tag:blogger.com,1999:blog-5204092591876211047.post642828804005925366..comments2023-03-23T07:34:12.473-04:00Comments on Advanced NFL Stats Community: What portion of “luck” is skill? (Maybe Atlanta IS that good!?)Unknownnoreply@blogger.comBlogger11125tag:blogger.com,1999:blog-5204092591876211047.post-28911576531939426192010-12-27T08:25:21.841-05:002010-12-27T08:25:21.841-05:00Anon,
There probably is no way to establish its n...Anon,<br /><br />There probably is no way to establish its not random.<br /><br />IF part of luck is skill, this MIGHT suggest Atlanta is more consistent than most at the skill portion.Bruce D.http://i60200nfl.clanteam.comnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-60356958537599903412010-12-26T22:54:35.071-05:002010-12-26T22:54:35.071-05:00How do you establish it wasn't random chance t...How do you establish it wasn't random chance that produced Atlanta's low variance? 15 games seems a low sample size.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-51078881017369661042010-12-25T08:25:22.195-05:002010-12-25T08:25:22.195-05:00Andrew,
The points are very ad-hocish after study...Andrew,<br /><br />The points are very ad-hocish after studying Brian's EPA values for various situations. <br /><br />The data I have doesn't include where or when a fumble happens etc, so its sort of averaged out.Bruce D.http://i60200nfl.clanteam.comnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-47117875544439660792010-12-25T00:18:03.758-05:002010-12-25T00:18:03.758-05:00The fractional variance on the variance is essenti...The fractional variance on the variance is essentially Sqrt(2)/Sqrt(N), which I imagine is about 40% for this sample. So I think you'd be able to say 6 and 56 are different with some statistical confidence; 37 and 56 not so much.<br /><br />How were the luck-point values assigned? ad hoc or based on some EPA-type study?Andrew Folandhttp://nuclearmangos.blogspot.comnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-30366288270709858032010-12-24T18:52:52.615-05:002010-12-24T18:52:52.615-05:00The problem with this kind of thinking is that you...The problem with this kind of thinking is that you're asking whether there is a significant difference in a variance. To figure that out, you need the variance of the variance! The error on the error. Working that out would require a sample size so large as to be completely infeasible.<br /><br />A more sane way of addressing this is to look at the model. The question being asked is basically whether the luck factor (things not included in the model that are assumed random) should actually have been included in the model. This gives you a much larger statistical base; you can use all games over all time instead of just this season's Atlanta results. Unless there's some identifiable problem with the model, you have to assume that luck is luck. It might not be, but you could never prove it...Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-28144447480170878772010-12-24T16:41:38.639-05:002010-12-24T16:41:38.639-05:00crap, didn't format properly.crap, didn't format properly.Bruce D.http://i60200nfl.clanteam.comnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-24811150898332613782010-12-24T16:39:18.869-05:002010-12-24T16:39:18.869-05:00Andrew,
Including your standard deviation,
Team ...Andrew,<br /><br />Including your standard deviation,<br /><br />Team Luck<br /> points Varianc Standard<br /> deviation<br />nwe -60 56.1 7.5<br />atl -42 6.2 2.5<br />phi -37 12.9 3.6<br />pit -33 33 5.7<br />tam -25 6.3 2.5<br />chi -21.5 22.9 4.8<br />kan -19.5 10 3.2<br />cle -17.5 26.5 5.1<br />ari -11.5 34.9 5.9<br />bal -9.5 29.7 5.4<br />nyj -9.5 36.9 6.1<br />buf -9.5 12.6 3.6<br />ten -7.5 57.5 7.6<br />gnb -5.5 17.8 4.2<br />ind -5.5 39.1 6.2<br />oak -0.5 31 5.6<br />stl 1.5 21.5 4.6<br />hou 2 27.2 5.2<br />sfo 4 28 5.3<br />dal 6.5 40.4 6.4<br />det 9.5 25.5 5<br />nyg 9.5 40.4 6.4<br />nor 12.5 32.5 5.7<br />sea 13 48.2 6.9<br />was 13 34.2 5.8<br />den 14.5 26.7 5.2<br />car 22 16.5 4.1<br />cin 27 34.2 5.8<br />min 32 21.6 4.6<br />jac 32 27.4 5.2<br />mia 47.5 37.3 6.1<br />sdg 48 49.4 7<br />Looks so much easier to understand. Thanks a lot.Bruce D.http://i60200nfl.clanteam.comnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-49241498661908272382010-12-24T15:39:27.900-05:002010-12-24T15:39:27.900-05:00A lower variance (or st. dev.) would imply that th...A lower variance (or st. dev.) would imply that the luck is roughly the same from week to week. If you get the same amount of luck from week to week, that's not luck.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-31162381428750498032010-12-24T14:17:44.551-05:002010-12-24T14:17:44.551-05:00I like this. Seeing how lucky a team is with their...I like this. Seeing how lucky a team is with their luck.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-45587617865910641422010-12-24T13:46:55.596-05:002010-12-24T13:46:55.596-05:00The square root of the variance is the standard de...The square root of the variance is the standard deviation among games, in points. The standard deviation is basically the amount of variation among the games.<br /><br />So a team with variance of 56.2 has variation of (crudely speaking) +-7.5 luck points from one game to another; a team with variance of 6.2 has variation of +-2.5 luck points from game to game.Andrew Folandhttp://nuclearmangos.blogspot.comnoreply@blogger.comtag:blogger.com,1999:blog-5204092591876211047.post-81939845372758549652010-12-24T10:59:38.305-05:002010-12-24T10:59:38.305-05:00Bruce-Really interesting. Strong case for ATL.Bruce-Really interesting. Strong case for ATL.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.com