NFL Parity Visualized

[InChiefsHeaven]

Originally Posted by Ace Gunner

if the lil circle on the far right inches closer to the top of the page, the Chiefs will sweep the donks -- but you must concentrate on that lil circle for it to move

OK....doing my part...

[Archie F. Swin]

which circle is Royals?

[ptlyon]

Looks like a duck

[Bugeater]

LOL @ Buzz TinBrain telling cdcox something went over his head.

[DaFace]

Originally Posted by Bugeater

LOL @ Buzz TinBrain telling cdcox something went over his head.

Yeah, no kidding. The number of data points in the charts is obviously constrained by the number of teams, but the variance in the data points themselves is driven by the number of games played.

[Ace Gunner]

it's fourteen season of data -- why is that not a large enough sample size? also, this is an abstract comparison, but to say the number of games is going to change the final conclusion is nuts, imo.

14 x 16 = 224 games, that's a good sample size. when all teams are included, the size increases to 224 x 16 = 3,584 games which is more than enough sample data imo.

if you reduced the numbers in each sport to 3,584 games, I don't think these charts will change much, really. in fact, it may make football even more varied, by comparison.

[cdcox]

Originally Posted by Ace Gunner

it's fourteen season of data -- why is that not a large enough sample size? also, this is an abstract comparison, but to say the number of games is going to change the final conclusion is nuts, imo.

14 x 16 = 224 games, that's a good sample size. when all teams are included, the size increases to 224 x 16 = 3,584 games which is more than enough sample data imo.

if you reduced the numbers in each sport to 3,584 games, I don't think these charts will change much, really. in fact, it may make football even more varied, by comparison.

The limiting sample size is 16 games per season. A team's record in a given year is a random variable that is some function of the underlying True Strength of the team. People that don't think statistically tend to equate the team record and the True Strength.

Think of it this way: if Tiger Woods hit two golf balls twice in a row under exactly the same conditions, they might land somewhat close to one another but not exactly in the same exact spot. There is some randomness that factors into his golf swing. In an NFL game there are probably millions of these golf-ball sized random variations. So if the Chiefs were able to replay all of their games this season, they would not finish 9-0 every time. There are enough random variations in any given game to allow the outcome to change if it were to be "replayed". If we would represent the Chiefs on the graph they would be 9-0. However if we replayed their season 100 times I suspect that on average we would be about 7-2. This is my guess of our True Strength. So if the season were now over, and we were to play another 9 game season in a year we would not necessarily expect the Chiefs to win 9 games again even if the rosters all remained in tact and the schedules were exactly the same. We'd expect some random variation. If next year the Chiefs went 5-4 with the same exact conditions, it wouldn't be that surprising. To a large degree we just don't know how good the Chiefs really are.

On the other hand if the Chiefs and played 160 games so far this season and had won 155 of them, we would know the Chiefs are really, really good. We would be shocked if a year from now they kept the same roster, every other team kept the same roster and we played the same schedule and went 90-70. Over a 160 game season the record will be a much better indicator of a team's True Strength than a 16 game season.

That is why the variance of MLB will have a smaller variance than the NFL, and why sample size matters.

[chiefzilla1501]

Originally Posted by cdcox

The limiting sample size is 16 games per season. A team's record in a given year is a random variable that is some function of the underlying True Strength of the team. People that don't think statistically tend to equate the team record and the True Strength.

Think of it this way: if Tiger Woods hit two golf balls twice in a row under exactly the same conditions, they might land somewhat close to one another but not exactly in the same exact spot. There is some randomness that factors into his golf swing. In an NFL game there are probably millions of these golf-ball sized random variations. So if the Chiefs were able to replay all of their games this season, they would not finish 9-0 every time. There are enough random variations in any given game to allow the outcome to change if it were to be "replayed". If we would represent the Chiefs on the graph they would be 9-0. However if we replayed their season 100 times I suspect that on average we would be about 7-2. This is my guess of our True Strength. So if the season were now over, and we were to play another 9 game season in a year we would not necessarily expect the Chiefs to win 9 games again even if the rosters all remained in tact and the schedules were exactly the same. We'd expect some random variation. If next year the Chiefs went 5-4 with the same exact conditions, it wouldn't be that surprising. To a large degree we just don't know how good the Chiefs really are.

On the other hand if the Chiefs and played 160 games so far this season and had won 155 of them, we would know the Chiefs are really, really good. We would be shocked if a year from now they kept the same roster, every other team kept the same roster and we played the same schedule and went 90-70. Over a 160 game season the record will be a much better indicator of a team's True Strength than a 16 game season.

That is why the variance of MLB will have a smaller variance than the NFL, and why sample size matters.

Yup. If you flip a coin 4 times, good chance that 75 percent will land heads. If you flip it 40 times, it's very unlikely you'll get anywhere near 100 percent heads.

The other key piece is environment. Because there are only 16 games, luck of scheduling impacts records. One injury can decimate an entire season. Just too many things in the Nfl beyond how good a football team actually is that impacts record.

[Ace Gunner]

Originally Posted by cdcox

The limiting sample size is 16 games per season. A team's record in a given year is a random variable that is some function of the underlying True Strength of the team. People that don't think statistically tend to equate the team record and the True Strength.

Think of it this way: if Tiger Woods hit two golf balls twice in a row under exactly the same conditions, they might land somewhat close to one another but not exactly in the same exact spot. There is some randomness that factors into his golf swing. In an NFL game there are probably millions of these golf-ball sized random variations. So if the Chiefs were able to replay all of their games this season, they would not finish 9-0 every time. There are enough random variations in any given game to allow the outcome to change if it were to be "replayed". If we would represent the Chiefs on the graph they would be 9-0. However if we replayed their season 100 times I suspect that on average we would be about 7-2. This is my guess of our True Strength. So if the season were now over, and we were to play another 9 game season in a year we would not necessarily expect the Chiefs to win 9 games again even if the rosters all remained in tact and the schedules were exactly the same. We'd expect some random variation. If next year the Chiefs went 5-4 with the same exact conditions, it wouldn't be that surprising. To a large degree we just don't know how good the Chiefs really are.

On the other hand if the Chiefs and played 160 games so far this season and had won 155 of them, we would know the Chiefs are really, really good. We would be shocked if a year from now they kept the same roster, every other team kept the same roster and we played the same schedule and went 90-70. Over a 160 game season the record will be a much better indicator of a team's True Strength than a 16 game season.

That is why the variance of MLB will have a smaller variance than the NFL, and why sample size matters.

look, I appreciate the stats work you do here and within your site, but I think the major contributor to football's wide performance gap compared with other sports from season to season is caused primarily by injury and secondarily by team chemistry. Imo that is also what separates football from other sports. certainly, other sports rely heavily on team chemistry, but I don't think it is quite as dynamic as it is within a football team and locker room.

Originally Posted by DaFace

And that's why you're not a statistician.

I don't claim to be one, and I, nor anyone else in this thread disputed the statistical data of the OP.

you are wrong to call the gist of this info "statistics". cross referencing this data is an abstract comparison, not statistics. some folks get confused comparing apples with oranges. they forget apples are apples and oranges are oranges. they forget the fact this kind of comparison is only that -- comparison, complete with a set of opinions that are loosely based in fact, but are not statistics

[chiefzilla1501]

Originally Posted by Ace Gunner

look, I appreciate the stats work you do here and within your site, but I think the major contributor to football's wide performance gap compared with other sports from season to season is caused primarily by injury and secondarily by team chemistry. Imo that is also what separates football from other sports. certainly, other sports rely heavily on team chemistry, but I don't think it is quite as dynamic as it is within a football team and locker room.





I don't claim to be one, and I, nor anyone else in this thread disputed the statistical data of the OP.

you are wrong to call the gist of this info "statistics". cross referencing this data is an abstract comparison, not statistics. some folks get confused comparing apples with oranges. they forget apples are apples and oranges are oranges. they forget the fact this kind of comparison is only that -- comparison, complete with a set of opinions that are loosely based in fact, but are not statistics

I think where the disagreement came in was in referencing sampling. There are a lot of reasons why the study in the op is a complete apples to oranges comparison and I would start with sampling. A series of 16 game seasons just cannot be compared to a 162 game season or an 82 game season. I think the nba vs mlb is pretty apples to apples. The data above tells me nothing about the Nfl. It assumes win loss record defines parity and it just doesn't for the Nfl. At least the mlb and nba are somewhat normalized.

[DaFace]

Originally Posted by Ace Gunner

it's fourteen season of data -- why is that not a large enough sample size? also, this is an abstract comparison, but to say the number of games is going to change the final conclusion is nuts, imo.

14 x 16 = 224 games, that's a good sample size. when all teams are included, the size increases to 224 x 16 = 3,584 games which is more than enough sample data imo.

if you reduced the numbers in each sport to 3,584 games, I don't think these charts will change much, really. in fact, it may make football even more varied, by comparison.

And that's why you're not a statistician.

[ChiefsCountry]

A bad year in baseball is 62-100.
A good year in baseball is 100-62.

A bad year in football is 2-14.
A good year in football is 14-2.

A bad year in baseball winning percentage wise in the NFL is 6-10.
A good year in baseball winning percentage wise in the NFL is 10-6.

That should explain why baseball is in a nice box in the middle and the NFL is spread out.

[Pitt Gorilla]

Those graphs are kinda hot.

[Bearcat]

You ****ers got me curious.... so, this is every team, comparing win % of 2002-2006 to 2007-2011.

The outlier at the bottom is the Rams (haha!) and the closest one to it is the Chiefs ( ...and it would have been worse had I included 2012). The two biggest improvements were the Texans and Saints.