tag:blogger.com,1999:blog-38600807.post9010715718223364925..comments2024-10-28T16:59:39.881-04:00Comments on Advanced Football Analytics (formerly Advanced NFL Stats): In-Game Win Probabilities BetaUnknownnoreply@blogger.comBlogger25125tag:blogger.com,1999:blog-38600807.post-59254174599154540632008-09-30T01:00:00.000-04:002008-09-30T01:00:00.000-04:00Brian, after using your picks for each game this w...Brian, after using your picks for each game this week, I think you have a solid system. I find these reads interesting and in depth. Im surprised you havent been offered a job setting the Vegas Lines haha.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-78244793762226640922008-09-30T00:19:00.000-04:002008-09-30T00:19:00.000-04:00Oops. Nothing for overtime in my code. Tune in nex...Oops. Nothing for overtime in my code. Tune in next week. Offline until then. You might want to check in on Saturday. I'll be using some college games as dress rehearsals. I hope to have a far more sophisticated model in place by then.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-14778008311693855842008-09-29T16:04:00.000-04:002008-09-29T16:04:00.000-04:00Brian,You certainly have my attention, I'll be sur...Brian,<BR/>You certainly have my attention, I'll be sure to check in during next weeks games. Good Luck!Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-11844608611964159482008-09-29T12:36:00.000-04:002008-09-29T12:36:00.000-04:00Yes, I'll publish the details, at least explain th...Yes, I'll publish the details, at least explain the process as best I can. <BR/><BR/>Yes, I'm using play by play, but I'm starting with simply score difference, possession, and minutes remaining. The problem is, just with those simple starting points, and even for a 2000+ game data set, the sub-sample sizes can get extremely small for empirical analysis. (We saw that yesterday quite a bit.)<BR/><BR/>First downs are keystones of the model because there are fewer 2nd downs, and even fewer 3rd and 4th downs. Plus, 2nd, 3rd, and 4th downs have varying 'to go' distances. <BR/><BR/>(I also did some extrapolation for seconds remaining yesterday, which is why you might have noticed some strange things like a .91 WP "Based on 5 games.")<BR/><BR/>So to break it into field position and then down/distance situations dices up the data into ever-more microscopic bits. <BR/><BR/>So here's my plan (copyrighted, of course!): spine field position into 20 yard chunks or so (the chunks don't have to be equal in size), calculate the WP for each chunk for each score difference/time remaining. Then I'll do some smoothing to reduce the (large amount of) noise. (I'm just planning to do a moving average for now, but I know there are some very sophisticated methods out there for smoothing.) <BR/><BR/>Then I'd interpolate between the center points of the chunks. Say the ball is on a team's own 38. That's 12 yds short of the midpoint of the 40-40 yd line chunk, and 8 yds beyond the midpoint of the 20-40 yd line chunk. That will help with smoothing too.<BR/><BR/>For down and distance, I'd do some Markov stuff. Say it's 3rd and 3 and it's a 50/50 shot of converting. I'd compute:<BR/><BR/>.5 * having a 1st and 10 3+ yds down the field<BR/><BR/>plus<BR/><BR/>.5 * kicking (either a FG or giving the other team possession 38 yds down the field). [I'd also need some way of accounting for end-game 4th down desperation.]<BR/><BR/>Time outs and kick return possibilities are far off in the distance for now.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-23781436000128272132008-09-29T11:26:00.000-04:002008-09-29T11:26:00.000-04:00I'm going to fix the bugs (halftime, immediately a...<I>I'm going to fix the bugs (halftime, immediately after scores) add some smoothing, field position adjustments.<BR/><BR/>Then, I'll add adjustments for down/distance and other stuff.</I><BR/><BR/>Are you going to make the details available? I know you usually publish all the nitty gritty, but some people seem to like keeping this stuff to themselves.<BR/><BR/>Right now, I have a win probability model using drive charts from 5 seasons as the dataset. Basically, it gives the win prob[*] at 1st and 10 given field position, time remaining, and score differential. That's about as much as you can do with drive charts, but I'm guessing you're using play by play as your dataset, so you can do a lot more. I'm hoping that you'll publish the details so I can set up a spreadsheet to output the results.<BR/><BR/>[* Win probability is not the only response variable I can use -- I've also got models to output probability of a td, fg, score (of and kind), safety -- all logistic regression models. I also have an Expected Pts model. These are all neat and useful, but the only problem is they only work for 1st and 10 situations. Play-by-play is required for within-possession modeling.Nankerhttps://www.blogger.com/profile/12256374128701491581noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-71614031861458386262008-09-28T22:16:00.000-04:002008-09-28T22:16:00.000-04:00Thanks. Yeah, I like that site. Doing the graphs i...Thanks. Yeah, I like that site. Doing the graphs is a little over my head though. I'm not a coder or web developer at all, but that's where I'd like to go eventually. I really like how they highlight particular plays that caused big swings in in WP. <BR/><BR/>Protrade.com did this for NFL games in some form a couple years ago. ESPN.com even used their graphs in the game recaps. But they gave up on it.<BR/><BR/>Football is many times more difficult to model than baseball, so most of my efforts are going into the modeling for now.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-69536466836631083712008-09-28T22:04:00.000-04:002008-09-28T22:04:00.000-04:00Brian you should check out fangraphs.com. They do...Brian you should check out fangraphs.com. They do a similar thing for baseball games, and they show the game probabilities in graphical format. Obviously you're just starting this thing up, but it might give you some ideas.Brianhttps://www.blogger.com/profile/15394006910997218733noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-2487570681265616442008-09-28T19:47:00.000-04:002008-09-28T19:47:00.000-04:00Nice pick on DallasNice pick on DallasAnonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-62326074732813222202008-09-28T19:36:00.000-04:002008-09-28T19:36:00.000-04:00If that was the real Childress. At least he knows ...If that was the real Childress. At least he knows he sucks.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-83819733732775468732008-09-28T19:34:00.000-04:002008-09-28T19:34:00.000-04:00I'm the worst coach in the NFL. Im also mentally ...I'm the worst coach in the NFL. Im also mentally retarded. I should get fired. I dont know how to coach. I try to lose most of the time.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-61934753123916637982008-09-28T19:33:00.000-04:002008-09-28T19:33:00.000-04:00i agree brad childress should be fire, he sucks.i agree brad childress should be fire, he sucks.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-48368960937723960782008-09-28T19:31:00.000-04:002008-09-28T19:31:00.000-04:00i think the vikings win% would go up if they tried...i think the vikings win% would go up if they tried to get peterson the ball somehow. They didnt need to run more but they do need to get peterson the ball more. why cant he do wut phily did when he was their O cordinater.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-90182963958033881192008-09-28T19:02:00.000-04:002008-09-28T19:02:00.000-04:00Purely empirical at this point. Just historical co...Purely empirical at this point. Just historical comparisons. For next week, I'm going to fix the bugs (halftime, immediately after scores) add some smoothing, field position adjustments.<BR/><BR/>Then, I'll add adjustments for down/distance and other stuff.<BR/><BR/>Thanks for the feedback.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-4773565368773723212008-09-28T18:52:00.000-04:002008-09-28T18:52:00.000-04:00I've spotted a couple of odd results, but it sound...I've spotted a couple of odd results, but it sounds like you're still tweaking the setup so I will wait till next week to pipe up. I did want to ask if the win probablities are modelled or emprical?Nankerhttps://www.blogger.com/profile/12256374128701491581noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-86279684122541844622008-09-28T18:37:00.000-04:002008-09-28T18:37:00.000-04:00One other problem--when a TD or FG occurs, the win...One other problem--when a TD or FG occurs, the win probabilities flip. I might be able to fix that by the night game.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-27158824159963988662008-09-28T18:30:00.000-04:002008-09-28T18:30:00.000-04:00Good point. Thanks for the suggestion. I wasn't aw...Good point. Thanks for the suggestion. I wasn't aware you don't need standard deviation for dichotomous variables to compute conf intervals.<BR/><BR/>By next week I'll have a much better probability model, so there won't be lots of "Based on 1 games" estimates.<BR/><BR/>Today was weird though. Odd scores such as 15-6 in the 1st quarter, and others that very rarely occur.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-81512638139353389732008-09-28T16:40:00.000-04:002008-09-28T16:40:00.000-04:002*sqrt(p*(1-p)/n) doesn't seem like that much math...2*sqrt(p*(1-p)/n) doesn't seem like that much math, but you're probably right that it's not worth the effort. n pretty much tells us all we need to know.Nankerhttps://www.blogger.com/profile/12256374128701491581noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-6414256377875067672008-09-28T16:31:00.000-04:002008-09-28T16:31:00.000-04:00nanker-Nothing against conf intervals, but it'd be...nanker-Nothing against conf intervals, but it'd be a lot more math. That's why I have the "based on x games" line in there, as a poor substitute.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-42943199039132782882008-09-28T16:29:00.000-04:002008-09-28T16:29:00.000-04:00Down for an hour, but back up.Down for an hour, but back up.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-73660766194374695122008-09-28T14:35:00.000-04:002008-09-28T14:35:00.000-04:00Would it be useful or mererly confusing to present...Would it be useful or mererly confusing to present confidence intervals?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-36596642742440194982008-09-28T14:31:00.000-04:002008-09-28T14:31:00.000-04:00Probabilities are incorrect at halftime.Probabilities are incorrect at halftime.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-47691696764080900912008-09-28T14:15:00.000-04:002008-09-28T14:15:00.000-04:00Still working. It's very mobile-friendly, by the w...Still working. <BR/><BR/>It's very mobile-friendly, by the way. I'm headed out, but I'll be checking in with my Blackberry.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-37155621996276648702008-09-28T13:29:00.000-04:002008-09-28T13:29:00.000-04:00Down for a bit. Now back up 1:28pm.Down for a bit. Now back up 1:28pm.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-34832637433520295782008-09-28T12:31:00.000-04:002008-09-28T12:31:00.000-04:00Looks great. Really looking forward to watching ho...Looks great. Really looking forward to watching how this works. Good work.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-22484966521594690312008-09-28T12:24:00.000-04:002008-09-28T12:24:00.000-04:00Looking forward to your project....Any adjustment ...Looking forward to your project....Any adjustment for the game pointspread? Clearly teams favored by 7 vs getting 7 should be lined differntly at most any point in the game...<BR/><BR/>BlueCardsAnonymousnoreply@blogger.com