tag:blogger.com,1999:blog-38600807.post3302983900380039269..comments2023-11-05T04:16:44.937-05:00Comments on Advanced Football Analytics (formerly Advanced NFL Stats): Is 3rd Down Conversion Percentage a Good Stat?Unknownnoreply@blogger.comBlogger10125tag:blogger.com,1999:blog-38600807.post-50289564328617984222008-01-16T10:45:00.000-05:002008-01-16T10:45:00.000-05:00What if wk 1-8 DVOA and wk 9-17 DVOA aren't correl...<I>What if wk 1-8 DVOA and wk 9-17 DVOA aren't correlated very highly?</I><BR/><BR/>I would be fairly shocked if that were true, even for the lousy teams. This is because staying consistent (i.e. having good correlation with later measurements of the same stat) should be true even for stats that are actually poor measures of team strength.<BR/><BR/>Let me give an example. Let's say we believed all the cliches that the talking heads cite. With that in mind, we formulated a power ranking that was based on rushing yardage, opposing rushing yardage, and turnover differential. Virtually every clear-headed analysis of football statistics has shown that this is a crappy way to measure team strength. Nevertheless, I have a feeling that it would come out as pretty strongly self-correlated over two halves of the season. My point is that self-correlation, in and of itself, does not prove much about the quality of a stat.<BR/><BR/>For what it's worth, the preseason projections of DVOA have a .71 correlation with that season's DVOA. Given what a crapshoot preseason projections are, that's not bad. They don't list 1st-2nd half correlations anywhere, but the game-by-game DVOAs are in the premium database so I could calculate them if I wanted to.<BR/><BR/><I>I think we're thinking along the same lines. One of my next projects is to adjust my model's coefficients in proportion to how noisy they are (after being adjusted for opponent).</I><BR/><BR/>Yes, exactly. My point about DVOA is that they are (implicitly) weighting one source of data (3rd down performance) more heavily that two other sets of data (1st and second down performance), despite what I suspect are nearly equal levels of noise and nearly equal degrees of correlation with future team success. I think they would have a more consistent and meaningful measure if they tweaked the numbers to give roughly equal weight to results from all three downs (on a per-play basis).<BR/><BR/><I>The other option is to discard the noisy stats altogether.</I><BR/><BR/>This is, of course, a classic problem when constructing a model.Tarrhttps://www.blogger.com/profile/09242627723328062618noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-60869641213772703732008-01-15T19:47:00.000-05:002008-01-15T19:47:00.000-05:00I guess I misunderstood your theory.What if wk 1-8...I guess I misunderstood your theory.<BR/><BR/>What if wk 1-8 DVOA and wk 9-17 DVOA aren't correlated very highly? The obvious teams would correlate, such as the Pats and Colts, but what about the majority of teams?<BR/><BR/>I think we're thinking along the same lines. One of my next projects is to adjust my model's coefficients in proportion to how noisy they are (after being adjusted for opponent). The other option is to discard the noisy stats altogether.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-20807045612553721022008-01-15T19:19:00.000-05:002008-01-15T19:19:00.000-05:00I don't think that analysis would effectively supp...I don't think that analysis would effectively support or detract from my theory. As I understand it, DVOA basically:<BR/><BR/>1) calculates the expected points of down/distance before and after a given play, and<BR/><BR/>2) Normalizes this result against a league-average result at that down/distance.<BR/><BR/>The issue is that the impact on expected points is magnified on third down, simply because third down plays have a lot of leverage on the outcome of drives. So third down plays (both good and bad) form a disproportionately large part of the measure.<BR/><BR/>I have no doubt that week 1-8 DVOA is strongly correlated with week 9-17 DVOA. That's not really my point, and moreover any cobbling of stats is going to accomplish that much. I'm suggesting that the way DVOA is calculated is essentially increasing the error in the measurement, and the correlation could be made better.<BR/><BR/>My contention is that the correlation would improve if the weight of the third down plays were artificially reduced, such that they were not as much more important than first or second down. My suspicion is that third down could/should still have a slightly greater weight than first or second, simply because the skills that are valuable on third down are slightly different than first and second, and therefore are probably slightly more useful overall.<BR/><BR/>Unfortunately, I don't have access to the raw PBP data, or the down/distance expected points tables that are the foundation of DVOA. So I can't really test my hypothesis.Tarrhttps://www.blogger.com/profile/14368810359650066790noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-68168619084112240262008-01-15T18:51:00.000-05:002008-01-15T18:51:00.000-05:00Tarr-Factoring in yard line and down and distance ...Tarr-Factoring in yard line and down and distance is what DVOA really is. I think they try to factor in time remaining and score difference too. So it would be easy enough to test your hypothesis by repeating the longitudinal auto-correlation analysis of Week 1-8 DVOA with Week 9-17 DVOA.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-76733985779986025322008-01-15T17:07:00.000-05:002008-01-15T17:07:00.000-05:00Very nice analysis. You've made an extremely stro...Very nice analysis. You've made an extremely strong case that considering 3rd down conversion percentage as part of a model based on overall game stats is a bad idea.<BR/><BR/>It would be interesting to see if it holds true if we consider individual play results as oppose to aggregated stats. It's possible that when we consider the context (distance to the marker, and field position) of a given 3rd down, we remove enough noise that the conversion becomes a useful, non-redundant piece of information.<BR/><BR/>That said, I've always been bothered by how heavily DVOA considers the third down. FO seems at least peripherally aware of how misleading this may be, since they have talked extensively about the "third down rebound", where a team that is playing over their heads on third down tends to regress, and vice versa. One possible conclusion would be that if DVOA didn't weight third down as heavily, they wouldn't regress - they'd just be rated lower. It seems like this would improve year-to-year DVOA correlation, which is a stated goal in improving the algorithm.<BR/><BR/>Sometimes it seems like DVOA is torn between being descriptive and being predictive. Weighting 3rd downs more heavily would improve correlation to past wins, surely, but it probably introduces a bias in predicting future ones.Tarrhttps://www.blogger.com/profile/09242627723328062618noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-34085206965101453972008-01-14T01:02:00.000-05:002008-01-14T01:02:00.000-05:00Yes. I'll post how various stats can predict other...Yes. I'll post how various stats can predict other stats in a future post.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-52413808232211810502008-01-12T13:59:00.000-05:002008-01-12T13:59:00.000-05:00It's actually adjusted r-squared, which corrects f...It's actually adjusted r-squared, which corrects for the number of added variables.Brian Burkehttps://www.blogger.com/profile/12371470711365236987noreply@blogger.comtag:blogger.com,1999:blog-38600807.post-59889963714707019302008-01-12T13:14:00.000-05:002008-01-12T13:14:00.000-05:00Are you using OLS for these regressions? Adding a...Are you using OLS for these regressions? Adding a variable should never decrease the R-squared.Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-53793703117490621362008-01-12T11:53:00.000-05:002008-01-12T11:53:00.000-05:00Nice article, apparently 3D conversion is just too...Nice article, apparently 3D conversion is just too noisy to be used as a predictor for anything, including itself. <BR/><BR/>Are other stats better predicted without reference to themselves?Anonymousnoreply@blogger.comtag:blogger.com,1999:blog-38600807.post-37239185469860560302008-01-12T11:50:00.000-05:002008-01-12T11:50:00.000-05:00Have you considered looking at the first down to t...Have you considered looking at the first down to third down ratio?<BR/>Maybe something like 1d/3da or 1d - 3d failure.<BR/>Those would corrolate better with points.<BR/>They would include first downs made on downs 1 and 2.<BR/>also yards per third down attempts or yards per third down failures would corrallate pretty well with points.Anonymousnoreply@blogger.com