Steve Kasper does not know how statistical analysis works

Cam Charron
August 12 2013 04:33PM

Another gem from Alec Brownscombe. I bet next year they don't get the access to do these again. The interviews went viral this year for all the wrong reasons. We've already parsed interviews with Greg Cronin and Dave Poulin. Today's is Steve Kasper, the Leafs' director of pro scouting:

No, we are not using a statistical analysis. I am not saying there’s not room for that in the game, but sometimes a player’s contribution does not always show up on a stat sheet. I know a statistical analysis isn’t simply looking at goals and assists, but sometimes a player can play his best game and you don’t see his name anywhere on the scoresheet. My own personal belief is that I like there be live and see a game myself.

Does anybody dispute the bolded point?

The scoresheet has the following categories: Goals, Assists, Points, +/-, penalties, penalty minutes, time on ice, shifts, powerplay time, shorthanded time, even strength time, shots, attempted shots blocked, missed shots, hits, giveaways, takeaways, blocked shots, faceoffs won, faceoffs lost, faceoffs percentage. Most of those categories are completely useless.

What statistical analysts do is look beyond the scoresheet to the play-by-play sheet and, with enough sample size, determine what happened when a certain player was on the ice in a certain situation. You can find a lot of things that don't show up on the scoresheet there. Nobody is scared of Patrice Bergeron's 10 goals and 32 points in 42 games this season, but they are scared of the fact that he's perhaps the most dominant two-way centreman in the game because the Bruins out-shoot the opposition 12.1 to 9.0 per 20 minutes when Bergeron is on the ice. This is why Bergeron gets an eight-year contract and is perennially nominated for the Selke Trophy.

You can do a lot with statistics, but a lot of people write it off as worrying too much about split statistics (how many goals does he score on a Tuesday) and a lot of numbers you can produce are absolute junk. The point isn't about using only numbers, but numbers have a memory and less bias than humans do. Even if a pro scout is told to look for a specific type of player, concentrating on one player leads to tunnel vision and you can't see anything in its context.

Such as this:

AB: Bolland had a bit of a down year despite ample PP time and the opportunity to play with some good linemates in Chicago. What makes the team confident he’ll bounce back? Do you think that 2nd line scoring role was an improper one for Bolland?

SK: Well, first of all, I don’t know who is making the determination that he had a down season. You didn’t hear that from me. Obviously Chicago had a very successful year winning the championship, but were also very successful from the day the puck was dropped to the final faceoff. I just think Bolland was a regular contributor to that team, and a big contributor to that team. You didn’t hear me say he had a down year. My job is not to define his role. The coaching staff assembles the team and plays them in the role that they see fit to help Toronto win. In Dave Bolland we have a very versatile player who can contribute in all three zones, and can play in all game situations. I’m sure Randy Carlyle and the coaching staff will find the best way to utilize his skillsets.

That's, uh, kinda scary. I wrote the day of the Mikhail Grabovski buy-out that it was odd to see the Leafs add a player coming off a down season in place of another. This reinforces the theory we've had that the Leafs didn't do any significant research into David Bolland. Dave Nonis suggested that the Leafs will play him in a more prominent role, when it would literally take 10 seconds to boot up David Johnson's website and note that Bolland played 392 of his 425 minutes at even strength this season alongside Patrick Kane. ("Stanley Cups won" is a statistic)

Those are the kinds of things that you can use data to analyze. You can see how a player fared with another, how they did in a situation off a defensive zone or offensive zone draw, or how often a player played with another. Again, these aren't things that are showing up on the scoresheet, and doing what I do night in and night out I often find myself ignorant to short hot streaks or cold streaks. A player could score and the commentator yells that's the player's first goal in 10 games and I find myself surprised, because here I am paying attention to things other than pucks going into the net, and mostly on which players are creating meaningful possessions.

The real issue is that the Maple Leafs are the richest team in hockey and are not doing anything to supplement their view of the game. There's no team run by a strawman general manager that puts together a lineup using only a computer and I'm not a proponent of that, but I'm a proponent of finding as much data you can find to go against a move you're thinking of making. Why? As Nassim Taleb pointed out in his book The Black Swan, a book that you haven't read is much more valuable to you than a book you have read. It's sometimes what you don't know that's of the most value to you.

63811cbf517d2d685ea09e103488ea3a
Cam Charron is a BC hockey fan that writes about hockey on many different websites including this one.
Avatar
#2 Shawn
August 12 2013, 05:46PM
Trash it!
11
trashes
+1
9
props

The thing I love about advanced stats is that I can make arguments or predictions about players and teams and never have to admit I was wrong about them. It's great - if they perform better or worse than I thought they would, then it's just good or bad luck and will even out over time. I win every argument now.

Avatar
#3 DP
August 12 2013, 07:15PM
Trash it!
9
trashes
+1
16
props

Battles over traditional methodology vs quantitative analysis have been going on for years in all sorts of professions like Finance, History, Psychology...

That you don't seem to realize this indicates that you lack perspective. I am guessing that you didn't study intellectual history a great deal during your Bachelor of Arts in Journalism?

I am guessing few courses in Statistics and no graduate courses in Quantitative Methods?

If you really want to be taken seriously, it's time to go back to school. Conduct research and defend a Master's or a Ph.D. thesis in this area where there are quants from other disciplines and Ph.D.'s in Statistics on your defense committee. Your work will better for it.

North Dakota State University actually has Ph.D. Program in Statistics with Emphasis in Sports Statistics.

The requirements are quite high, in addition to the Graduate School requirements, the applicant must:

Have had four courses in math at the university calculus level or above. Have had several courses in statistics. Have had a least one programming language.

Spend some years and do some stunning peer reviewed research. Do something that is so good that people in the NHL want to hire you to replace those that you critique.

Until you do this, you are just a guy with a B.A in Journalism, constructing high school level arguments about data.

Avatar
#6 DP
August 12 2013, 10:46PM
Trash it!
8
trashes
+1
13
props

@Cam Charron & Back in Black

If you are going to publicly question another professional in an article entitled "Steve Kasper does not know how statistical analysis works" then I think it is fair to question the writer's credentials as they relate to Statistics.

It's even more appropriate considering that the author has written many articles using advanced statistics, yet in today's article, "Steve Kasper does not know how statistical analysis works" Cam writes this beautiful sentence:

"The point isn't about using only numbers, but numbers have a memory and less bias than humans do."

Anyone with any sort of education involving statistics probably cringes when reading that sentence.

Who created the numbers?

Humans!

Plus there are all sorts sources and types of possible bias in numbers...selection bias, spectrum bias, detection bias, and so on

In a rebuttal, Cam even gives an example:

"A guy called Michael Schuckers wrote up a Total Hockey Rating that got some press at Sloan, but he forgot to account for the fact that RTSS data is calculated differently in each arena and that score effects exist.

In closing Cam gets sounds more like Steve Kasper:

"I really could not care less what MLSE or commenter DP thinks of my credentials. I'm not around to speak entirely in numbers and obscure language."

Have we struck a nerve? Could it be that a guy who constantly whines about advanced stats and criticizes others has a minimal or no university level education in statistics?

I am a quant. My dissertation used massive amounts of quantitative data. I had to take those Statistics and Quantitative Methods courses. Because of this, I think its fair for me to question the credentials of others, especially if they publicly criticize others in this area and make their own questionable statements in the same article.

Avatar
#7 Back in Black
August 12 2013, 08:49PM
Trash it!
6
trashes
+1
20
props

@DP

You know, I think there's a term for criticizing the credentials of your opponent while ignoring his arguments. I'd tell you what it is, but since I don't have an advanced degree in Latin I'm probably not qualified.

Avatar
#8 Justin
August 13 2013, 12:11AM
Trash it!
6
trashes
+1
14
props

@DP

@DP

As somebody currently enrolled in a PhD program, I'd just like to say that this kind of Ivory Tower elitism isn't representative of academia in general. The idea that you need a graduate degree to make an astute argument is so ridiculous that it's barely worth dignifying with a response. Your sense of self-aggrandizement just confirms the worst stereotypes that people have about academics. Apparently your dissertation wasn't in Philosophy, or you'd know what an "appeal to authority" was. Heck, literally thousands of teenagers take courses in statistics. It's really not difficult stuff. Using numbers to argue something in a meaningful fashion, though, is an acquired skill, and one that I've seen used by countless people from countless walks of life. So you're getting a grad degree. Big deal. You aren't even refuting anything that Cam's saying aside from bragging about how smart you ostensibly are. Really, I'd expect somebody who was really in a grad program to understand how un-exceptional that grad students really are.

"The point isn't about using only numbers, but numbers have a memory and less bias than humans do."

My statistics education is pretty solid. It's solid enough to understand that the reason that human beings use statistics is that mathematical reasoning is a system of logic with agreed-upon rules that allow any person who properly apply those rules to arrive at the same conclusions. I might use stats in a biased fashion, but if you run those same stats then you'll arrive at different conclusions and reveal my bias. I could probably wrangle the numbers to demonstrate that Nazem Kadri was better than John Tavares, but it wouldn't take you much time to use those same numbers to refute me... because we all have access to the same pool of numbers. Not so with scouting-- every scout has their own opinion that is not replicable by others. Which is the point-- scouts are trained to do their job and not just anybody can, and scouts absolutely have value in interpreting low-sample size data in a meaningful fashion. Scouts, then, deal with qualitative and not quantitative data. They're definitely valuable, though, and no real "advanced" stats person says they aren't.

Also, what kind of "advanced" stats does hockey even have? CORSI is the exact same thing as plus/minus, except it's counting shots rather than goals. If looking at CORSI is "advanced" then "advanced" hockey analytics has been around for decades. I'd wager it has more to do with people disliking numbers that they disagree with. And I have bad news for you-- it's probably not the numbers that are wrong in most cases.

Avatar
#9 Steve Burtch
August 13 2013, 08:07AM
Trash it!
6
trashes
+1
4
props
DP wrote:

Battles over traditional methodology vs quantitative analysis have been going on for years in all sorts of professions like Finance, History, Psychology...

That you don't seem to realize this indicates that you lack perspective. I am guessing that you didn't study intellectual history a great deal during your Bachelor of Arts in Journalism?

I am guessing few courses in Statistics and no graduate courses in Quantitative Methods?

If you really want to be taken seriously, it's time to go back to school. Conduct research and defend a Master's or a Ph.D. thesis in this area where there are quants from other disciplines and Ph.D.'s in Statistics on your defense committee. Your work will better for it.

North Dakota State University actually has Ph.D. Program in Statistics with Emphasis in Sports Statistics.

The requirements are quite high, in addition to the Graduate School requirements, the applicant must:

Have had four courses in math at the university calculus level or above. Have had several courses in statistics. Have had a least one programming language.

Spend some years and do some stunning peer reviewed research. Do something that is so good that people in the NHL want to hire you to replace those that you critique.

Until you do this, you are just a guy with a B.A in Journalism, constructing high school level arguments about data.

So talk about absurd appeals to authority. Cam's work is rarely if ever statistically flawed. Saying qualitative vs quantitative research debates have been going for years is ridiculous.

Your referencing of psychology, economics, history is funny because those are "soft sciences" with huge numbers of theorists drawn into them who tend to rely on qualitative observations in absurdly small samples for "controlled experiments". The statistical underpinnings of much of the quantitative analysis it goes up against tends to be full of bizarre assumptions as a result of attempts to idealize extremely chaotic systems for analysis.

Most quantitative analysts in these fields are up front about the limitations of their work (as is the sports analytics community). The ones that aren't are dishonest at best or ignorant at worst.

I teach mathematics, I have a degree in engineering, I've taken multiple courses in Calculus, Algebra, Programming, Information Systems, Dynamic Systems modelling, oh and yes.... Statistics.

I actually know a number of PhDs in information analytics and data analysis who would agree that Steve Kaspers views are ridiculous... Cam doesn't need extra degrees to point out the obvious.

The fact you require a bunch of letters beside someone's name before you consider their statements sincerely is a sad indictment of your ability to synthesize and process views that are alternative to your own.

Avatar
#10 kadrimania
August 12 2013, 09:34PM
Trash it!
5
trashes
+1
8
props

I don't think you read the interview fully or are ignoring facts because it doesn't fit your narrative. I will requote below.

"Dave Nonis obviously makes the final determination on anything that goes on in the organization. We’re consulted and we give our opinion. Dave accumulates all of the data and all of the information and makes his decision."

His job is to give his opinion on the player and not run spreadsheets and such. And from what he says, it appears that Dave himself or an associate are collecting data, stats to make the final decision.

I'm not sure if you have ever worked professionally, but usually what happens is you are given a specific task. And another person has another task etc. I find it funny you want everyone to practice advanced stats? I can't wait for the water boy and trainer interview, when you go off on how he doesn't understand advanced stats.

Avatar
#11 Steve Burtch
August 13 2013, 08:19AM
Trash it!
5
trashes
+1
5
props

@kadrimania

In the same interview Kaspers mentions the only have 4 pro scouts. If none of them record or understand advanced stats then who in the scouting department does?

Avatar
#12 Bryan Harold
August 12 2013, 05:02PM
Trash it!
4
trashes
+1
10
props

"Another gem from Alec Brownscombe. I bet next year they don't get the access to do these again. The interviews went viral this year for all the wrong reasons."

Seems like a fair statement (:-/). Where are your interviews with these guys, Cam? Why do you have to aggregate the content and make posts about it?

Avatar
#13 Roke
August 12 2013, 05:10PM
Trash it!
4
trashes
+1
9
props
Cam Charron wrote:

The worst thing about being a blogger is that I don't have access to the limitless wisdom of the Toronto Maple Leafs executives.

I might learn something like "sometimes a player can play his best game and you don’t see his name anywhere on the scoresheet".

It's true though: Colton Orr's best games come when he's sitting in the press box.

Avatar
#14 Bryan Harold
August 12 2013, 05:26PM
Trash it!
4
trashes
+1
5
props

@Cam Charron

But he's posting to a website? Surely it can't be that hard, can it?

Avatar
#15 Jordan
August 12 2013, 05:32PM
Trash it!
4
trashes
+1
8
props

I'd like to think that a good scout would know the overall value of a Bergeron without needing to look the stats. I also think many stats. can be misleading and may tend to cloud the judgement of scouts who are trained to use their eyes. There is obviously a place for stats. to a point, but they can lead to bad decisions at the same time.

Avatar
#16 Not Norm Ullman
August 12 2013, 09:15PM
Trash it!
4
trashes
+1
8
props

I GUT ME A P00-HD FRUM NORD DAKETTA!

HEY! MORE GRAVY MA! MORE GRAVY GOLDURNIT! IFFN YOU HAD THE CALCULUS I GUT MA, YOUD NO I NEED MOAR GRAVY!

AS FOR HACKEY, EEZE ON DOWN THER LIL FELLA. PUT YER SKATS ON 1 FEET AT A TIME. STOP TAWKING! YOU R JUST LIKE CORN TO ME. ALL TASSEL, NO EARS! THASSA FARGO JOKE!

NOW. LISSEN TO MY PIGHD IS STATS. MY ADVICE IS - TRADE FOR BETTER PLAYERS. THE HI-ER SCORERS. GIT SUM THAT GUT MANY MANY GOALS. LIKE THAT GORDIE HULL. AND OTHER NORF DAKTTEA GRATES.

MORE GRAVEE MA! JEEBUZ H WOOD-CHIPPR WOMAN, MORE FRACKING GRAVEY!

Avatar
#17 millzy09
August 12 2013, 11:00PM
Trash it!
4
trashes
+1
2
props

@Cam Charron

"Most of those categories are completely useless."

While I think ad stats have a lot of value, this is a pretty bold statement. The only categories that are completely useless to me are penalty stuff and TOI subgroups. +/- is also debatable but a guy that is +40 is generally a way better two-way player than someone at -40.

Avatar
#19 DP
August 13 2013, 12:16AM
Trash it!
3
trashes
+1
8
props

"This is hockey and not rocket science.

How hard is it to point out that a player's shooting percentage is unsustainable? Do I need to go to North Dakota for two years to be able to see that David Bolland played most of his minutes with Patrick Kane?"

Here's my opinion. I actually think the advanced stats guys are on to something.I don't agree with all the specific arguments, but there are some instances where I take a second look and say, "My gosh, you're right."

As somebody who is a quant, I recognize that there are instances where statistical analysis gives a unique and profound insight that you can't get any other way and the rocket science approach is important to getting to that point of insight.

Sometime in the future it would not surprise me if some young coaching staff uses even more advanced stats to change the way game is won. It also wouldn't surprise me if a core member of that staff had Ph.D. from North Dakota in Sports Statistics or something similar and the the rocket science approach will have played a role.

Avatar
#20 DP
August 13 2013, 12:58AM
Trash it!
3
trashes
+1
7
props

"So you're getting a grad degree. Big deal...Really, I'd expect somebody who was really in a grad program to understand how un-exceptional that grad students really are."

I was in grad school 20 years ago. I turned my research into a job and my own department and staff in the private sector.

There were tough times with no jobs in the nineties, but the good education helped remove doubt from people's minds and opened doors.

What I don't really understand is why people who are so into advanced stats don't try combine that with a graduate education that would help legitimize their approach. I think they could turn that into a terrific career, working up the scouting ranks, etc.

That's just the way I think about things.

Avatar
#21 Set Theory
August 13 2013, 09:18AM
Trash it!
3
trashes
+1
1
props

Pardon me.

I would like to point out that a certain Chad Fines would be a perfect addition to the Leafs scouting department. Further, this proves my prior assertion that a certain article surrounding Chad Fines was not obviously satirical. In fact, the similarities between fact and fiction are startling. Very startling, indeed.

Now, by all means, carry on with the squabble. It's amusing, if not enlightening.

Avatar
#22 kadrimania
August 13 2013, 09:37AM
Trash it!
3
trashes
+1
5
props

@Steve Burtch

What is funny is all this talk about "appeal to authority", is that they than use "appeal to stats". Like because they are "stats" they have some sort of authority. Yet stats can be as biased, manipulated and misused just like those in power.

Avatar
#23 Not Norm Ullman
August 13 2013, 11:57AM
Trash it!
3
trashes
+1
1
props

MOAR GRAVEY MAM!

ND STATE WOOOOOOOO!

Avatar
#24 Bryan Harold
August 12 2013, 05:09PM
Trash it!
2
trashes
+1
4
props

@Cam Charron

Alec is a blogger, though.

Avatar
#25 rw970
August 12 2013, 07:17PM
Trash it!
2
trashes
+1
7
props

"First of all, it’s easy to identify need but, similar drafting to players, if you have an opportunity to get a player that is going to help make your team better then you’re going to look at it."

I find this idea kind of disturbing, and I'm worried that it keeps popping up.

Fact is, drafting players is really not that much like acquiring players on either the trade or free agency markets. Drafting players is free!

At the draft, it kind of makes sense not to draft for need. Draft picks are free, all the players you sign from the draft will be really cheap, and essentially the same price, anyway, so might as well go for the very best you can find. After all, it could be years by the time Kari Lehtonen or whoever develops into a number one goaltender, and by that time, you may have solved the problem anyway. Might as well draft Rick Nash.

But with trades and FA, these players are not free to acquire. In both instances, you have to use up cap space, a very limited resource. To acquire players on the trade market, you have to give up players and/or draft picks, and to acquire free agents you have to overpay. It really doesn't make sense to go after the best players available if they don't satisfy an organizational need because it's an inefficient use of resources.

So, for example, if you have a whole bunch of scoring forwards, you don't buy out your best centre and let an undervalued winger walk so you can overpay a thirty year old who has yet to crack 50 points, even if TradeCentre thinks he's the hottest commodity out there, no matter how many hundreds of percent he gives every night.

You don't go after an expensive goaltender, give up players and retain their salaries to get him because he might be slightly better than the backup you currently have.

You have to think. I have X amount of resources, and Y needs to address. You can't spend all your money on candy.

Avatar
#27 rw970
August 13 2013, 08:49AM
Trash it!
2
trashes
+1
2
props
DP wrote:

Battles over traditional methodology vs quantitative analysis have been going on for years in all sorts of professions like Finance, History, Psychology...

That you don't seem to realize this indicates that you lack perspective. I am guessing that you didn't study intellectual history a great deal during your Bachelor of Arts in Journalism?

I am guessing few courses in Statistics and no graduate courses in Quantitative Methods?

If you really want to be taken seriously, it's time to go back to school. Conduct research and defend a Master's or a Ph.D. thesis in this area where there are quants from other disciplines and Ph.D.'s in Statistics on your defense committee. Your work will better for it.

North Dakota State University actually has Ph.D. Program in Statistics with Emphasis in Sports Statistics.

The requirements are quite high, in addition to the Graduate School requirements, the applicant must:

Have had four courses in math at the university calculus level or above. Have had several courses in statistics. Have had a least one programming language.

Spend some years and do some stunning peer reviewed research. Do something that is so good that people in the NHL want to hire you to replace those that you critique.

Until you do this, you are just a guy with a B.A in Journalism, constructing high school level arguments about data.

It looks like WATCH THE GAMEZ!!!! has come full circle. Now fancystaters must GET THE NORTH DAKOTA DEGREEEZ!!! before making statistically based arguments.

Avatar
#28 Not Norm Ullman
August 13 2013, 09:12AM
Trash it!
2
trashes
+1
2
props

MOAR GRAVEY, CHAM!

Avatar
#29 Jordan
August 13 2013, 09:44AM
Trash it!
2
trashes
+1
5
props

@Steve Burtch

"I actually know a number of PhDs in information analytics and data analysis who would agree that Steve Kaspers views are ridiculous"

I don't see anything ridiculous. What are you referring to? If the PhD's don't know anything about hockey, then their analysis is pretty much useless.

Avatar
#30 DP
August 13 2013, 11:16AM
Trash it!
2
trashes
+1
5
props

@Steve Burtch

"So talk about absurd appeals to authority...I actually know a number of PhDs in information analytics and data analysis who would agree that Steve Kaspers views are ridiculous... Cam doesn't need extra degrees to point out the obvious. The fact you require a bunch of letters beside someone's name before you consider their statements sincerely is a sad indictment of your ability to synthesize and process views that are alternative to your own."

But isn’t part of this issue really about influence?

Part of this issue is about the fact that advanced stat guys have only a smattering of influence in the NHL, while old boys like Steve Kasper (who may be less insightful) still have jobs, lots of influence and get to make real decisions?

Graduate degrees, dissertations, peer reviewed research and eventual real professional results are a potential way to build credibility and influence. Quants in other disciplines have used this path to make inroads in their professions. Why can’t the advanced stat guys do this?

I’m not saying the advanced stats guys are wrong. I am saying, “step up your game.”

Avatar
#31 Steve Burtch
August 13 2013, 05:41PM
Trash it!
2
trashes
+1
1
props

Allez Y Habitants Go Habs Go!! 1967 Bby.

Avatar
#32 TML67
August 15 2013, 07:08AM
Trash it!
2
trashes
+1
3
props

So you're trying to tell me guys who dedicate their entire lives to watching as many hockey games as they can, who have very little if anything to call a home life, should also be doing statistical analysis of the sport and taking any spare time for their wife and kids to do that?

They're paid to watch hockey. The Leafs very likely have a guy or team/department who works on some sort of statistical analysis to be added to what the pro scouts do. If they don't, it's not on the scouts to do it.

I honestly think you guys have lost sight of the real world to a point where the human element isn't a real thing anymore.

Maybe you should walk outside and maybe even go visit your mom and give her a big kiss? Just a thought, boys.

Again, let me hammer this through. The pro scouts get paid to scout. There should be a guy or team or even outside consultants who work on the analysis. In a recent interview, one of the ass. coaches mentioned they track scoring chances, so I'm going to assume that it might be something they track on a broader scale to use for their own theories.

Stop the crusade. This whole stats vs. scouting thing has become a complete sideshow to the point that it's become more personal than Christians vs. Atheists. To draw a parallel to that, shouldn't the ones who are "evolving" (stats) be the ones to show some sort of tolerance to other viewpoints?

Grow up.

Avatar
#33 Clrkaitken
August 12 2013, 05:47PM
Trash it!
1
trashes
+1
4
props

@Bryan Harold

Alec did the interviews for the magazine, but publication fell through at the last minute.

Rather than waste the content, he's been publishing them

Avatar
#34 Bryan Harold
August 12 2013, 06:49PM
Trash it!
1
trashes
+1
1
props

@Clrkaitken

Ah, makes sense.

Avatar
#35 kadrimania
August 12 2013, 09:22PM
Trash it!
1
trashes
+1
3
props
Shawn wrote:

The thing I love about advanced stats is that I can make arguments or predictions about players and teams and never have to admit I was wrong about them. It's great - if they perform better or worse than I thought they would, then it's just good or bad luck and will even out over time. I win every argument now.

At least you are honest about how you use advanced stats. It is nice to know there are some users of advanced stats who have integrity.

Avatar
#36 DP
August 13 2013, 05:25PM
Trash it!
1
trashes
+1
2
props

Dion Phaneuf's butt cheeks make my nipples hard.

Avatar
#37 Gene
August 14 2013, 05:13AM
Trash it!
1
trashes
+1
2
props

@Steve Burtch

"The statistical underpinnings of much of the quantitative analysis it goes up against tends to be full of bizarre assumptions as a result of attempts to idealize extremely chaotic systems for analysis."

Steve Burtch just described the paucity of attempts to use "advanced statistics" in hockey to a T.

Avatar
#38 Gene
August 14 2013, 05:23AM
Trash it!
1
trashes
+1
2
props

"(P)aucity" should read "paltry".

Avatar
#39 Gene
August 15 2013, 08:50AM
Trash it!
1
trashes
+1
2
props

Do we really suppose opposing players are scared of Bergeron because of his Corsi rating?

Player: "Oh sh$t, guys, Bergie's a total Corsi Gawd! I never knew he was this good all those times he was kicking my ass all over the ice."

Coach: "We'll have to devise a whole new way of thinking about hockey. From now on, we're going to try and keep the puck away from the other team! Thanks, Stats Guy!"

Avatar
#40 Back in Black
August 13 2013, 08:44AM
Trash it!
0
trashes
+1
4
props

@DP

My dissertation also used massive amounts of quantitative data. I teach those statistics and quantitative methods courses. Now that we've got the argument from authority out of the way, I've never had a problem with Charron's use of statistical data. He's clear with what he does and he mainly uses methods that have been well-established and tested by others, including professionals in the field of sports analysis.

If you want to find actual errors in the application of statistics on this site, you're welcome to it. In fact, I'm sure it would be appreciated by the authors. However, if you just want to nitpick the phrasing to show off your education it's not going to go over well.

Avatar
#41 Sean
August 13 2013, 10:50AM
Trash it!
0
trashes
+1
3
props
kadrimania wrote:

What is funny is all this talk about "appeal to authority", is that they than use "appeal to stats". Like because they are "stats" they have some sort of authority. Yet stats can be as biased, manipulated and misused just like those in power.

Sure they can be manipulated. Those same statistics can also be used to reveal how the statistics are being manipulated. That's the point.

Comments are closed for this article.