 DQ 45 DQ 51 Cr
50 KP 49 pW 46 bW 44 Cr 36 KP 42 em 43 dt 50 WS
50 bW 49 DQ 45 dt 44 WS 36 TT 41 KP 43 eW 50 bW
47 WS 49 Cr 45 KP 43 pW 35 mr 39 mr 43 mr 50 dt
47 dt 47 KP 44 WS 40 KP 35 pW 39 bW 42 pW 48 TT
47 mr 47 WS 43 b-r 38 dt 33 Cr 38 WS 41 bW 47 b-r
45 b-r 47 bW 41 eW 36 DQ 32 em 37 pW 41 TT 46 pW
43 em 46 TT 40 pW 33 em 31 eW 36 eW 34 WS 43 KP
w NOP w OKC w Phx w Por w Sac w SAS w Uta
49 mr 66 b-r 51 TT 33 b-r 50 Cr 38 em 33 pW
49 em 62 mr 50 mr 33 KP 49 KP 37 pW 32 eW
48 Cr 61 DQ 49 dt 31 eW 49 bW 37 b-r 32 WS
45 DQ 59 TT 48 Cr 28 pW 48 pW 36 eW 31 mr
44 bW 58 em 48 pW 27 bW 47 eW 36 bW 29 KP
44 pW 55 WS 47 bW 26 Cr 47 DQ 34 WS 29 DQ
44 TT 54 bW 47 WS 26 WS 47 TT 34 TT 29 dt
44 WS 54 Cr 46 em 26 DQ 47 dt 34 KP 29 bW
44 eW 54 dt 45 KP 24 TT 46 WS 31 DQ 28 em
42 dt 54 KP 45 eW 24 mr 44 em 31 dt 27 TT
42 KP 52 pW 43 DQ 23 em 42 mr 31 mr 26 Cr
21 b-r 49 eW 37 b-r 22 dt 41 b-r 29 Cr 22 b-r
In the last 3 days before the break, almost all hit or approached our worst errors of the season. (Exceptions: medi, DQ, vegas)
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 6.38 8.6 .52 WShr 7.16 9.2 .43
dtka 6.68 8.4 .53 emin 7.42 9.5 .45
avgA 6.69 8.7 .49 24pr 7.44 10.0 .33
bpmW 6.78 8.8 .49 Crow 7.47 9.4 .47
medi 6.92 9.7 .45 eWin 7.76 10.2 .30
DQin 6.93 8.9 .50 24py 8.33 11.3 .33
KPel 6.95 8.3 .56 perW 8.36 10.5 .26
vegas 7.06 9.2 .47 bmgm 8.72 11.6 .34
eExp 7.07 9.2 .54
There are 9 teams that I am within 3 games of B-Ref projections.
8 are in the East.
Re: 2024-25 team win projection contest
Posted: Mon Feb 17, 2025 5:37 am
by Crow
Half a point or a point off of the leader is not much and still pretty good.
To get closer to actual, a projection set probably needs to expect the statistically unexpected, in the right way.
Statistically unexpected or just unaccounted for?
Brooklyn, new head coach wanting to prove competency before tank. Hornets, LaMelo injured again. Pistons get vet starters and a Coach. TWolves lose their star. Pelicans really don't make sense and then get injured. Thunder ascend with effort and clunky part removed. Embid and George don't play much.
Not going to guess all the unexpected. Injuries are a big factor. But some looking beyond the strict numbers maybe helpful. Unless you are playing very conservative.
What's the average length of time before teams bounce off their bottom? Closer to 3 or 4? I don't actually know. Checking could help.
Re: 2024-25 team win projection contest
Posted: Sun Feb 23, 2025 1:19 pm
by Mike G
Worse than the last report but not as bad as yesterday.
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 6.33 8.7 .52 WShr 7.27 9.3 .42
dtka 6.63 8.5 .52 Crow 7.40 9.5 .46
avgA 6.74 8.8 .49 emin 7.52 9.6 .45
KPel 6.83 8.3 .55 24pr 7.55 10.1 .32
medi 6.84 9.8 .44 eWin 7.95 10.4 .28
DQin 6.90 9.0 .50 24py 8.28 11.3 .32
bpmW 6.92 8.9 .47 perW 8.42 10.6 .25
vegas 7.02 9.3 .46 bmgm 8.64 11.7 .34
eExp 7.14 9.3 .54
Pelton trending up, bpm sinking.
UPDATE feb. 25 -- Closest #1-2 since Jan. 23
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 6.41 8.8 .51 eExp 7.26 9.4 .53
dtka 6.57 8.6 .52 WShr 7.29 9.4 .42
avgA 6.72 8.8 .48 Crow 7.45 9.4 .47
medi 6.87 9.8 .44 emin 7.49 9.6 .45
bpmW 6.90 8.9 .47 24pr 7.56 10.1 .32
KPel 6.91 8.4 .56 eWin 8.07 10.4 .28
DQin 6.96 9.1 .49 24py 8.31 11.4 .32
vegas 7.18 9.4 .46 perW 8.55 10.7 .25
eExp 7.26 9.4 .53 bmgm 8.70 11.7 .33
e=.25 e=.85 e=1.60 e=4.6
4.32 dtka 6.04 TmTj 7.84 dtka 11.3 KPel
4.54 TmTj 6.21 dtka 7.86 KPel 11.8 dtka
4.64 medi 6.41 medi 7.86 TmTj 12.7 bpmW
5.11 bpmW 6.56 bpmW 8.15 bpmW 13.0 TmTj
5.22 DQin 6.62 DQin 8.26 DQin 13.1 WShr
5.31 vegas 6.65 KPel 8.53 vegas 13.1 DQin
Re: 2024-25 team win projection contest
Posted: Fri Feb 28, 2025 4:19 pm
by Crow
AvgAPBR over ESPN experts and Vegas at this point.
50% BPM + 50%TT?
30% BPM + 30%TT +40% avgA?
How good would they be?
50% avgA + 50% Eexp?
What composite, if any, gets below 6.0 avg error?
Re: 2024-25 team win projection contest
Posted: Fri Feb 28, 2025 6:26 pm
by knarsu3
Is there a reason the LEBRON and DARKO projections aren't included?
Mike G wrote: ↑Sun Feb 23, 2025 1:19 pm
Worse than the last report but not as bad as yesterday.
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 6.33 8.7 .52 WShr 7.27 9.3 .42
dtka 6.63 8.5 .52 Crow 7.40 9.5 .46
avgA 6.74 8.8 .49 emin 7.52 9.6 .45
KPel 6.83 8.3 .55 24pr 7.55 10.1 .32
medi 6.84 9.8 .44 eWin 7.95 10.4 .28
DQin 6.90 9.0 .50 24py 8.28 11.3 .32
bpmW 6.92 8.9 .47 perW 8.42 10.6 .25
vegas 7.02 9.3 .46 bmgm 8.64 11.7 .34
eExp 7.14 9.3 .54
Pelton trending up, bpm sinking.
UPDATE feb. 25 -- Closest #1-2 since Jan. 23
Code: Select all
. avg err rmse r^2 . avg err rmse r^2
TmTj 6.41 8.8 .51 eExp 7.26 9.4 .53
dtka 6.57 8.6 .52 WShr 7.29 9.4 .42
avgA 6.72 8.8 .48 Crow 7.45 9.4 .47
medi 6.87 9.8 .44 emin 7.49 9.6 .45
bpmW 6.90 8.9 .47 24pr 7.56 10.1 .32
KPel 6.91 8.4 .56 eWin 8.07 10.4 .28
DQin 6.96 9.1 .49 24py 8.31 11.4 .32
vegas 7.18 9.4 .46 perW 8.55 10.7 .25
eExp 7.26 9.4 .53 bmgm 8.70 11.7 .33
e=.25 e=.85 e=1.60 e=4.6
4.32 dtka 6.04 TmTj 7.84 dtka 11.3 KPel
4.54 TmTj 6.21 dtka 7.86 KPel 11.8 dtka
4.64 medi 6.41 medi 7.86 TmTj 12.7 bpmW
5.11 bpmW 6.56 bpmW 8.15 bpmW 13.0 TmTj
5.22 DQin 6.62 DQin 8.26 DQin 13.1 WShr
5.31 vegas 6.65 KPel 8.53 vegas 13.1 DQin