Wild Card Race (Western Conference)

[blender]

Originally Posted by CorsiHockeyLeague

2. The responses are absurd here - I was responding to a post that suggested that the only things that matter are points and games remaining. That's obviously wrong.

I'm all for different ways to look at the game, and I'm not anti-advanced stats per se, but points ARE the only thing that matter, and GAMES are the only way to get points.

It's you who is being absurd.

[Vinny01]

Wild win tonight the Flames fall out of a playoff spot for the first time in weeks

[saillias]

When you see a new poster with the username "CorsiHockeyLeague" you know it's not going to end well.

[heep223]

Originally Posted by CorsiHockeyLeague

At this point people who dismiss those metrics are the hockey equivalent of the anti-vaccination folks. Believe what you want, if you're happier living in ignorance, enjoy.

Comparing critics of possession proxy stats to anti-vaccination advocates is a great way to fast track yourself into someone's sig.

Not in a good way.

[Rejean31]

Advanced hockey stats and Corsi and Fenwick is such a load of crap. For crying out loud, the Oilers kill it in Corsi and Fenwick and they are the biggest dumpster fire in the league. Just a complete load of crap.

[CorsiHockeyLeague]

Originally Posted by Jay Random

The best predictor of future success in hockey is goal differential. Puck possession proxies are not even close.

This is not the case. Over time, goal differential approaches possession in terms of predictive value, but to say goal differential is better and possession stats are "not even close" will require that you provide some link to somewhere where that's been demonstrated, or you could demonstrate it yourself.

So basically, you've just called everyone on CP Jenny McCarthy. Would you like ketchup for that foot?

If literally everyone on CP is dismissive of possession as a useful predictive measure (see the guy immediately above me) then they deserve it. Or, if you don't like the anti-vaccination comparison, try flat-earthers. Not even worth talking about hockey with.

[Jay Random]

Originally Posted by CorsiHockeyLeague

This is not the case. Over time, goal differential approaches possession in terms of predictive value, but to say goal differential is better and possession stats are "not even close" will require that you provide some link to somewhere where that's been demonstrated, or you could demonstrate it yourself.

For instance:

http://rinkstats.blogspot.ca/2013/10...key-games.html

Money quote:

What surprised me is that the statistic that I would have guess correlates most strongly with winning (shots on goal) is highly correlated with winning, but in the wrong direction. That's to say, the team that takes more shots in a game is, on average, less likely to win the game.

The article goes on to describe the methodology used to minimize score effects in the data. Even with score effects eliminated, the negative correlation persists.

Now remember, Fenwick and Corsi measure shots on goal (or shots attempted), NOT puck possession. We actually have no good numbers for puck possession. If SOG are negatively correlated with winning, that pretty much eliminates the possibility that Corsi or Fenwick could be positively correlated. I suspect that may be too much to say based on the analysis given, but it certainly calls into question the idea that there is a strong correlation.

Meanwhile, the correlation between goal differential and winning percentage is exceptionally strong – R ~ 0.96, R^2 ~ 0.93:

http://hockeyanalytics.com/2008/01/t...key-analytics/

(See Law #4.)

Now, how about you demonstrate the reverse?

If literally everyone on CP is dismissive of possession as a useful predictive measure (see the guy immediately above me) then they deserve it. Or, if you don't like the anti-vaccination comparison, try flat-earthers. Not even worth talking about hockey with.

Boy, you just love making friends, don't you? First you insult everyone, then you double down on the insult. And you have done absolutely nothing to make your case, except to insult people for not agreeing with you.

[Goodlad]

Originally Posted by CorsiHockeyLeague

If literally everyone on CP is dismissive of possession as a useful predictive measure (see the guy immediately above me) then they deserve it. Or, if you don't like the anti-vaccination comparison, try flat-earthers. Not even worth talking about hockey with.

Personally I'm someone who admits to having a limited understanding of "advanced" stats, but am always open to new ways to analyze and understand the game I love. I find more than anything that the viewpoint you seem to typify in your posts so far is my biggest turn-off with them. This elitist attitude does nothing whatsoever to generate discussion in this or any other forum, and I find it very prevalent with a lot of stats advocates.

Instead of being so dismissive with posters who take a differing view you could instead expand upon why you feel your stance is valid.

[indes]

I fail to see how anyone can defend a premise that has already been proven false up to this point in the season. You keep saying you're right even though using your method doesn't come close to what the standings look like. Who really has their head in the sand?

[CorsiHockeyLeague]

Originally Posted by Jay Random

For instance:

http://rinkstats.blogspot.ca/2013/10...key-games.html

Money quote:

What surprised me is that the statistic that I would have guess correlates most strongly with winning (shots on goal) is highly correlated with winning, but in the wrong direction. That's to say, the team that takes more shots in a game is, on average, less likely to win the game.

Yeah, so, I have no idea who that guy is, but he doesn't adequately adjust for score effects. "Games tied entering the third" often don't stay that way and score effects exist as early as the five minute mark of the first in some games. If he just removed all data from non-score-close situations, this would make more sense. Either way, it's pretty clear this dude has no idea what he's talking about - look at his conclusion; "win the faceoff battle". If you want to know how useless faceoffs are, I'll direct you here: http://statsportsconsulting.com/main...lysis12-12.pdf

If you want to see the correlation and reliability for numerous different statistics as they pertain to winning, it's all right here: http://www.pensionplanpuppets.com/20...-blocked-shots

Now remember, Fenwick and Corsi measure shots on goal (or shots attempted), NOT puck possession. We actually have no good numbers for puck possession. If SOG are negatively correlated with winning, that pretty much eliminates the possibility that Corsi or Fenwick could be positively correlated. I suspect that may be too much to say based on the analysis given, but it certainly calls into question the idea that there is a strong correlation.

They measure shot attempts, there is no "or" about it. They are an excellent proxy for puck possession, which was determined when a bunch of leafs fans took a stopwatch and compared actual time of possession over a series of games in 2013 and found the results basically mirrored corsi. Another couple of guys did it with the Flyers, same thing. That being said, once sportVU or whatever is implemented and actual minutes / seconds of possession time are determined, these stats will basically be obsolete.

Meanwhile, the correlation between goal differential and winning percentage is exceptionally strong – R ~ 0.96, R^2 ~ 0.93:

http://hockeyanalytics.com/2008/01/t...key-analytics/

(See Law #4.)

Hahaha, wait, your argument is that a team that scores more goals than their opponents is more likely to have won more games? Yes, if at the end of the season you look at the teams that have scored the most goals and allowed the fewest, you're likely to see them at the top of the standings. That's more or less a truism. What exactly is this supposed to show? The purpose of predictive analysis is to try to determine who will outscore who in the future. Past goal differential does not do as good a job of this as possession (particularly fenwick close) - basically because of reliability. Refer to the pensionplanpuppets article above.

As for why I'm not willing to have the debate at any length (even this is a waste of time) it's that regardless, people with inherent biases will try to find reasons to disbelieve something that suggests their hockey team isn't very good. All of this information is out there and has been for more than half a decade, yet you still get people essentially saying "this is false because there are teams in the current standings that frustrate your predictions" like Indes, as if that demonstrated anything important. I could post every relevant article and answer every criticism (as has been done a thousand times on dozens of internet fora) and the same criticisms would arise a week later, expressed as though only just thought of for the first time. It's pointless.

Hockey fans exhibit some incredible tribalism, especially on the internet. As a result, I'd rather just say, "here's the data", and if you'd prefer to ignore it, fine.

[Vulcan]

Originally Posted by Jay Random

The thing is that the season cannot possibly end today, because not all teams have played equal numbers of games. If for some reason the NHL had to cut the season short, they would have to come up with some ad-hoc rule to compensate for different numbers of games played – and that rule probably would not be the current tie-breakers for standings in mid-season. If it were, they would be opening themselves up to seven-figure lawsuits from teams that did not get a fair chance at playoff berths because of the unequal schedule.

Which pretty much takes out ‘if the season ended today’ as a valid argument.

The rules are there in black and white and have been agreed to, the rest is just your opinion.

I stand by my first statement.

In fact with the current standings the Canucks would play the Kings.

[indes]

Originally Posted by CorsiHockeyLeague

Yeah, so, I have no idea who that guy is, but he doesn't adequately adjust for score effects. "Games tied entering the third" often don't stay that way and score effects exist as early as the five minute mark of the first in some games. If he just removed all data from non-score-close situations, this would make more sense. Either way, it's pretty clear this dude has no idea what he's talking about - look at his conclusion; "win the faceoff battle". If you want to know how useless faceoffs are, I'll direct you here: http://statsportsconsulting.com/main...lysis12-12.pdf

If you want to see the correlation and reliability for numerous different statistics as they pertain to winning, it's all right here: http://www.pensionplanpuppets.com/20...-blocked-shots


They measure shot attempts, there is no "or" about it. They are an excellent proxy for puck possession, which was determined when a bunch of leafs fans took a stopwatch and compared actual time of possession over a series of games in 2013 and found the results basically mirrored corsi. Another couple of guys did it with the Flyers, same thing. That being said, once sportVU or whatever is implemented and actual minutes / seconds of possession time are determined, these stats will basically be obsolete.


Hahaha, wait, your argument is that a team that scores more goals than their opponents is more likely to have won more games? Yes, if at the end of the season you look at the teams that have scored the most goals and allowed the fewest, you're likely to see them at the top of the standings. That's more or less a truism. What exactly is this supposed to show? The purpose of predictive analysis is to try to determine who will outscore who in the future. Past goal differential does not do as good a job of this as possession (particularly fenwick close) - basically because of reliability. Refer to the pensionplanpuppets article above.

As for why I'm not willing to have the debate at any length (even this is a waste of time) it's that regardless, people with inherent biases will try to find reasons to disbelieve something that suggests their hockey team isn't very good. All of this information is out there and has been for more than half a decade, yet you still get people essentially saying "this is false because there are teams in the current standings that frustrate your predictions" like Indes, as if that demonstrated anything important. I could post every relevant article and answer every criticism (as has been done a thousand times on dozens of internet fora) and the same criticisms would arise a week later, expressed as though only just thought of for the first time. It's pointless.

Hockey fans exhibit some incredible tribalism, especially on the internet. As a result, I'd rather just say, "here's the data", and if you'd prefer to ignore it, fine.

If there's been what you consider and adequate sample size to use to compare corsi and fenwick how is there not a large enough size to use goal differential?? There is literally no evidence of your stats being a better predictor than goal diff. To laught off stats that have been backed up is pretty ironic considering the meaningless percentages you've put onto a graph.


Yes, heaven forbid we look at results of the methods used. Minnesota has less points, more games played and is farther out of the top 3 in their division than Calgary. They have double Calgary's chance to make the playoffs? As has already been mentioned Corsi and Fenwick do an incredibly poor job predicting wins. Your choice in stats to combine is inherently flawed and it becomes obvious with the results, even though those aren't important. I guess if you can make a fancy a graph with some random numbers that's good enough for hits

[blender]

The thing that gets me about this debate is why we are even having it. I've always wondered what the motivation of predictive analysis is. To gain a gambling edge? Or is it just the human need to assign meaning to things.

As fan of sports, hockey in particular, and the Flames especially, I know why I like to watch; the thrill of the game and the uncertainty of the outcome. Down three to the Bruins for the win; blowing a two-goal lead on the Ducks. I was there in the moment watching my team perform, for good or for bad. I don't need or want a flawed analysis, and frankly, don't know why anyone would. What is the purpose in the middle of a playoff race.
I think that is why a lot of members here bristle at the concept of analytics.

Anyways, obviously just my two cents, so take it or leave it. I'll be watching the Flames go after two much-needed points on Tuesday in New York City. Hope you can put down the stop watch or slide rule and enjoy the game, too.

[fuffalo]

Out of curiosity, does the NHL publish their statistical data somewhere? That is to say, a database dump of some kind? Is it something you can purchase or buy the rights to use?

[Kjesse]

I wonder if Corsi Dude has read "The Value of Outscoring, a Primer", or more particularly, if he wrote it and forgot.

[MotoRacer]

Originally Posted by Vinny01

Wild win tonight the Flames fall out of a playoff spot for the first time in weeks

Huge game tonight

[the2bears]

Originally Posted by blender

The thing that gets me about this debate is why we are even having it. I've always wondered what the motivation of predictive analysis is. To gain a gambling edge? Or is it just the human need to assign meaning to things.

As fan of sports, hockey in particular, and the Flames especially, I know why I like to watch; the thrill of the game and the uncertainty of the outcome. Down three to the Bruins for the win; blowing a two-goal lead on the Ducks. I was there in the moment watching my team perform, for good or for bad. I don't need or want a flawed analysis, and frankly, don't know why anyone would. What is the purpose in the middle of a playoff race.
I think that is why a lot of members here bristle at the concept of analytics.

Anyways, obviously just my two cents, so take it or leave it. I'll be watching the Flames go after two much-needed points on Tuesday in New York City. Hope you can put down the stop watch or slide rule and enjoy the game, too.

Ah, but you see, playing the game is exactly the type of debate, an on-ice type, that Kid Fancy Stats does not have time for.

[heep223]

Originally Posted by CorsiHockeyLeague

Hockey fans exhibit some incredible tribalism, especially on the internet. As a result, I'd rather just say, "here's the data", and if you'd prefer to ignore it, fine.

Except you're not doing that. You're saying "here's the data" alright, with the caveat that whoever doesn't agree with you is an idiot and not worth talking to. All in a really condescending way.

This really discredits anything you say regardless of the data and the response to you is likely overwhelmingly negative.

Which is probably why you seem to have such a jaded view of hockey fans (and probably people in general) and don't get very far with your arguments. There are a lot of smart people in the world, and they all disagree with each other. The sooner you accept this the sooner people will start paying attention to you.

[MotoRacer]

Wild win tonight flames both be at 68% to make playoffs according to SCS site

[2ArmBands]

This whole analytics and enhanced stats debate is just plain annoying now. There are so many pro analytics guys walking around like they are preaching the hockey gospel and are trying to take way too much credit for it IMO.

Many of their stats albeit interesting are nothing more than an addition to a stats base already existing. They are proven to do nothing more than provide information and have no concrete base. It's another stat. Great... We get it.

Please stop trying to shove it down our throats and telling us life long hockey fans how uneducated we are about the game.