HFBoards

Go Back   HFBoards > NHL Eastern Conference > Atlantic Division > Buffalo Sabres
Mobile Hockey's Future Become a Sponsor Site Rules Support Forum vBookie Page 2
Notices

SBD Interview with Pegula

Reply
 
Thread Tools
Old
06-07-2012, 08:09 PM
  #51
joshjull
Moderator
 
joshjull's Avatar
 
Join Date: Aug 2005
Location: Hamburg,NY
Country: United States
Posts: 34,402
vCash: 500
Quote:
Originally Posted by Awwufelloff View Post
It will show a scatter plot since if you look at the data its all over the place. St Louis has more man games lost yet almost won Presidents trophy. They have ZERO star players. For those who say Pitts + Philly can win despite injuries because they have a plethora of star players.
A couple of things

1. You still keep missing the point that its who is out and when that matters most not total man games lost.

2. St.Louis has no stars? Pietroangelo says hello. He's one of the best dmen in the game. Its also no coincidence that the Kings went after him. He gets injured (head injury believed to be a concussion) and that made things pretty tough for the Blues. They also didnt have Halak (lower body injury) who was part of their 1-2 punch in net. I would argue those injuries mattered but I doubt you would agree.

joshjull is online now   Reply With Quote
Old
06-07-2012, 08:42 PM
  #52
Dixon Ward
Fire SOMEONE
 
Dixon Ward's Avatar
 
Join Date: Oct 2006
Location: District of Columbia
Country: United States
Posts: 2,030
vCash: 500
Quote:
Originally Posted by LoveDaSwords View Post
0.0193 is basically saying "no correlation"...actually weaker than I thought, I was expecting it to be in the .3-.4 range

Nice try though.
actually, excel 2010 told me that the r^2 for my scatter plot was .05...not that it makes any difference.

Dixon Ward is offline   Reply With Quote
Old
06-07-2012, 08:44 PM
  #53
McTankel
HFBoards Sponsor
 
McTankel's Avatar
 
Join Date: Jul 2011
Location: Hamburg, NY
Country: United States
Posts: 6,378
vCash: 500
Quote:
Originally Posted by joshjull View Post
A couple of things

1. You still keep missing the point that its who is out and when that matters most not total man games lost.

2. St.Louis has no stars? Pietroangelo says hello. He's one of the best dmen in the game. Its also no coincidence that the Kings went after him. He gets injured (head injury believed to be a concussion) and that made things pretty tough for the Blues. They also didnt have Halak (lower body injury) who was part of their 1-2 punch in net. I would argue those injuries mattered but I doubt you would agree.
As I already stated, injuries do matter. But when the GM/Coach/Owner are using them as an excuse to why the team does bad is what I have a problem with. Its a lack of good management/coaching skills. If you were the owner of a public company, trying to keep the stock price at a high value to please shareholders...Would you for instance, have a press conference giving excuses to why the stock is falling horribly? Or would you talk about what needs to change in order to keep the company successful and moving in the right direction?

McTankel is online now   Reply With Quote
Old
06-07-2012, 08:45 PM
  #54
McTankel
HFBoards Sponsor
 
McTankel's Avatar
 
Join Date: Jul 2011
Location: Hamburg, NY
Country: United States
Posts: 6,378
vCash: 500
Quote:
Originally Posted by Dixon Ward View Post
actually, excel 2010 told me that the r^2 for my scatter plot was .05...not that it makes any difference.
My data is correct. I just finished Advanced Statistics in college last year. Only reason why I remember it so easily.

McTankel is online now   Reply With Quote
Old
06-07-2012, 08:47 PM
  #55
Der Jaeger
Registered User
 
Der Jaeger's Avatar
 
Join Date: Feb 2009
Location: Northern Virginia
Country: United States
Posts: 2,036
vCash: 500
Quote:
Originally Posted by LoveDaSwords View Post
0.0193 is basically saying "no correlation"...actually weaker than I thought, I was expecting it to be in the .3-.4 range

Nice try though.
The r2 prediction says there is no correlation.

Is the argument sound? Do you really believe that injuries have no correlation to games won / lost? Or is the the overall argument weak: two sets of data in a linear model, trying to predict a non-linear system.

Der Jaeger is online now   Reply With Quote
Old
06-07-2012, 08:48 PM
  #56
Der Jaeger
Registered User
 
Der Jaeger's Avatar
 
Join Date: Feb 2009
Location: Northern Virginia
Country: United States
Posts: 2,036
vCash: 500
Quote:
Originally Posted by Awwufelloff View Post
My data is correct. I just finished Advanced Statistics in college last year. Only reason why I remember it so easily.
Have you taken systems theory yet?

Der Jaeger is online now   Reply With Quote
Old
06-07-2012, 08:51 PM
  #57
New Sabres Captain
ForFriendshipDikembe
 
New Sabres Captain's Avatar
 
Join Date: Oct 2006
Country: United States
Posts: 39,515
vCash: 500
Quote:
Originally Posted by Der Jaeger View Post
The r2 prediction says there is no correlation.

Is the argument sound? Do you really believe that injuries have no correlation to games won / lost? Or is the the overall argument weak: two sets of data in a linear model, trying to predict a non-linear system.
You're right, one really should build a regression model that adjusts for confounding variables and then check for a significant p value.

New Sabres Captain is offline   Reply With Quote
Old
06-07-2012, 09:01 PM
  #58
tsujimoto74
Registered User
 
tsujimoto74's Avatar
 
Join Date: May 2012
Location: Virginia
Country: United States
Posts: 9,700
vCash: 500
Quote:
Originally Posted by Awwufelloff View Post
As I already stated, injuries do matter. But when the GM/Coach/Owner are using them as an excuse to why the team does bad is what I have a problem with. Its a lack of good management/coaching skills. If you were the owner of a public company, trying to keep the stock price at a high value to please shareholders...Would you for instance, have a press conference giving excuses to why the stock is falling horribly? Or would you talk about what needs to change in order to keep the company successful and moving in the right direction?
You're arguing semantics now. How is acknowledging that injuries matter -- as you claim you're doing -- any different from what Pegula said? No one is saying they're an excuse..They're not an excuse, they're a fact of the game. You lose players that matter a lot to the team, you lose a lot of players at the same time, that's gonna affect the team. Even if the players substituted were of the same caliber of the players missing (which they weren't in most cases) you still mess with on-ice chemistry and team confidence.

tsujimoto74 is offline   Reply With Quote
Old
06-07-2012, 09:01 PM
  #59
Dixon Ward
Fire SOMEONE
 
Dixon Ward's Avatar
 
Join Date: Oct 2006
Location: District of Columbia
Country: United States
Posts: 2,030
vCash: 500
Quote:
Originally Posted by Awwufelloff View Post
My data is correct. I just finished Advanced Statistics in college last year. Only reason why I remember it so easily.
our data is exactly the same. you plotted points as the independent variable whereas i plotted man-games lost as the independent variable, which accounts for the different (yet equally meaningless) slopes. we're asking slightly different questions.

Quote:
Originally Posted by LoveDaSwords View Post
You're right, one really should build a regression model that adjusts for confounding variables and then check for a significant p value.
i would also think that analyzing a single season is completely inadequate. sounds like a good thesis. anyone?


Last edited by Dixon Ward: 06-07-2012 at 09:15 PM.
Dixon Ward is offline   Reply With Quote
Old
06-07-2012, 09:04 PM
  #60
BuiltTagonTough
Stand still laddy!
 
BuiltTagonTough's Avatar
 
Join Date: Jul 2009
Location: Buffalo
Country: United States
Posts: 10,536
vCash: 500
Quote:
Originally Posted by LoveDaSwords View Post
You're right, one really should build a regression model that adjusts for confounding variables and then check for a significant p value.
I hate all of you.

I dont think it was an excuse so much as telling it like it is. Injuries happen and it hurts the team, we'll work toward being better next year.

What did he say that wasnt true?

BuiltTagonTough is offline   Reply With Quote
Old
06-07-2012, 09:04 PM
  #61
WhoIsJimBob
Circle the Bandwagon
 
WhoIsJimBob's Avatar
 
Join Date: Feb 2002
Location: Rochester, NY
Country: United States
Posts: 16,653
vCash: 500
Quote:
Originally Posted by Awwufelloff View Post
As I already stated, injuries do matter. But when the GM/Coach/Owner are using them as an excuse to why the team does bad is what I have a problem with. Its a lack of good management/coaching skills. If you were the owner of a public company, trying to keep the stock price at a high value to please shareholders...Would you for instance, have a press conference giving excuses to why the stock is falling horribly? Or would you talk about what needs to change in order to keep the company successful and moving in the right direction?
I think that both items are true in this case.

I absolutely believe that injuries were one of the top 5 reasons that the team missed the playoffs and if even just Myers and Ehrhoff were able to play 82 games each that they would have made the playoffs.

I also think that Regier and Ruff should be replaced as they have been given ample time and not done enough to remain.

I don't see why some people need it to be one or the other.

Another factor that I don't blame on Regier or Ruff is Miller not earning his paycheck until too late in the season. I blame that all on Miller himself.

WhoIsJimBob is offline   Reply With Quote
Old
06-07-2012, 10:27 PM
  #62
Zip15
Registered User
 
Zip15's Avatar
 
Join Date: Jun 2009
Posts: 17,889
vCash: 396
Quote:
Originally Posted by Jim Bob View Post
I think that both items are true in this case.

I absolutely believe that injuries were one of the top 5 reasons that the team missed the playoffs and if even just Myers and Ehrhoff were able to play 82 games each that they would have made the playoffs.

I also think that Regier and Ruff should be replaced as they have been given ample time and not done enough to remain.

I don't see why some people need it to be one or the other.

Another factor that I don't blame on Regier or Ruff is Miller not earning his paycheck until too late in the season. I blame that all on Miller himself.
You don't blame it on two brain injuries--i.e., concussions--in one calendar year? Walk it off, Miller. Rub some dirt on it.

Zip15 is online now   Reply With Quote
Old
06-07-2012, 10:34 PM
  #63
Der Jaeger
Registered User
 
Der Jaeger's Avatar
 
Join Date: Feb 2009
Location: Northern Virginia
Country: United States
Posts: 2,036
vCash: 500
Quote:
Originally Posted by LoveDaSwords View Post
You're right, one really should build a regression model that adjusts for confounding variables and then check for a significant p value.
I was wrong earlier when I said that there was correlation - and you're right, there might not be statistical correlation (unless we check for extraneous values).

Better point: correlation isn't causation. Regression models can indicate correlation. There may not be a correlation between man-games-lost and wins, but is there a causal relationship between man-games-lost and wins?

This difference is the mistake that the quants made on Wall Street. The PhD's Wall Street hired applied models in an attempt to predict an interactively complex system. The ones that AIG hired told them that there was a 99.85 percent chance of never having to pay out on credit-default swaps. Didn't work out so well. Did the .15 just happen, or were the models wrong?

Taking two data points (man-games-lost and wins/loses), using a regression model, and determining that because there's no correlation, they don't effect each other is like using a set of pliers to dissect a giraffe. The pliers work just fine. Wrong tool.

There are so many variables that aren't considered in that model. I'm not great at math, but I can tell where it applies, and where it doesn't apply well.

Der Jaeger is online now   Reply With Quote
Old
06-07-2012, 10:50 PM
  #64
Der Jaeger
Registered User
 
Der Jaeger's Avatar
 
Join Date: Feb 2009
Location: Northern Virginia
Country: United States
Posts: 2,036
vCash: 500
Quote:
Originally Posted by LoveDaSwords View Post
You're right, one really should build a regression model that adjusts for confounding variables and then check for a significant p value.
BTW, you almost certainly wrote this sarcastically, but it made me break out some old books I haven't looked at in a while. Nice.

Der Jaeger is online now   Reply With Quote
Old
06-07-2012, 11:54 PM
  #65
jamers
McTankel Mechanic
 
jamers's Avatar
 
Join Date: Sep 2011
Posts: 2,424
vCash: 500
Don't disagree with anything he said. Was interesting to read his comments at finding a balance in ownership. I'm sure if I were in his position it'd probably be 110% gung-ho all of the time, which isn't necessarily a good thing.

Quote:
Originally Posted by Zip15 View Post
You don't blame it on two brain injuries--i.e., concussions--in one calendar year? Walk it off, Miller. Rub some dirt on it.
Miller is paid to be a star goaltender, concussions or no.

jamers is offline   Reply With Quote
Old
06-08-2012, 07:48 AM
  #66
HiddenInLight
Registered User
 
HiddenInLight's Avatar
 
Join Date: Sep 2011
Posts: 3,014
vCash: 500
Quote:
Originally Posted by Zip15 View Post
You don't blame it on two brain injuries--i.e., concussions--in one calendar year? Walk it off, Miller. Rub some dirt on it.
Reminded me of King of the Hill "Take a salt tablet"



Honestly, I don't disagree with anything pegula said in this interview. =/ Not sure why people have to blow up about this interview, didn't say much that hasn't been said already. Also Man Games lost to points/wins is a bad comparison to make because man games lost doesn't differentiate from guys like Stuert (who was on our IR for a whole) or McCormick, and guys like Myers. It also doesn't include players that are playing hurt during the season, such as Regehr, Vanek, Leopold, Ennis, and Ehrhoff all did throughout the season.

HiddenInLight is offline   Reply With Quote
Old
06-08-2012, 12:24 PM
  #67
brian_griffin
Measured Intangibles
 
brian_griffin's Avatar
 
Join Date: May 2007
Location: Z4QQQ batman symbol
Country: Vatican City State
Posts: 6,725
vCash: 500
Quote:
Originally Posted by Der Jaeger View Post
Reality: you're at ten years of waiting. Pegula's just a little over one.

Good comparison: Bills fans are sick of waiting too. Buddy Nix never cared about making moves in his first two years in a "make or break" fashion. He just rebuilt the team. This season will tell, but it's sorta paying off.

Pegula's going to do a lot of the same, regardless of his 3 year comment.
Not really a good comparison. Bills of the past 10-12 years are / were / always have been MUCH FARTHER away from competing for the playoffs than the Sabres. Objective data should support that. I'd suggest yearly Bills win pct deficit relative to avg. yearly playoff team win % as compared to Sabres pts. per season vs. avg. yearly playoff team pts per season.

Quote:
Originally Posted by joshjull View Post
They also traded for Jeff Carter and promoted King and Nolan from their farm team. As Sutter himself said, it FINALLY allowed him to play the system he wanted to play the way he wanted to play it. It gave him size throughout the lineup. EVERY single line had at least one huge player if not two. Lets not pretend he waived a magic wand and turned the struggling Kings roster he had when he first took over into the team we see now. That group was playing at the same level prior to Sutter taking over. It wasn't until those players took over that things started clicking for Sutter and the Kings.

Sutter also never dealt with any major injuries to his top players. One guy was injured (Gagne) and he was replaced at the deadline with Carter. So comapring our situations is ridiculous. The Kings were flat out underachieving. They had all their key players in the lineup all year long. So injuries were a complete non-factor in their struggles before Sutter was brought on.

Sutter also has pieces to work with that we don't, particularly up front. Namely having Kopitar and Richards as his top two centers. We have nothing remotely equivilant. Not to mention the huge roster he has that is perfectly suited to play the way he likes to play. That would be straight ahead, aggressive and simple forechecking. It relies on size and strength to overwhelm the opposing defense. Not something our forward core would be able to do.

It drives me nut we posters make such simplistic statements as the Kings changed their coach and look where they are now. The situations aren't remotely comparable. We had a ton on injuries they did not. They had a great set of centers we did not. Its fine if you want to fire Lindy but its ridiculous to compare our situation to LA's and think firing Ruff will yield the same results. No coach wins without having the players. Thats regardless if he doesn't have them due to injuries or they just aren't on the roster.
Off-topic of the statistical discussions, but that style has been oh-so-much-fun to watch!!

Quote:
Originally Posted by Awwufelloff View Post
As I already stated, injuries do matter. But when the GM/Coach/Owner are using them as an excuse to why the team does bad is what I have a problem with. Its a lack of good management/coaching skills. If you were the owner of a public company, trying to keep the stock price at a high value to please shareholders...Would you for instance, have a press conference giving excuses to why the stock is falling horribly? Or would you talk about what needs to change in order to keep the company successful and moving in the right direction?
OT, but if I'm the owner of a public company, I don't fret about the stock price, because I can't control people and institution behavior to buy/sell. I focus on earnings and cash flow per share, cash reserves and funding sources / strategies for my business model, and my long-term growth strategies, beyond the time horizon of my tenure. The extent the public chooses to value that or not, I can influence very little. I'm being truthful here - that's my view.

Quote:
Originally Posted by joshjull View Post
Ruff's skill as a coach is a seperate discussion.

Injuries without question impacted our ability to make the playoffs last season. We need to add more talent to overcome injuries to the defense. In particular we need to add up front.
Most important thing to do - adding the right talent up front will help the GF, but equally important, help the GA when the defense is depleted.

Quote:
Originally Posted by Awwufelloff View Post
Anything can happen once your in the playoffs. I don't buy "favorites" when entering them. Proof is this year where the 6th seed and 8th seed are in the Stanley. I consider any year making the playoffs a success. Many of teams making the playoffs dealt with many injuries. Obviously they played a role, but can't blame it on them entirely.
Yep, anything can happen. And you have a higher probability of a deeper playoff run if you're not injury-riddled.

Quote:
Originally Posted by Dixon Ward View Post
not exactly true.

just throwing this out there for discussion.
Quote:
Originally Posted by LoveDaSwords View Post
The axis labels are irrelevant.

The real question is what the r^2 value for the trendline is. That will tell you how well the trendline fits the data, and I'd guess just looking at that data that the r^2 is not all that strong.
Quote:
Originally Posted by Der Jaeger View Post
There we go! Just change the axis interval. Proof positive.

No doubt that a few folks on here are into statistical analysis, and can show numerous different ways that the data points correlate, or do not. The problem is that you're using a systematic, linear process to explain a non-linear, systemic situation.

Chart looks neat. . . doesn't explain reality.
Agree with the inability of a 1-factor model to well-predict the system.

Quote:
Originally Posted by LoveDaSwords View Post
You're right, one really should build a regression model that adjusts for confounding variables and then check for a significant p value.
Quote:
Originally Posted by Der Jaeger View Post
BTW, you almost certainly wrote this sarcastically, but it made me break out some old books I haven't looked at in a while. Nice.
A legit point, I think, on even this simple correlation is:
Imagine (hypothetical - none are plotted) the confidence interval on the prediction (the SEE - Standard Error of the Estimate??) at low values of man-games lost. Even without a high r^2, the confidence interval is far more narrowly bound at low-man-games lost, suggesting a team with fewer injuries has greater "control" of their points earned.

As many have noted, blocking for other factors, and a multi-factor ANOVA, is far more ideal (and I'm also not a statistician).

Lastly, another factor that would be completely missed in any multi-factor analysis is what "healthy" players are playing sub-par because they are compromised by a minor injury, or are still recovering after returning from an injury.

brian_griffin is online now   Reply With Quote
Old
06-08-2012, 02:27 PM
  #68
SackTastic
Embrace The Suck
 
SackTastic's Avatar
 
Join Date: Mar 2011
Country: United States
Posts: 5,115
vCash: 500
Quote:
Originally Posted by FreddieBisco View Post
Any other amazing contributions you want to make or you just want to post another stupid picture

When I say make or break, I mean this season there is no excuses , we need to win a playoff series, if not two. If we don't , then we need to overhaul management/ coaching. This will be the 2nd off-season for Regier where he has no budget restrictions and there is no more grace period for Pegula, the honeymoon is over. Btw, this is year 2 of Pegulas self imposed "3 year plan" so my view on a make or break year isn't far-fetched at all, but I know how touchy you are when it comes to Lindy Ruff, so you probably think Pegula gets 15 years before it's a make or break season.

I mean did Pegula ever clarify the 3 year plan? Was that for winning the cup or is it just for making the postseason

Sabres = won a playoff series only twice in the past 10 seasons. I'm sick of waiting.
If you wanted to say that this is make or break for Ruff, and Regier, then ok, I'll listen to that argument. (And probably agree with it, because I think that it is.)

But saying it's make or break for Pegula doesn't make sense. No matter what outcome they have this season, Pegula isn't going to sell the team. He's not going anywhere.

SackTastic is online now   Reply With Quote
Old
06-08-2012, 02:53 PM
  #69
WhoIsJimBob
Circle the Bandwagon
 
WhoIsJimBob's Avatar
 
Join Date: Feb 2002
Location: Rochester, NY
Country: United States
Posts: 16,653
vCash: 500
Quote:
Originally Posted by Zip15 View Post
You don't blame it on two brain injuries--i.e., concussions--in one calendar year? Walk it off, Miller. Rub some dirt on it.
I think it was an issue from the neck up.

I just don't think it was entirely a concussion issue. He was playing like garbage before he got trucked by Lucic.

WhoIsJimBob is offline   Reply With Quote
Old
06-08-2012, 03:17 PM
  #70
New Sabres Captain
ForFriendshipDikembe
 
New Sabres Captain's Avatar
 
Join Date: Oct 2006
Country: United States
Posts: 39,515
vCash: 500
Quote:
Originally Posted by Jim Bob View Post
I think it was an issue from the neck up.

I just don't think it was entirely a concussion issue. He was playing like garbage before he got trucked by Lucic.
He went 4-4 in October, but with a 930 S% and a 2.14 GAA (and 1 shutout).

The couple games right before the Lucic hit (and including it) were pretty bad--got pulled in the Philly game after 6 minutes, and won the Jets game despite being real shaky and giving up 5 goals. And then we know the Lucic game and the second period implosion.

New Sabres Captain is offline   Reply With Quote
Old
06-08-2012, 05:32 PM
  #71
joshjull
Moderator
 
joshjull's Avatar
 
Join Date: Aug 2005
Location: Hamburg,NY
Country: United States
Posts: 34,402
vCash: 500
Quote:
Originally Posted by Jim Bob View Post
I think it was an issue from the neck up.

I just don't think it was entirely a concussion issue. He was playing like garbage before he got trucked by Lucic.
LDS beat me to it but Miller had 8 pretty good games in October. He had 2 rough games before getting trucked by Lucic. That's 2 of 10. Yet some keep trying to created this false narrative that he was a headcase that was struggling with his game well before the Lucic hit. Basically trying to minimize the hit, as if it wasn't a major reason for his struggles after.

Btw LDS he was playing quite well in that Bruins game before he got steamrolled. He stopped all 12 shots in the first period of that game. We went into the 1st intermission up 1-0. He was hit by Lucic in the 1st period, 13:12 into the first period to be exact. It wasn't until the 2nd period that he started to struggle, giving up 3 goals on 10 shots. Then he sat out the 3rd period. Basically he had his "A"game until he got drilled.


Last edited by joshjull: 06-10-2012 at 02:22 AM.
joshjull is online now   Reply With Quote
Reply

Forum Jump


Bookmarks

Thread Tools

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off



All times are GMT -5. The time now is 04:03 PM.

monitoring_string = "e4251c93e2ba248d29da988d93bf5144"
Contact Us - HFBoards - Archive - Privacy Statement - Terms of Use - Advertise - Top - AdChoices

vBulletin Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.
HFBoards.com is a property of CraveOnline Media, LLC, an Evolve Media, LLC company. 2014 All Rights Reserved.