The Pitfalls of "Regression to the Mean" analysis (1 Viewer)

[Creed Bratton]

I agree with you when people frequently over-attribute an individual's circumstances in similar situations and overlook reasons that suggest otherwise. But just because that's the case in other situations doesn't mean it applies in every situation. You're assuming that 2006 Eli Manning in the third year of his career is the same player as Eli Manning of last year. Eli's completion percentage and yards per attempt have increased gradually as his career progressed and is probably indicative of his growth as a quarterback. I believe that he has QB 5-8 upside and it has as much to do with his growth as a quarterback and his receivers as it does the other quarterbacks in the league. Roethlisberger got suspended and lost Holmes, Rivers lost his best receiver and left tackle, and it's not unreasonable to think that age catches up to Favre. You make the claim that the numbers were inflated in 2009 similar to wide receivers in 1995 and say that a "rising tide lifts all ships", but then give no reason to explain that at all. It's easy to see how that expression might explain a particular team but not the league as a whole for last season pertaining to just quarteracks. I have a much simpler explanation that isn't nearly as vague. A few quarterbacks had their situations improve or stay static and none of the major quarterbacks really missed time due to injury. Schaub, Romo, and Brady all missed significant time in 2008 and the Steelers passing attack improved while Favre played with better receivers and without a torn biceps. Those are tangible explanations for the increase in 4000 yard pasers and not some vague "rising tide"You say that Eli's improved numbers(as well as the rest of the league) were the product of NFL environment last season and then give no explanation as to what that could be. I fully expect Eli's positional ranking to increase this year and it has as much to do with Eli and his situation as well as the other quarterbacks he's competing against as well. That doesn't mean I believe in regression to the mean for every quarterback in the NFL besides Eli, it just means that I think his situation has improved while several of the other quarterbacks ahead of him last season have had their prospects worsen.

I can spell out what "a rising tide lifts all ships" means. Here is the average passing yardage per team game in each year of the past decade:2009- 218.52008- 211.32007- 214.32006- 204.82005- 203.52004- 210.5 (this was the year of the "passing explosion" as the league cracked down on PI)2003- 200.42002- 212.22001- 205.82000- 206.9The 2009 passing totals were a full 4 yards per game higher than the next highest season of the past decade, and 11 yards per game more than the average of the previous 9 seasons (207.7). The league as a whole saw a passing explosion the likes of which it hadn't ever seen before (that's the "rising tide"), and the result was 10 players reaching the 4,000 yard passing mark (those are the ships that all got lifted). I don't see any meaningful trends in that passing yardage, so it's possible that the yardage goes down hard next year and the league sees its 4,000 yard QBs reduced to the typical 3 or 4. It's also possible that it stays high and the league sees a DOZEN 4,000 yard QBs next year. Neither of which has the slightest impact on Manning's ordinal ranking vs. his peers.Now, you make a good point about some of the guys ahead of Manning and why they won't finish there again. Favre is old, Roethlisberger is suspended, Rivers is missing his weapons. At the same time, a similar case can be made for why the guys behind Eli are going to suddenly jump him. You've got Flacco, Ryan, Sanchez, Stafford, Henne, Leinart, Young, and Freeman poised to make big jumps. Jay Cutler just gained Mike Martz. Donovan McNabb has another chance to play 16 games (he scored more FP/G than Eli last season). Carson Palmer's another year removed from his injury, and he's got better weapons now.At the end of the day, Eli Manning is a guy who has finished 10th or worse for 4 straight years, even in his career year (which happened to come during the most QB-friendly season of at least the last decade). As I'm fond of saying... at this point, he is who we thought he was. Don't let him off the hook.

None of this should take away from what I think might be SSOG's essential points:(a) On average, if a player has played 5 season and then puts up their best, you will tend to be wrong if you predict all such players maintain that level. You might be right about some, but don't make a habit of it.(b) People who try to find reasons for the increase will surely find SOMETHING (much as I can starting at cumulous clouds), the question is whether they are making a "fundamental attribution error": assuming the increase was due to something about the person and not the situation. Or ignoring situational factors that affected that single season that will not be there anymore.So even if we discount a person-based attribution for Manning (that his skill or ability has improved), could be better WRs but could be decreased rushing from RBs.To the extent those cancel, I go with RTM.BTW, when I do not tend to go with RTM is when a new player improves each of their first 3 seasons.

I need to keep ookook on retainer to start following me around and clarifying what I mean better than I can explain it. That's pretty much exactly what I'm trying to say, in far fewer words than I've been using.

See, you've done a good job describing the "rising tide" but nobody was disputing that there was a spike in 4000 yard passers or quarterback numbers last year. My criticism was, and still is, is that there is no explanation for that statistical phenomena in your argument. Unless you can explain the specific causal factors for that rising tide and how it affected Eli Manning as well as the other quarterbacks in the league last year and how you project those factors will impact those players next season, that statistical phenomena is pretty meaningless for our purposes.The other argument that you make is that Eli Manning is a quarterback who has never been better than QB10 four straight seasons so there's no reason to think why he'll be better. By that line of logic, Kurt Warner had far worse numbers before lighting it up in Arizona and it had as much to do with the improvement in his situation as anything else. It illustrates how a quarterback can finish no better than QB23 for five straight seasons before putting up 2 consecutive top ten finishes. You say Eli finished between QB10-13 for four straight seasons so that's who he is. I say that he finished at QB 10,13,13,and 10 for four straight seasons while his surrounding receiving talent got progressively worse until last season.The only other reason you have to state against Eli's interpositional ranking is that other quarterbacks are also expected to improve and that will serve as a check against better quarterbacks doing worse this season. But in order for that to hold true and Eli's ranking to stay about the same, you're requiring a bigger "statistical leap of faith" for some of those younger quarterbacks. You say that we shouldn't let Eli off the hook, but have no problem doing that for any number of younger quarterbacks. I'm not letting Eli off the hook, because this is a quarterback who has finished at QB5 when surrounded with talent at the skill positions. If Steve Smith or Nicks were to blow out their knee, you wouldn't be seeing a lot of top ten rankings for Eli, at least not from me. If anything it's a far safer and more conservative projection that Eli finishes inside the top ten rather than one of the other younger and lower ranked quarterbacks. A person with greater rankings inertia should favor Eli rather than discount him.

 

[SSOG]

See, you've done a good job describing the "rising tide" but nobody was disputing that there was a spike in 4000 yard passers or quarterback numbers last year. My criticism was, and still is, is that there is no explanation for that statistical phenomena in your argument. Unless you can explain the specific causal factors for that rising tide and how it affected Eli Manning as well as the other quarterbacks in the league last year and how you project those factors will impact those players next season, that statistical phenomena is pretty meaningless for our purposes.The other argument that you make is that Eli Manning is a quarterback who has never been better than QB10 four straight seasons so there's no reason to think why he'll be better. By that line of logic, Kurt Warner had far worse numbers before lighting it up in Arizona and it had as much to do with the improvement in his situation as anything else. It illustrates how a quarterback can finish no better than QB23 for five straight seasons before putting up 2 consecutive top ten finishes. You say Eli finished between QB10-13 for four straight seasons so that's who he is. I say that he finished at QB 10,13,13,and 10 for four straight seasons while his surrounding receiving talent got progressively worse until last season.The only other reason you have to state against Eli's interpositional ranking is that other quarterbacks are also expected to improve and that will serve as a check against better quarterbacks doing worse this season. But in order for that to hold true and Eli's ranking to stay about the same, you're requiring a bigger "statistical leap of faith" for some of those younger quarterbacks. You say that we shouldn't let Eli off the hook, but have no problem doing that for any number of younger quarterbacks. I'm not letting Eli off the hook, because this is a quarterback who has finished at QB5 when surrounded with talent at the skill positions. If Steve Smith or Nicks were to blow out their knee, you wouldn't be seeing a lot of top ten rankings for Eli, at least not from me. If anything it's a far safer and more conservative projection that Eli finishes inside the top ten rather than one of the other younger and lower ranked quarterbacks. A person with greater rankings inertia should favor Eli rather than discount him.

Why do I need to be able to describe the causal factors behind a statistical phenomenon in order to account for it in my projections going forward? Justin Forsett averaged 5.4 yards per carry. I'm pretty sure that was a statistical fluke, and so I'd expect it to regress... even if I have no clue how Justin Freaking Forsett managed to average 5.4 yards per carry last year. Last year was a big year for passing. Why? I don't know. Maybe the referees were instructed to be a little bit more lenient on holding calls. Maybe the talent level of the average CB was slightly lower than it was the year before. Maybe the new Tom Brady Rule led to fewer QB injuries, which led to better QB play around the league, which led to more passing yardage. Maybe it was just a statistical fluke with no cause other than simple random variation. All I know is that the league's passing yardage average has ebbed and flowed for the past decade with no real rhyme or reason, so if this year was an all-time high, then next year is likely to be significantly lower.Second off, Kurt Warner is an incredibly disingenuous comp for Eli Manning. In 2001, he was 1st in 16 games. In '07 he was 10th in 14 games. In '08 he was 4th in 16 games. From 2002-2006, he failed to rank higher than 23rd, which might seem a tiny bit relevant until you look at the number of games he played. In those 5 seasons he played 7, 2, 10, 10, and 7 games. In other words, when Warner played 14 games he was a top-10 QB. When he played 16 games he was a top-5 QB. When he played 10 games he wasn't a top-20 QB. That's another perfect example of "he is who we thought he was". Anyway, as I said, I fail to see how a guy who played 10 or fewer games for 5 straight years is a decent comp for a guy who hasn't missed a game in the past 5 seasons.Also, I don't think it's a "bigger statistical leap of faith" to expect a 3rd year QB who has been steadily improving to continue his improvement than it is to expect a 7th year QB to suddenly morph into a radically different player. It's far too early to say that Matt Ryan or Joe Flacco (2 year vets) "are who we thought they were". They're still learning the game. Eli Manning, on the other hand, is a 6-year vet who gave us SIX YEARS worth of incredibly, incredibly consistent data to analyze. At this point, I'm far more inclined to believe that what we see is what we get, and any dramatic departures from that (such as last season) are statistical outliers and therefore the perfect subject of "regression to the mean". I believe that most of the time when a player plays at an incredibly flat level for 5 years and then sees a sudden spike in year 6, that spike is more likely statistical noise than it is meaningful trend. I'd like to see some examples of players who saw dramatic spikes 5 or 6 years into their career who then managed to maintain their new, higher level of production. I suppose you could go with Thomas Jones, but Thomas Jones actually showed signs of being a quality football player in year 4 in Tampa Bay (which, not coincidentally, was his first season after he got out of the black hole that was early-2000s Arizona). There was Jake Plummer, but once again, Jake Plummer's signs of life coincided perfectly with Jake Plummer getting the hell out of Arizona. If you rule out players who left Arizona, I can't think of anyone who showed pretty much nothing for the first 5 years of their career who then went on to be major fantasy assets.I also fail to see why someone with a high degree of rankings inertia should favor Eli. I've had Eli outside of my dynasty top 12 for years now. Inertia means that I resist efforts to move a player, so I don't see why I should be more likely to suddenly put Eli in my top 12 based on the strength of one outlier season. That's the opposite of rankings inertia.

 

[Creed Bratton]

See, you've done a good job describing the "rising tide" but nobody was disputing that there was a spike in 4000 yard passers or quarterback numbers last year. My criticism was, and still is, is that there is no explanation for that statistical phenomena in your argument. Unless you can explain the specific causal factors for that rising tide and how it affected Eli Manning as well as the other quarterbacks in the league last year and how you project those factors will impact those players next season, that statistical phenomena is pretty meaningless for our purposes.The other argument that you make is that Eli Manning is a quarterback who has never been better than QB10 four straight seasons so there's no reason to think why he'll be better. By that line of logic, Kurt Warner had far worse numbers before lighting it up in Arizona and it had as much to do with the improvement in his situation as anything else. It illustrates how a quarterback can finish no better than QB23 for five straight seasons before putting up 2 consecutive top ten finishes. You say Eli finished between QB10-13 for four straight seasons so that's who he is. I say that he finished at QB 10,13,13,and 10 for four straight seasons while his surrounding receiving talent got progressively worse until last season.The only other reason you have to state against Eli's interpositional ranking is that other quarterbacks are also expected to improve and that will serve as a check against better quarterbacks doing worse this season. But in order for that to hold true and Eli's ranking to stay about the same, you're requiring a bigger "statistical leap of faith" for some of those younger quarterbacks. You say that we shouldn't let Eli off the hook, but have no problem doing that for any number of younger quarterbacks. I'm not letting Eli off the hook, because this is a quarterback who has finished at QB5 when surrounded with talent at the skill positions. If Steve Smith or Nicks were to blow out their knee, you wouldn't be seeing a lot of top ten rankings for Eli, at least not from me. If anything it's a far safer and more conservative projection that Eli finishes inside the top ten rather than one of the other younger and lower ranked quarterbacks. A person with greater rankings inertia should favor Eli rather than discount him.

Why do I need to be able to describe the causal factors behind a statistical phenomenon in order to account for it in my projections going forward? Justin Forsett averaged 5.4 yards per carry. I'm pretty sure that was a statistical fluke, and so I'd expect it to regress... even if I have no clue how Justin Freaking Forsett managed to average 5.4 yards per carry last year. Last year was a big year for passing. Why? I don't know. Maybe the referees were instructed to be a little bit more lenient on holding calls. Maybe the talent level of the average CB was slightly lower than it was the year before. Maybe the new Tom Brady Rule led to fewer QB injuries, which led to better QB play around the league, which led to more passing yardage. Maybe it was just a statistical fluke with no cause other than simple random variation. All I know is that the league's passing yardage average has ebbed and flowed for the past decade with no real rhyme or reason, so if this year was an all-time high, then next year is likely to be significantly lower.Second off, Kurt Warner is an incredibly disingenuous comp for Eli Manning. In 2001, he was 1st in 16 games. In '07 he was 10th in 14 games. In '08 he was 4th in 16 games. From 2002-2006, he failed to rank higher than 23rd, which might seem a tiny bit relevant until you look at the number of games he played. In those 5 seasons he played 7, 2, 10, 10, and 7 games. In other words, when Warner played 14 games he was a top-10 QB. When he played 16 games he was a top-5 QB. When he played 10 games he wasn't a top-20 QB. That's another perfect example of "he is who we thought he was". Anyway, as I said, I fail to see how a guy who played 10 or fewer games for 5 straight years is a decent comp for a guy who hasn't missed a game in the past 5 seasons.Also, I don't think it's a "bigger statistical leap of faith" to expect a 3rd year QB who has been steadily improving to continue his improvement than it is to expect a 7th year QB to suddenly morph into a radically different player. It's far too early to say that Matt Ryan or Joe Flacco (2 year vets) "are who we thought they were". They're still learning the game. Eli Manning, on the other hand, is a 6-year vet who gave us SIX YEARS worth of incredibly, incredibly consistent data to analyze. At this point, I'm far more inclined to believe that what we see is what we get, and any dramatic departures from that (such as last season) are statistical outliers and therefore the perfect subject of "regression to the mean". I believe that most of the time when a player plays at an incredibly flat level for 5 years and then sees a sudden spike in year 6, that spike is more likely statistical noise than it is meaningful trend. I'd like to see some examples of players who saw dramatic spikes 5 or 6 years into their career who then managed to maintain their new, higher level of production. I suppose you could go with Thomas Jones, but Thomas Jones actually showed signs of being a quality football player in year 4 in Tampa Bay (which, not coincidentally, was his first season after he got out of the black hole that was early-2000s Arizona). There was Jake Plummer, but once again, Jake Plummer's signs of life coincided perfectly with Jake Plummer getting the hell out of Arizona. If you rule out players who left Arizona, I can't think of anyone who showed pretty much nothing for the first 5 years of their career who then went on to be major fantasy assets.I also fail to see why someone with a high degree of rankings inertia should favor Eli. I've had Eli outside of my dynasty top 12 for years now. Inertia means that I resist efforts to move a player, so I don't see why I should be more likely to suddenly put Eli in my top 12 based on the strength of one outlier season. That's the opposite of rankings inertia.

Well, I think if you're going to downgrade Eli's prospects for the season because of that particular statistical phenomena then it is important to know why. As you said, it could be anything including fluke coincidence so why does that automatically mean you have to discount Eli's numbers for last season? It could just as easily be a reason to value Eli as it is to devalue him or have no impact at all. Even if you think that next year's passing yardage decreases across the board(which I do as well), there's no reason to think that applies Eli anymore than another quarterback.The Kurt Warner example was not incredibly disingenuous because my fundamental point was to illustrate a quarterback's productivity in relation to his surrounding talent. That point holds up even if you look at Warner's productivity on a per game basis. There were several seasons in the middle of his career in which his completion percentage, yards per attempt, yards per game, touchdown percentage, and fantasy points per game were generally lower when he had less talent surrounding him. It wasn't a perfect comparison, but it doesn't betray the underlying point I was trying to make.I think I would also like to see how many players show marked improvement after their first three or four seasons as well. Ultimately, I don't think that type of data would be the most overwhelming piece of evidence in evaluating Eli's prospects for the season, but it would be interesting to see. One example I can think of is Rich Gannon, who was a late bloomer as a quarterback and had several good statistical seasons with the Raiders. And i still disagree with you when you say that Eli's performance as a quarterback has been incredibly flat. There's a lot of evidence to indicate that he's becoming a more accurate quarterback including a steady increase in his completion percentage throughout his career and as well as a better TD/INT ratio in recent seasons.

 

[Chase Stuart]

Last year was a big year for passing. Why? I don't know. Maybe the referees were instructed to be a little bit more lenient on holding calls. Maybe the talent level of the average CB was slightly lower than it was the year before. Maybe the new Tom Brady Rule led to fewer QB injuries, which led to better QB play around the league, which led to more passing yardage. Maybe it was just a statistical fluke with no cause other than simple random variation. All I know is that the league's passing yardage average has ebbed and flowed for the past decade with no real rhyme or reason, so if this year was an all-time high, then next year is likely to be significantly lower.

I'm not sure if this year will bring down passing numbers, absent QB injury (last year was certainly a healthy year for quarterbacks, so that inflated passing numbers a bit). But QB passing averages have been on the rise significantly over the years.Here are the ANY/A league-wide averages over the last 40 years:

YR	ANY/A2009	5.662008	5.702007	5.512006	5.392005	5.342004	5.642003	5.202002	5.342001	5.192000	5.211999	5.181998	5.301997	5.151996	5.131995	5.411994	5.381993	5.111992	4.881991	5.171990	5.281989	5.241988	5.031987	5.051986	4.951985	4.861984	5.001983	4.981982	4.751981	4.991980	4.861979	4.591978	4.031977	3.541976	4.061975	4.021974	3.881973	3.881972	4.261971	3.901970	4.15

The last two years have been the most successful seasons by ANY/A standards, and last year wasn't even as good as '08. I'm not sure a regression is in order. More to the point for fantasy purposes, passing attempts are on the rise as teams get better at passing.

YR	ANY/A	Att/G2009	5.66	33.192008	5.70	32.202007	5.51	33.252006	5.39	31.942005	5.34	32.092004	5.64	31.832003	5.20	32.112002	5.34	33.672001	5.19	32.542000	5.21	32.851999	5.18	33.741998	5.30	32.191997	5.15	32.731996	5.13	33.211995	5.41	34.731994	5.38	33.551993	5.11	32.111992	4.88	29.851991	5.17	31.061990	5.28	30.091989	5.24	31.951988	5.03	31.461987	5.05	32.051986	4.95	32.171985	4.86	32.081984	5.00	31.831983	4.98	31.191982	4.75	31.311981	4.99	31.521980	4.86	30.481979	4.59	28.851978	4.03	26.261977	3.54	24.781976	4.06	26.061975	4.02	27.271974	3.88	26.291973	3.88	24.211972	4.26	24.591971	3.90	25.701970	4.15	26.76

Attempts spiked in 1995, the year all those receivers in the NFC had absurd yardage totals. But for the most part, attempts have been relatively flat over the last 15-20 years. In 1994 teams averaged more attempts per game than in 2009. I'm not sure why that is (although if I had more time I could test any of the following theories), but maybe teams are also running less often and there are just fewer plays per game, maybe there are more QB runs, maybe fewer incompletions lead to fewer plays with a more constantly running clock, maybe good teams are passing less often but bad teams are passing more often, etc. But at some point, that might change. If you think the NFL is pass happy now, it might become really pass happy soon. Teams are getting really, really good at passing, and pretty soon, I think that means teams are going to pass even more than they do now. So come 2010 or 2011, we might see even more 4,000 yard passers.

 

[ookook]

I think that it is hard to project that someone like Manning will continue to come in 10th (let alone 9th) when it is better than ANY of his other 5 seasons. He is 1 for 6 on Top 10, just sqeaking in on that one. Regression to the means is one reason and the anamolous rushing attempts/success in the second half being the other.

And I like the guy as a QB. I have him a "safe" 12th.

But I confess some amusement at people that have Favre 11th or 12th when he has been Top 10 in something like 7 of his last 10 seasons and has EXCATLY the same situation for the most part as last year (3rd?), and then have E. Manning at 9th who is 1 for 6 with a much higher median ranking.

With that said, I hold Favre to the same standard of regressing to his mean and have him around 7th.

 

[Chase Stuart]

I think that it is hard to project that someone like Manning will continue to come in 10th (let alone 9th) when it is better than ANY of his other 5 seasons. He is 1 for 6 on Top 10, just sqeaking in on that one. Regression to the means is one reason and the anamolous rushing attempts/success in the second half being the other.

And I like the guy as a QB. I have him a "safe" 12th.

But I confess some amusement at people that have Favre 11th or 12th when he has been Top 10 in something like 7 of his last 10 seasons and has EXCATLY the same situation for the most part as last year (3rd?), and then have E. Manning at 9th who is 1 for 6 with a much higher median ranking.

With that said, I hold Favre to the same standard of regressing to his mean and have him around 7th.

Manning's career has been fascinating on a lot of levels. For example, his 2005 season is the only year where he ranked in the top 5 -- but he really didn't play like a top-5 fantasy quarterback. He just didn't get hurt and he played an easy schedule. When you adjust his performance that year for games played (he played a full 16) and strength of schedule (he had a really easy one), he came in as the 16th best quarterback.Then in '06, he again didn't miss any time, and again had an easy schedule. He ranked 11th, though, overall, which means he really wasn't impressive. Adjusting for SOS and games played, he ranked 31st overall.

He was 14th overall in '07; after adjusting for SOS and adjusted games, he came in 16th, because he didn't have an easy SOS for a change.

Then in '08 he had a really difficult schedule. He ranked 13th overall, and 15th in adjFP/adjG.

So most years Eli has been overrated, IMO, because he usually had a soft schedule and didn't miss time. His "great" season in '05 was a product of that. On the other hand, he's starting to actually improve as a QB, IMO. I didn't adjust his SOS for '09 just yet, but I do think he's on the rise. And Nicks/Smith/Manningham are obviously on the upswing, not to mention Boss/Barden/Moss. So it wouldn't shock me at all to see Eli have a breakout year in 2010. After years of being overvalued, now I think he might be undervalued. But that's mostly because I really like Nicks/Smith/Manningham.

 

[SSOG]

I'm not sure if this year will bring down passing numbers, absent QB injury (last year was certainly a healthy year for quarterbacks, so that inflated passing numbers a bit). But QB passing averages have been on the rise significantly over the years.

...

Attempts spiked in 1995, the year all those receivers in the NFC had absurd yardage totals. But for the most part, attempts have been relatively flat over the last 15-20 years. In 1994 teams averaged more attempts per game than in 2009. I'm not sure why that is (although if I had more time I could test any of the following theories), but maybe teams are also running less often and there are just fewer plays per game, maybe there are more QB runs, maybe fewer incompletions lead to fewer plays with a more constantly running clock, maybe good teams are passing less often but bad teams are passing more often, etc. But at some point, that might change. If you think the NFL is pass happy now, it might become really pass happy soon. Teams are getting really, really good at passing, and pretty soon, I think that means teams are going to pass even more than they do now. So come 2010 or 2011, we might see even more 4,000 yard passers.

I think this is entirely possible, too... but even this doesn't mean squat for Eli. A rising tide lifts all ships. If the league becomes even more pass happy, Eli's numbers might go up... but his peers' numbers will also go up, leaving Eli in the exact same relative position as he was before the increase. If the league becomes less pass-happy, Eli's peers might go down... but Eli's numbers will also go down, leaving Eli in the exact same relative position as he was before the increase. Eli doesn't benefit from the NFL's pass-happy or pass-unhappy ways any more than any of his peers do. This is why I keep discussing Eli's rankings against his peers rather than his raw numbers.

Manning's career has been fascinating on a lot of levels. For example, his 2005 season is the only year where he ranked in the top 5 -- but he really didn't play like a top-5 fantasy quarterback. He just didn't get hurt and he played an easy schedule. When you adjust his performance that year for games played (he played a full 16) and strength of schedule (he had a really easy one), he came in as the 16th best quarterback.

Then in '06, he again didn't miss any time, and again had an easy schedule. He ranked 11th, though, overall, which means he really wasn't impressive. Adjusting for SOS and games played, he ranked 31st overall.

He was 14th overall in '07; after adjusting for SOS and adjusted games, he came in 16th, because he didn't have an easy SOS for a change.

Then in '08 he had a really difficult schedule. He ranked 13th overall, and 15th in adjFP/adjG.

So most years Eli has been overrated, IMO, because he usually had a soft schedule and didn't miss time. His "great" season in '05 was a product of that. On the other hand, he's starting to actually improve as a QB, IMO. I didn't adjust his SOS for '09 just yet, but I do think he's on the rise. And Nicks/Smith/Manningham are obviously on the upswing, not to mention Boss/Barden/Moss. So it wouldn't shock me at all to see Eli have a breakout year in 2010. After years of being overvalued, now I think he might be undervalued. But that's mostly because I really like Nicks/Smith/Manningham.

When a QB is as thoroughly mediocre as Eli is with no signs of improvement (16th, 31st, 16th, 15th), and he then has a season that is a radical departure from his career norms, I'm just inclined to naturally distrust that season. The way I see it, there are three possible explanations for such a season. Either Manning, after 5 straight years of mediocre play with little reason for optimism, took a sudden and dramatic leap in his game... or Manning was playing way over his head... or Manning made a small jump in his game, but was still playing over his head. Of the three explanations, explanation #1 seems the least plausible to me... and explanations 2 and 3 both call for some degree of regression to the mean.Edit: Also, I'm going on record right now predicting that when you run the numbers, Eli Manning comes out 10th or worse in adjusted fantasy points per adjusted game. According to FO, every one of the QBs ahead of Manning faced a neutral or tougher slate of passing defenses except for Aaron Rodgers... and that scoring deficit is far too large for Manning to overcome. Plus, McNabb is waiting in the wings and is sure to leap Manning in that metric. If that's the case, then his "dramatic leap" this year was really just from 15th to 10th.