Any statisticians around? Warning: Math!

[Guest]

[quote="Chris Levy":mpkbispw]

There is no statistical reason to consider the signifcance of pWAR 9.0+ or pWAR 10.0+. Unlike WAR 8.0+ and 5.0+, which were not randomly chosen, but instead were statistically identified by the developer of WAR when every player in the history of the game was profiled.

The 52 players thusfar identified to have a pWAR 8.0+ are great players.

Great, but not the greatest, and definetely not in the order suggested. Collect pWAR if you wish, but don't expect acceptance or following of those as the greatest. At minimum, anyone besides yourself that wishes a collection of the greatest will include Johnny Bench in their collection....

I will have Johnny Bench in place of your Robin Roberts.

The baseball Gods are disappointed in you.

Science and math have destroyed all gods.

Science and math?
Please tell me what value that is attributed to the different positions in WAR and explain the science to me. :lol: ::facepalm::[/quote:mpkbispw]

If you PM me your contact information or join me in FCB Chat, I would be happy to explain every aspect of WAR and pWAR to you in great detail.

 

[hofautos]

[quote="Chris Levy":spfl5jdv]

[quote="Chris Levy":spfl5jdv]

There is no statistical reason to consider the signifcance of pWAR 9.0+ or pWAR 10.0+. Unlike WAR 8.0+ and 5.0+, which were not randomly chosen, but instead were statistically identified by the developer of WAR when every player in the history of the game was profiled.

The 52 players thusfar identified to have a pWAR 8.0+ are great players.

Great, but not the greatest, and definetely not in the order suggested. Collect pWAR if you wish, but don't expect acceptance or following of those as the greatest. At minimum, anyone besides yourself that wishes a collection of the greatest will include Johnny Bench in their collection....

I will have Johnny Bench in place of your Robin Roberts.

The baseball Gods are disappointed in you.

Science and math have destroyed all gods.

Science and math?
Please tell me what value that is attributed to the different positions in WAR and explain the science to me. :lol: ::facepalm::[/quote:spfl5jdv]

If you PM me your contact information or join me in FCB Chat, I would be happy to explain every aspect of WAR and pWAR to you in great detail.[/quote:spfl5jdv]

PM sent. But i think you will find that I understand that you are happy to profess that the best 52 players include many pitchers and not one catcher. I understand WAR uses hitting and defense stats to define great players. I understand WAR is great for it's intended purposes. I understand how pWAR can be used to compare positions of the same against positions of the same. Most people will not accept pWAR as a conclusive meausre of one's greatness.
I don't know what further details you can explain that will make me think any different of it. I like pWAR, I just would like to use it in my own methodology.
You are using it for your purposes, and I actually understand that. I struggled a lot with whom I wanted to collect because I didn't want to collect all the HOF'ers, just like you. I want the greatest players. The only problem is, is that my definition of great differs from your definiton of great.

 

[hofautos]

^^^ I actually REALLY look forward to a "gWAR", where I will decide who I will collect. I want something that is "logical" in the way that I define logical, not in the way someone else defines logical. So I am very excited about pWAR....but just for the purposes of defining gWAR.

 

[hofautos]

Also, how do these players stack up?

Ichiro
Miguel Cabrera
Hanley Ramirez
Joe Mauer
Derek Jeter

 

[ronfromfresno]

Chris, since so much has been talked about catchers what are your thoughts on why no catchers are in the top 50 in WAR in general or why the rest fall far behind? Is it simply a matter of not adjusting the numbers, like with the HOF monitor, to give catchers enough credit? Catchers in history have been asked to manage pitchers and, if able, to hit a little bit. A lead off hitter is asked to get on base and not really hit HR. Number 5 hitters are asked to drive in runs, not to walk and so on. Adjusting potential wins based on position is fine but it's as arbitray as the HOF monitor saying "These are the best players, what do they have in common and let's make an equation that ranks others accordingly." To me defense is really sketchy in WAR and the adjustments just don't seem to add up. Like you said the creator is no longer discussing his formula in an open fourm, so we don't know when he has corrected his error that we continue to use in the WAR calculation. But when an entire popualtion in one position is constantly ranked low there is something wrong with the equation, bell curve seems flat.

 

[Guest]

[quote="Chris Levy"89lnqjq]

[quote="Chris Levy"89lnqjq]

There is no statistical reason to consider the signifcance of pWAR 9.0+ or pWAR 10.0+. Unlike WAR 8.0+ and 5.0+, which were not randomly chosen, but instead were statistically identified by the developer of WAR when every player in the history of the game was profiled.

The 52 players thusfar identified to have a pWAR 8.0+ are great players.

Great, but not the greatest, and definetely not in the order suggested. Collect pWAR if you wish, but don't expect acceptance or following of those as the greatest. At minimum, anyone besides yourself that wishes a collection of the greatest will include Johnny Bench in their collection....

I will have Johnny Bench in place of your Robin Roberts.

The baseball Gods are disappointed in you.

Science and math have destroyed all gods.

Science and math?
Please tell me what value that is attributed to the different positions in WAR and explain the science to me. :lol: ::facepalm::

If you PM me your contact information or join me in FCB Chat, I would be happy to explain every aspect of WAR and pWAR to you in great detail.[/quote89lnqjq]

PM sent. But i think you will find that I understand that you are happy to profess that the best 52 players include many pitchers and not one catcher. I understand WAR uses hitting and defense stats to define great players. I understand WAR is great for it's intended purposes. I understand how pWAR can be used to compare positions of the same against positions of the same. Most people will not accept pWAR as a conclusive meausre of one's greatness.
I don't know what further details you can explain that will make me think any different of it. I like pWAR, I just would like to use it in my own methodology.
You are using it for your purposes, and I actually understand that. I struggled a lot with whom I wanted to collect because I didn't want to collect all the HOF'ers, just like you. I want the greatest players. The only problem is, is that my definition of great differs from your definiton of great.[/quote89lnqjq]

Neither you, nor I, are capable of defining 'great' in an arbitrary capacity like you are attempting.

When WAR was developed every single season in the histoy of the game was plotted and the results showed that MVP Quality was best defined as 8.0+, All-Star Quality as 5.0+, etc. as I've outlined countless times now.

Someone did not select 8.0+ at random because it "sounded good." It was statistical proven and plotted using thousands of statistical elements.

The community has accepted this as a given.

Therefore, the question has been posed? How many MVP Quality seasons must a player have to be considered 'great'.

I selected five MVP Quality Seasons, which translated as pWAR 8.0+.

If I told you "a player won 5 MVP awards." You'd stop and say "Wow. That's geat!" And that's what you need to do. You need to interpret the data in that capacity.

pWAR 8.0+ = at least 5 MVP awards.

Some people believe a player must have 10 good seasons to be considered great. That would look like = 10-yr-avg WAR 5.0+.

A player can be statistically defined as a MVP, All-Star, Starter, Reserve, or Replacement using WAR.

So think of it in those terms.

How many MVP years must a player have for you to consider them great? How many years as an All-Star?

Once you've answered those questions a formula can be constructed scientifically to define the results. HOWEVER, you must not pick your results first. You must define the criteria, and then see who ultimately fits into it.

 

[hofautos]

Chris, since so much has been talked about catchers what are your thoughts on why no catchers are in the top 50 in WAR in general or why the rest fall far behind? Is it simply a matter of not adjusting the numbers, like with the HOF monitor, to give catchers enough credit? Catchers in history have been asked to manage pitchers and, if able, to hit a little bit. A lead off hitter is asked to get on base and not really hit HR. Number 5 hitters are asked to drive in runs, not to walk and so on. Adjusting potential wins based on position is fine but it's as arbitray as the HOF monitor saying "These are the best players, what do they have in common and let's make an equation that ranks others accordingly." To me defense is really sketchy in WAR and the adjustments just don't seem to add up. Like you said the creator is no longer discussing his formula in an open fourm, so we don't know when he has corrected his error that we continue to use in the WAR calculation. But when an entire popualtion in one position is constantly ranked low there is something wrong with the equation, bell curve seems flat.

He will argue catchers don't have offensive numbers to consider them great....my response is, neither do pitchers, yet there are plenty of pitchers in pWAR.
but i will let him try and rationalize it in his own manner to you

 

[Guest]

Chris, since so much has been talked about catchers what are your thoughts on why no catchers are in the top 50 in WAR in general or why the rest fall far behind? Is it simply a matter of not adjusting the numbers, like with the HOF monitor, to give catchers enough credit? Catchers in history have been asked to manage pitchers and, if able, to hit a little bit. A lead off hitter is asked to get on base and not really hit HR. Number 5 hitters are asked to drive in runs, not to walk and so on. Adjusting potential wins based on position is fine but it's as arbitray as the HOF monitor saying "These are the best players, what do they have in common and let's make an equation that ranks others accordingly." To me defense is really sketchy in WAR and the adjustments just don't seem to add up. Like you said the creator is no longer discussing his formula in an open fourm, so we don't know when he has corrected his error that we continue to use in the WAR calculation. But when an entire popualtion in one position is constantly ranked low there is something wrong with the equation, bell curve seems flat.

There is a component to WAR titled Rpos (Runs from Positional Scarcity). A bonus is applied to certain positions, including Catcher. During Johnny Bench's career 98 artifical runs were added to adjust his RAR based on his position.

That is a heck of a lot of artificial runs to be added, just because he was a catcher. However, even with this bonus he still did not reach the levels needed.

Johnny Bench was the best at his position, but it is a historically weak position.

I really think this is a case of people saying "Johnny Bench was great" and most people going along with it without taking the time to do the actual research themselves.

Before I did this test, I thought Yogi Berra, Johnny Bench, and others would meet the criteria. They did not.

I was SHOCKED to see Gary Carter place highter than Yogi Berra on this list (but he does so not just at 5 years, but for 10 years as well!) I had to re-enter the data twice here to make sure it was accurate, because it did not meet expectations. But when I actually took the time to look at Carter's numbers and Berra's numbers in depth, I found that Carter was the better player, and the stories I had heard about Berra skewed my opinion away from the stats.

I do not believe WAR is broken in regards to catchers. I believe our previously held notions and opinions are wrong and we must re-educate ourselves and re-evaluate players based on the new tools we have available.

 

[hofautos]

[quote="Chris Levy":2ofs4f4y]

[quote="Chris Levy":2ofs4f4y]

[quote="Chris Levy":2ofs4f4y]

There is no statistical reason to consider the signifcance of pWAR 9.0+ or pWAR 10.0+. Unlike WAR 8.0+ and 5.0+, which were not randomly chosen, but instead were statistically identified by the developer of WAR when every player in the history of the game was profiled.

The 52 players thusfar identified to have a pWAR 8.0+ are great players.

Great, but not the greatest, and definetely not in the order suggested. Collect pWAR if you wish, but don't expect acceptance or following of those as the greatest. At minimum, anyone besides yourself that wishes a collection of the greatest will include Johnny Bench in their collection....

I will have Johnny Bench in place of your Robin Roberts.

The baseball Gods are disappointed in you.

Science and math have destroyed all gods.

Science and math?
Please tell me what value that is attributed to the different positions in WAR and explain the science to me. :lol: ::facepalm::

If you PM me your contact information or join me in FCB Chat, I would be happy to explain every aspect of WAR and pWAR to you in great detail.[/quote:2ofs4f4y]

PM sent. But i think you will find that I understand that you are happy to profess that the best 52 players include many pitchers and not one catcher. I understand WAR uses hitting and defense stats to define great players. I understand WAR is great for it's intended purposes. I understand how pWAR can be used to compare positions of the same against positions of the same. Most people will not accept pWAR as a conclusive meausre of one's greatness.
I don't know what further details you can explain that will make me think any different of it. I like pWAR, I just would like to use it in my own methodology.
You are using it for your purposes, and I actually understand that. I struggled a lot with whom I wanted to collect because I didn't want to collect all the HOF'ers, just like you. I want the greatest players. The only problem is, is that my definition of great differs from your definiton of great.[/quote:2ofs4f4y]

Neither you, nor I, are capable of defining 'great' in an arbitrary capacity like you are attempting.[/quote:2ofs4f4y]

Believe me, I am fully capable of assigning an arbitrary number to put catchers on the list. I am sure my IQ surpasses the author of WAR, and I assure you there is more fudging than science. You can think differently if you so choose, but I assure you, some day you will realize that arbitrary numbers are used for subjective objectives. There is no scientific manner which can be used to suggest position x is worth value y.

 

[Guest]

Chris, since so much has been talked about catchers what are your thoughts on why no catchers are in the top 50 in WAR in general or why the rest fall far behind? Is it simply a matter of not adjusting the numbers, like with the HOF monitor, to give catchers enough credit? Catchers in history have been asked to manage pitchers and, if able, to hit a little bit. A lead off hitter is asked to get on base and not really hit HR. Number 5 hitters are asked to drive in runs, not to walk and so on. Adjusting potential wins based on position is fine but it's as arbitray as the HOF monitor saying "These are the best players, what do they have in common and let's make an equation that ranks others accordingly." To me defense is really sketchy in WAR and the adjustments just don't seem to add up. Like you said the creator is no longer discussing his formula in an open fourm, so we don't know when he has corrected his error that we continue to use in the WAR calculation. But when an entire popualtion in one position is constantly ranked low there is something wrong with the equation, bell curve seems flat.

He will argue catchers don't have offensive numbers to consider them great....my response is, neither do pitchers, yet there are plenty of pitchers in pWAR.
but i will let him try and rationalize it in his own manner to you

Johnny Bench neve batted over .300 in a full season. He only scored over 100 runs once. He was nowhere near the level of the players on that list.

And if you actually sit there and look at all their statistics, you'll see that.

As you have still yet to provide any statistical evidence whatsoever in defense of Bench or in opposition of anyone else.

 

[hofautos]

Chris, since so much has been talked about catchers what are your thoughts on why no catchers are in the top 50 in WAR in general or why the rest fall far behind? Is it simply a matter of not adjusting the numbers, like with the HOF monitor, to give catchers enough credit? Catchers in history have been asked to manage pitchers and, if able, to hit a little bit. A lead off hitter is asked to get on base and not really hit HR. Number 5 hitters are asked to drive in runs, not to walk and so on. Adjusting potential wins based on position is fine but it's as arbitray as the HOF monitor saying "These are the best players, what do they have in common and let's make an equation that ranks others accordingly." To me defense is really sketchy in WAR and the adjustments just don't seem to add up. Like you said the creator is no longer discussing his formula in an open fourm, so we don't know when he has corrected his error that we continue to use in the WAR calculation. But when an entire popualtion in one position is constantly ranked low there is something wrong with the equation, bell curve seems flat.

He will argue catchers don't have offensive numbers to consider them great....my response is, neither do pitchers, yet there are plenty of pitchers in pWAR.
but i will let him try and rationalize it in his own manner to you

Johnny Bench neve batted over .300 in a full season. He only scored over 100 runs once. He was nowhere near the level of the players on that list.

And if you actually sit there and look at all their statistics, you'll see that.

As you have still yet to provide any statistical evidence whatsoever in defense of Bench or in opposition of anyone else.

The same can be said for pitchers, but they made the list.
And please don't think you are arguing with me....like i shared the other article with you, and you can google 100 top 50 lists, and you will always find Bench.

 

[Guest]

Chris, since so much has been talked about catchers what are your thoughts on why no catchers are in the top 50 in WAR in general or why the rest fall far behind? Is it simply a matter of not adjusting the numbers, like with the HOF monitor, to give catchers enough credit? Catchers in history have been asked to manage pitchers and, if able, to hit a little bit. A lead off hitter is asked to get on base and not really hit HR. Number 5 hitters are asked to drive in runs, not to walk and so on. Adjusting potential wins based on position is fine but it's as arbitray as the HOF monitor saying "These are the best players, what do they have in common and let's make an equation that ranks others accordingly." To me defense is really sketchy in WAR and the adjustments just don't seem to add up. Like you said the creator is no longer discussing his formula in an open fourm, so we don't know when he has corrected his error that we continue to use in the WAR calculation. But when an entire popualtion in one position is constantly ranked low there is something wrong with the equation, bell curve seems flat.

He will argue catchers don't have offensive numbers to consider them great....my response is, neither do pitchers, yet there are plenty of pitchers in pWAR.
but i will let him try and rationalize it in his own manner to you

Johnny Bench neve batted over .300 in a full season. He only scored over 100 runs once. He was nowhere near the level of the players on that list.

And if you actually sit there and look at all their statistics, you'll see that.

As you have still yet to provide any statistical evidence whatsoever in defense of Bench or in opposition of anyone else.

The same can be said for pitchers, but they made the list.

How do you win a game? By scoring runs on offense, and not allowing runs on defense.

Who has the most say in terms of not allowing runs? The pitcher.

The argument can be made that the pitcher has the greatest impact on the outcome of the game, so obviously there will be a number of pitchers with a high WAR.

 

[hofautos]

[quote="Chris Levy":3fx0rilu]

Chris, since so much has been talked about catchers what are your thoughts on why no catchers are in the top 50 in WAR in general or why the rest fall far behind? Is it simply a matter of not adjusting the numbers, like with the HOF monitor, to give catchers enough credit? Catchers in history have been asked to manage pitchers and, if able, to hit a little bit. A lead off hitter is asked to get on base and not really hit HR. Number 5 hitters are asked to drive in runs, not to walk and so on. Adjusting potential wins based on position is fine but it's as arbitray as the HOF monitor saying "These are the best players, what do they have in common and let's make an equation that ranks others accordingly." To me defense is really sketchy in WAR and the adjustments just don't seem to add up. Like you said the creator is no longer discussing his formula in an open fourm, so we don't know when he has corrected his error that we continue to use in the WAR calculation. But when an entire popualtion in one position is constantly ranked low there is something wrong with the equation, bell curve seems flat.

He will argue catchers don't have offensive numbers to consider them great....my response is, neither do pitchers, yet there are plenty of pitchers in pWAR.
but i will let him try and rationalize it in his own manner to you

Johnny Bench neve batted over .300 in a full season. He only scored over 100 runs once. He was nowhere near the level of the players on that list.

And if you actually sit there and look at all their statistics, you'll see that.

As you have still yet to provide any statistical evidence whatsoever in defense of Bench or in opposition of anyone else.

The same can be said for pitchers, but they made the list.

How do you win a game? By scoring runs on offense, and not allowing runs on defense.

Who has the most say in terms of not allowing runs? The pitcher.

The argument can be made that the pitcher has the greatest impact on the outcome of the game, so obviously there will be a number of pitchers with a high WAR.[/quote:3fx0rilu]

Pitchers pitch one in 5 games, otherwise I would consider them more important than catchers.
Catchers do make a difference, like it or not...it is just a lot more difficult to gauge.

 

[elmalo]

[quote="Chris Levy":47tht3ue]

Chris, since so much has been talked about catchers what are your thoughts on why no catchers are in the top 50 in WAR in general or why the rest fall far behind? Is it simply a matter of not adjusting the numbers, like with the HOF monitor, to give catchers enough credit? Catchers in history have been asked to manage pitchers and, if able, to hit a little bit. A lead off hitter is asked to get on base and not really hit HR. Number 5 hitters are asked to drive in runs, not to walk and so on. Adjusting potential wins based on position is fine but it's as arbitray as the HOF monitor saying "These are the best players, what do they have in common and let's make an equation that ranks others accordingly." To me defense is really sketchy in WAR and the adjustments just don't seem to add up. Like you said the creator is no longer discussing his formula in an open fourm, so we don't know when he has corrected his error that we continue to use in the WAR calculation. But when an entire popualtion in one position is constantly ranked low there is something wrong with the equation, bell curve seems flat.

He will argue catchers don't have offensive numbers to consider them great....my response is, neither do pitchers, yet there are plenty of pitchers in pWAR.
but i will let him try and rationalize it in his own manner to you

Johnny Bench neve batted over .300 in a full season. He only scored over 100 runs once. He was nowhere near the level of the players on that list.

And if you actually sit there and look at all their statistics, you'll see that.

As you have still yet to provide any statistical evidence whatsoever in defense of Bench or in opposition of anyone else.

The same can be said for pitchers, but they made the list.

How do you win a game? By scoring runs on offense, and not allowing runs on defense.

Who has the most say in terms of not allowing runs? The pitcher.

The argument can be made that the pitcher has the greatest impact on the outcome of the game, so obviously there will be a number of pitchers with a high WAR.

Pitchers pitch one in 5 games, otherwise I would consider them more important than catchers.
Catchers do make a difference, like it or not...it is just a lot more difficult to gauge.[/quote:47tht3ue]
Actually for the older pitchers it was 1 in 4. Now it is 1 in 5.

 

[hofautos]

CHEVY>> Historically catchers have just been a bunch of fat guys that squat there and throw the ball to the pitcher.
That's what a catcher is.

 

[hofautos]

..

 

[pigskincardboard]

Why do you guys keep humouring him?

There are plenty of beautifully written articles out there that are based on actual math, not 7th grade spreadsheet math. They take data, chart data, group data, smooth data, regress data, fit data and interpret data.

The premise of this crap is that the only thing that matters in a player is his best five seasons. Absolutely nothing else has any weight, at all. It doesn't even matter if you believe in WAR as an accurate measurement, you just have to believe in sanity.

He's not even graphing this stuff and getting a corr. for his data.

This is akin to saying "We will judge the rainiest month of the year by the month that has the three rainiest days"

If January has 10cm, 15cm and 8cm and no more rain; it is greater than December's 15 straight days of 8cm. January is the rainest month of the year!

STOP HUMOURING HIM!

Order him a statistics text book or something if you want to humour him.

 

[hofautos]

Why do you guys keep humouring him?

There are plenty of beautifully written articles out there that are based on actual math, not 7th grade spreadsheet math. They take data, chart data, group data, smooth data, regress data, fit data and interpret data.

The premise of this crap is that the only thing that matters in a player is his best five seasons. Absolutely nothing else has any weight, at all. It doesn't even matter if you believe in WAR as an accurate measurement, you just have to believe in sanity.

He's not even graphing this stuff and getting a corr. for his data.

This is akin to saying "We will judge the rainiest month of the year by the month that has the three rainiest days"

If January has 10cm, 15cm and 8cm and no more rain; it is greater than December's 15 straight days of 8cm. January is the rainest month of the year!

STOP HUMOURING HIM!

Order him a statistics text book or something if you want to humour him.

You've been thanked!

 

[Guest]

Why do you guys keep humouring him?

There are plenty of beautifully written articles out there that are based on actual math, not 7th grade spreadsheet math. They take data, chart data, group data, smooth data, regress data, fit data and interpret data.

The premise of this crap is that the only thing that matters in a player is his best five seasons. Absolutely nothing else has any weight, at all. It doesn't even matter if you believe in WAR as an accurate measurement, you just have to believe in sanity.

He's not even graphing this stuff and getting a corr. for his data.

This is akin to saying "We will judge the rainiest month of the year by the month that has the three rainiest days"

If January has 10cm, 15cm and 8cm and no more rain; it is greater than December's 15 straight days of 8cm. January is the rainest month of the year!

STOP HUMOURING HIM!

Order him a statistics text book or something if you want to humour him.

If the purpose is to measure how a player's five best seasons compare to another player's five best seasons, then why would I include any data outside of the five year range.

I plotted the data of all the members of the Hall of Fame, stating as low as 1 year (their best single season WAR) and as high as 15 years (an average of their top 15 statistical seasons).

Once I had this data it showed that 5 years was the largest sample size that would produce at least 50 players with an average WAR of 8.0+.

The reason 8.0+ was selected as the benchmark, was because the complete WAR data has showed that an MVP Quality season was defined by this benchmark.

To confirm that there were no outliers (that is to say one unusually high single season WAR inflating the average) I checked all 52 players in the result at 10 years. It was found that each player in the result maintained the WAR 5.0+ threshold at 10 years. Again, this is significant because the complete WAR data has showed that an All-Star Quality season is defined by this benchmark.

Knowing that the data did not have any outliers and was consistent up to 10 years, I felt confident to procede.

I stand by my data and the way it was constructed.

I feel that my list is an accurate ranking of the players by the average of their five best seasons.

The math and statistics behind this is solid.

The question is, do you care how players rank using just 5 years of data?

I do. You don't. Some do. Others don't.

It's not designed to be the be-all, end-all.

It is a list of 52 players (post-1901) who had the ability over a 5 year span to win 5 MVP awards based on WAR. That's the only factor considered. The only factor that was meant to be considered.

If 5x MVP awards and 10x All-Star appearances means something to you, then these are the players who could have done such a feat.

Interpret it as you will.

 

[hofautos]

If 5x MVP awards and 10x All-Star appearances means something to you, then these are the players who could have done such a feat.

Interpret it as you will.

Accurately interpreted as the 5 best seasons of WAR, nothing more. It is valuable but not in of itself.
Modify it with career numbers and it could potentially have better usage, especially if WAR's deficiency in comparing catchers to other positions is updated.