Bracketology for 2020 NCAAs

We're going to Allentown! Jeff Hopkins will be happy.

In before someone says “it’s too early for this to be really meaningful”

Who is going to watch any games in Albany. They should switch Clarkson/North Dakota with Minn. State/Sacred Heart. Clarkson fans go to Albany and U Mass fans go to Worcester. Sacred Heart fans can easily get to either and the rest have to fly anyway.

Jim Hyla
Who is going to watch any games in Albany. They should switch Clarkson/North Dakota with Minn. State/Sacred Heart. Clarkson fans go to Albany and U Mass fans go to Worcester. Sacred Heart fans can easily get to either and the rest have to fly anyway.

Has Nathan a track record with three brackets?

dbilmes
We're going to Allentown! Jeff Hopkins will be happy.

Assuming I can get a seat!

Shocked we didn't end up in Albany, but I guess I can see his logic.

playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

blackwidow

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

getting controversial here on eLF

ugarte

blackwidow

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

getting controversial here on eLF

60 teams and no NCAA since 1970. Gotta happen at some point. (I'm very new here. I apologize if I unintentionally started something.)

blackwidow

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

You’ve succinctly summed up why this forum still exists.

RichH

blackwidow

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

You’ve succinctly summed up why this forum still exists.

I thought it was just to make snarky comments.

Jeff Hopkins '82

RichH

blackwidow

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

You’ve succinctly summed up why this forum still exists.

I thought it was just to make snarky comments.

Speaking of which they should fire Schaffer if we don’t win it all this year.

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

You know, if people wouldn't post this deeply flawed model every year, we wouldn't have to spend time every year discussing why it's deeply flawed.

BearLover

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

You know, if people wouldn't post this deeply flawed model every year, we wouldn't have to spend time every year discussing why it's deeply flawed.

or you could just post a link to the thread from last year

Then we can start another thread about the spelling of Coach's name.....

redice
Then we can start another thread about the spelling of Coach's name.....

Thank you Redice I was afraid no one noticed.

BearLover

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

You know, if people wouldn't post this deeply flawed model every year, we wouldn't have to spend time every year discussing why it's deeply flawed.

Or you could, I dunno, fucking lighten up Francis.

RichH

blackwidow

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

You’ve succinctly summed up why this forum still exists.

"All this has happened before. And it will happen again."

redice
Then we can start another thread about the spelling of Coach's name.....

Maybe Ken wants to fire a different coach. Ever think of that?

KenP

Jeff Hopkins '82

RichH

blackwidow

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

You’ve succinctly summed up why this forum still exists.

I thought it was just to make snarky comments.

Speaking of which they should fire Schaffer if we don’t win it all this year.

Hell, why wait? Fire him now!

Swampy

KenP

Jeff Hopkins '82

RichH

blackwidow

Trotsky
playoffstatus.com current odds:

                FF    Final  Champion
North Dakota   .49     .30     .17
Cornell        .47     .29     .17
Mankato        .40     .22     .12
Denver         .32     .16     .09
BC             .28     .14     .07
Penn State     .22     .10     .05
Ohio State     .20     .10     .05

it would be wonderful to see Cornell win the NCAA.

You’ve succinctly summed up why this forum still exists.

I thought it was just to make snarky comments.

Speaking of which they should fire Schaffer if we don’t win it all this year.

Hell, why wait? Fire him now!

Srsly. He hasn't even won the 2020 ECACs and it's already January.

Swampy

redice
Then we can start another thread about the spelling of Coach's name.....

Maybe Ken wants to fire a different coach. Ever think of that?

Maybe he misspelled Archer?

Jeff Hopkins '82

Swampy

redice
Then we can start another thread about the spelling of Coach's name.....

Maybe Ken wants to fire a different coach. Ever think of that?

Maybe he misspelled Archer?

+1

Belongs in the soon-to-be-compiled Elynah Humor collection.

Last week's NCAA version.

The Bracket:

Albany Regional (Albany, NY - Host ECAC)
1. Cornell vs. 16. Sacred Heart
8. Massachusetts vs. 9. Minnesota Duluth

Worcester Regional (Worcester, MA - Host Holy Cross)
2. North Dakota vs. 15. Northern Michigan
5. Boston College vs. 10. Clarkson

Allentown Regional (Allentown, PA - Host Penn State)
3. Minnesota State vs. 14. Arizona State
6. Penn State vs. 11. Providence

Loveland Regional (Loveland, CO - Host Denver)
4. Denver vs. 13. UMass Lowell
7. Ohio State vs. 12. Northeastern

and from this week's USCHO.

This week’s brackets

West Regional (Loveland):
14 Northeastern vs. 2 Minnesota State
11 Arizona State vs. 5 Denver

Midwest Regional (Allentown):
16 AIC vs. 1 North Dakota
9 Penn State vs. 8 Clarkson

East Regional (Albany):
13 UMass Lowell vs. 3 Cornell
12 Minnesota Duluth vs. 6 Massachusetts

Northeast Regional (Worcester):
15 Quinnipiac vs. 4 Boston College
10 Providence vs. 7 Ohio State

Conference breakdowns

Hockey East — 5
ECAC Hockey — 3
NCHC — 3
Big Ten – 2
Atlantic Hockey – 1
Independent – 1
WCHA — 1

Interesting. CHN has Denver in 4th and BC in 5th. USCHO has them tied for 4th.

Jeff Hopkins '82
Interesting. CHN has Denver in 4th and BC in 5th. USCHO has them tied for 4th.

There's something wrong on uscho - not sure what. When you go to their list of comparisons, it shows Denver with 56 - which is what we have. On their chart, it shows 55. I don't know why. But 56 is correct.

Jim Hyla

Allentown Regional (Allentown, PA - Host Penn State)
3. Minnesota State vs. 14. Arizona State
6. Penn State vs. 11. Providence

This one from last week caught my eye as an all-timer, if you ask me. Four of the top six highest scoring teams in one regional, and loads of star power. Providence having to take their medicine and go against the hosts for once. Three teams trying to prove their worth as rising powers and make their 1st FF. Sure, it won't happen, but I'd pay to see that.

RichH

Jim Hyla

Allentown Regional (Allentown, PA - Host Penn State)
3. Minnesota State vs. 14. Arizona State
6. Penn State vs. 11. Providence

This one from last week caught my eye as an all-timer, if you ask me. Four of the top six highest scoring teams in one regional, and loads of star power. Providence having to take their medicine and go against the hosts for once. Three teams trying to prove their worth as rising powers and make their 1st FF. Sure, it won't happen, but I'd pay to see that.

Depending on where and when we play, I might just go to this regional final for grins.

This was before last weeks games, but I thought I'd put it up anyway.

College hockey bracketology: What things look like two months before tournament selections

The Bracket:

Worcester Region (Worcester, MA - Host Holy Cross)
1. North Dakota vs. 16. American International
8. Clarkson vs. 9. Providence

Albany Regional (Albany, NY - Host ECAC)
2. Cornell vs. 15. Northern Michigan
7. Massachusetts vs. 10. Ohio State

Allentown Region (Allentown, PA - Host Penn State)
3. Minnesota State vs. 14. New Hampshire
6. Penn State vs. 11. Arizona State

Loveland Region (Loveland, CO - Host Denver)
4. Denver vs. 13. Northeastern
5. Boston College vs. 12. Minnesota Duluth

Teams by conference:
Hockey East: 5
NCHC: 3
Big Ten: 2
ECAC: 2
WCHA: 2
Atlantic Hockey: 1
Independent: 1

In: New Hampshire, American International
Out: UMass Lowell, Sacred Heart

Well it looks like everybody is into it now.

CHN; Adam discusses Bracket ABCs ... February Edition in reference to Pairwise Probability Matrix

USCHO has a couple of different ideas in Bracketology: Figuring out problems on how to best seed the 2020 NCAA hockey national tournament

Jim’s bracket

Allentown, Pa. Regional
1. North Dakota (1)
2. Penn State (8)
3. UMass Lowell (11)
4. AIC (16)

Loveland, Colo. Regional
1. Minnesota Duluth (4)
2. Denver (5)
3. Northeastern (12)
4. Quinnipiac (14)

Worcester, Mass. Regional
1. Minnesota State (2)
2. Massachusetts (7)
3. Arizona State (10)
4. Michigan State (15)

Albany, N.Y. Regional
1. Cornell (3)
2. Boston College (6)
3. Clarkson (9)
4. Maine (13)

Jayson’s bracket

Worcester, Mass. Regional
1. North Dakota (1)
2. UMass (7)
3. Clarkson (9)
4. AIC (16)

Loveland, Colo. Regional
1. Minnesota Duluth (4)
2. Denver (5)
3. Northeastern (12)
4. Quinnipiac (14)

Allentown, Pa. Regional
1. Minnesota State (2)
2. Penn State (8)
3. UMass Lowell (11)
4. Michigan State (15)

Albany, N.Y. Regional
1. Cornell (3)
2. Boston College (6)
3. Arizona State (10)
4. Maine (13)

NCAA: The 2020 NCAA college hockey bracket, predicted about 2 months from the Frozen Four

The projected 2020 NCAA college hockey bracket (as of Feb. 12)

Albany Regional (Albany, NY - Host ECAC)
1. North Dakota vs. 16. American International
6. Boston College vs. 9. Clarkson

Worcester Region (Worcester, MA - Host Holy Cross)
2. Minnesota State vs. 14. Quinnipiac
7. Massachusetts vs. 10. Arizona State

Allentown Region (Allentown, PA - Host Penn State)
3. Cornell vs. 15. Michigan State
8. Penn State vs. 11. UMass Lowell

Loveland Region (Loveland, CO - Host Denver)
4. Minnesota Duluth vs. 13. Maine
5. Denver vs. 12. Northeastern

Well if Jim read my article (I'm sure he was one of the ones rolling his eyes) - he'd know that those brackets are neither "projections" nor "predictions" at all. It bothers the ever loving hell out of me when they're called that.

adamw
Well if Jim read my article (I'm sure he was one of the ones rolling his eyes) - he'd know that those brackets are neither "projections" nor "predictions" at all. It bothers the ever loving hell out of me when they're called that.

I read your article, Adam. I didn't roll my eyes, but I did smirk a bit at the disclaimer.

But based on the article, I get these brackets:

Worcester, Mass. Regional
1. North Dakota (1)
2. Boston College (6)
3. Arizona State (10)
4. AIC (16)

Loveland, Colo. Regional
1. Minnesota Duluth (4)
2. Denver (5)
3. UMass Lowell (11) or Northeastern (12)
4. Ohio State (13)

Allentown, Pa. Regional
1. Minnesota State (2)
2. Penn State (8)
3. UMass Lowell (11) or Northeastern (12)
4. Providence (15)

Albany, N.Y. Regional
1. Cornell (3)
2. UMass (7)
3. Clarkson (9).
4. Maine (14)

Albany, N.Y. Regional
1. Cornell (3)
2. UMass (7)
3. Clarkson (9).
4. Maine (14)

That regional is fascinating.

Interesting... At this point it is down to a 59-team race. Even though their PWR is higher than both Princeton and St. Lawrence... Vermont has 0.0% chance to make the NC$$ tournament.

Trotsky

Albany, N.Y. Regional
1. Cornell (3)
2. UMass (7)
3. Clarkson (9).
4. Maine (14)

That regional is fascinating.

It is, isn't it? I did my own bracketology a few days ago, and put Az. State in Albany and Clarkson in Worcester, but that was simply because I didn't want to see Cornell and Clarkson match up a potential 4th time in the regionals.

KenP
Interesting... At this point it is down to a 59-team race. Even though their PWR is higher than both Princeton and St. Lawrence... Vermont has 0.0% chance to make the NC$$ tournament.

Merrimack's really close, too.

According to this, 20 of those 59 can only make it now by winning their auto bid, including half the ECAC.

Jeff Hopkins '82

Trotsky

Albany, N.Y. Regional
1. Cornell (3)
2. UMass (7)
3. Clarkson (9).
4. Maine (14)

That regional is fascinating.

It is, isn't it? I did my own bracketology a few days ago, and put Az. State in Albany and Clarkson in Worcester, but that was simply because I didn't want to see Cornell and Clarkson match up a potential 4th time in the regionals.

I was thinking it would be wild to see us play Clarkson 3 times in 30 days: Feb 29 in Ithaca for the ECAC RS title, March 21 in Lake Placid for the ECAC title, and March 29 in Albany for advance to the Frozen Four.

Trotsky

Jeff Hopkins '82

Trotsky

Albany, N.Y. Regional
1. Cornell (3)
2. UMass (7)
3. Clarkson (9).
4. Maine (14)

That regional is fascinating.

It is, isn't it? I did my own bracketology a few days ago, and put Az. State in Albany and Clarkson in Worcester, but that was simply because I didn't want to see Cornell and Clarkson match up a potential 4th time in the regionals.

I was thinking it would be wild to see us play Clarkson 3 times in 30 days: Feb 29 in Ithaca for the ECAC RS title, March 21 in Lake Placid for the ECAC title, and March 29 in Albany for advance to the Frozen Four.

I'd rather see us meet up the fourth time in Detroit, not Albany. And with Clarkson in Worcester with NoDak as #1, and us as #3, that meeting would be the finals.

The Pairwise Probability Matrix, which I believe "accounts for" uncertainty the same way playoffstatus.com does, gives Cornell (currently in 3rd place in the Pairwise/KRACH) a 67% chance of finishing with exactly the 3-seed. It gives NoDak (currently first) an 87% likelihood of finishing with the 1-seed. It gives Minn State (currently second) 75% odds of finishing with the 2-seed. Each of these teams still has ~12 games left before seeding. Sounds legit?

BearLover
The Pairwise Probability Matrix, which I believe "accounts for" uncertainty the same way playoffstatus.com does, gives Cornell (currently in 3rd place in the Pairwise/KRACH) a 67% chance of finishing with exactly the 3-seed. It gives NoDak (currently first) an 87% likelihood of finishing with the 1-seed. It gives Minn State (currently second) 75% odds of finishing with the 2-seed. Each of these teams still has ~12 games left before seeding. Sounds legit?

We're not accounting for any "uncertainty" at all - yet.

One thing that does it make it legit - yeah - is the gap in RPI between all of these teams. There is a larger gap between 1 and 2 - 2 to 3 - and, in particular 3 to 4 - than there is most of groups of 5 teams. In particular, there's a .0231 gap from 3 to 4. By comparison - No. 4 and 10 are closer than that gap.

adamw

BearLover
The Pairwise Probability Matrix, which I believe "accounts for" uncertainty the same way playoffstatus.com does, gives Cornell (currently in 3rd place in the Pairwise/KRACH) a 67% chance of finishing with exactly the 3-seed. It gives NoDak (currently first) an 87% likelihood of finishing with the 1-seed. It gives Minn State (currently second) 75% odds of finishing with the 2-seed. Each of these teams still has ~12 games left before seeding. Sounds legit?

We're not accounting for any "uncertainty" at all - yet.

One thing that does it make it legit - yeah - is the gap in RPI between all of these teams. There is a larger gap between 1 and 2 - 2 to 3 - and, in particular 3 to 4 - than there is most of groups of 5 teams. In particular, there's a .0231 gap from 3 to 4. By comparison - No. 4 and 10 are closer than that gap.

I may be using the wrong terminology, but what do you mean you are not accounting for uncertainty? And would you put your money where your mouth is and assert that if this season were to be replicated from this point forward one million times, in 2/3 of those scenarios Cornell would finish with exactly the 3-seed? That Minn St would finish 3/4 of the time with exactly the 2-seed? That NoDak would finish 7/8 of the time with the 1-seed? Do you also believe Cornell is almost three times as likely to win the ECAC championship as Clarkson, and more likely to win it than the rest of the ECAC combined? I believe these numbers are quite a bit off, and a few years ago someone on here ran a regression [correct terminology?] showing that the tails of these models are off--the chances of a top team beating a bottom team are overstated by the model, which over the course of a lengthy stretch (in this case, ~12 remaining games) leads to significantly underrating volatility.

BearLover
The Pairwise Probability Matrix, which I believe "accounts for" uncertainty the same way playoffstatus.com does, gives Cornell (currently in 3rd place in the Pairwise/KRACH) a 67% chance of finishing with exactly the 3-seed. It gives NoDak (currently first) an 87% likelihood of finishing with the 1-seed. It gives Minn State (currently second) 75% odds of finishing with the 2-seed. Each of these teams still has ~12 games left before seeding. Sounds legit?

I've long had the same complaints about these models that you routinely bring up, and I've found it helps me to think of this less as a prediction of real probabilities and more as a mechanism of demonstrating the likely finishing positions assuming the rest of the game results follow from the existing game results. Honestly, there's no real reason to suspect that the high percentages indicate anything wrong with the model, at least not based on what it's effectively doing. At the end of the day, these monte carlo simulations based on KRACH (which is itself based solely on record) are incredibly information-poor and we have to account for that in our interpretation.

I ended up subscribing to The Athletic last year and I found their NHL playoff possibility models very interesting because they have access to a lot more team and player-level data. Of course, those richer models didn't come out looking very good last season what with Tampa Bay getting bounced in the first round and St. Louis winning it all. Even so, if I end up becoming an unemployed hobbyist for a while I'd love to try to get something similar for NCAA hockey, although the much smaller sample of games will make it super noisy.

I found the old thread, which includes jfeath's incredibly helpful analysis:

[Ugh sorry, having problems posting the link on my phone, but it's post #12 or so on the thread titled "2018 ECAC Permutations"]

all i know its a lot more fun being 6 games left wondering how Cornell can screw it up than it is 6 games left hoping other teams screw it up.

Amen, brother.

upprdeck
all i know its a lot more fun being 6 games left wondering how Cornell can screw it up than it is 6 games left hoping other teams screw it up.

And a lot more fun than wondering how Schafer talks to his team.

Also Adam's stats are probably better than any for the above.

adamw
Well if Jim read my article (I'm sure he was one of the ones rolling his eyes) - he'd know that those brackets are neither "projections" nor "predictions" at all. It bothers the ever loving hell out of me when they're called that.

Ok, but to be *really* pedantic, I wouldn’t necessarily call a KRACH-based Monte Carlo simulation a “prediction” either. The future results are based exactly on prior performance, and each team performs exactly that well through the remainder of the season - there’s no new information being added. Therefore, I am a little skeptical that it is much/any more predictive than a strict “if the season ended today” approach, because even in the Monte Carlo approach, the addition of new information ended today, too.

This is especially true since you’re boiling it down to a single predicted bracket (which is obviously not what the real bracket will be, no matter the methodology). Looking at the histograms of the 20,000 final PWR ranks for each team would be more interesting/informative for me than trying to “predict” an exact bracket.

BearLover
I found the old thread, which includes jfeath's incredibly helpful analysis:

[Ugh sorry, having problems posting the link on my phone, but it's post #12 or so on the thread titled "2018 ECAC Permutations"]

The thread is here [elf.elynah.com]

Robb

adamw
Well if Jim read my article (I'm sure he was one of the ones rolling his eyes) - he'd know that those brackets are neither "projections" nor "predictions" at all. It bothers the ever loving hell out of me when they're called that.

Ok, but to be *really* pedantic, I wouldn’t necessarily call a KRACH-based Monte Carlo simulation a “prediction” either. The future results are based exactly on prior performance, and each team performs exactly that well through the remainder of the season - there’s no new information being added. Therefore, I am a little skeptical that it is much/any more predictive than a strict “if the season ended today” approach, because even in the Monte Carlo approach, the addition of new information ended today, too.

This is especially true since you’re boiling it down to a single predicted bracket (which is obviously not what the real bracket will be, no matter the methodology). Looking at the histograms of the 20,000 final PWR ranks for each team would be more interesting/informative for me than trying to “predict” an exact bracket.

Fair enough of course - but at least it's "predicting" future games and then factoring that into a creating a final bracket. The others do nothing of the sort and are thus completely useless.

BearLover
I may be using the wrong terminology, but what do you mean you are not accounting for uncertainty? And would you put your money where your mouth is and assert that if this season were to be replicated from this point forward one million times, in 2/3 of those scenarios Cornell would finish with exactly the 3-seed? That Minn St would finish 3/4 of the time with exactly the 2-seed? That NoDak would finish 7/8 of the time with the 1-seed? Do you also believe Cornell is almost three times as likely to win the ECAC championship as Clarkson, and more likely to win it than the rest of the ECAC combined? I believe these numbers are quite a bit off, and a few years ago someone on here ran a regression [correct terminology?] showing that the tails of these models are off--the chances of a top team beating a bottom team are overstated by the model, which over the course of a lengthy stretch (in this case, ~12 remaining games) leads to significantly underrating volatility.

"uncertainty" in the mathematical sense, as I understand it, takes into consideration that only using relatively small sample sizes of past results, is too "precise" - so to speak - and therefore pulls things closer to the mean. This will account for the high odds you're talking about, and addresses your concerns - if we can get around to implementing it. I'm not the expert on this, however. The same dumb conversation from past years spurred us - i.e. John Whelan - to come up with an algorithm that adds uncertainty to the mix.

I do wonder - pray tell - how I'm supposed to put my money where my mouth is in regards to the season being played out 1,000,000 times. How are we supposed to test this hypothesis so that I can wager with you?

As it stands, we play out the season 20,000 times - which is pretty stable. Doing it 1,000,000 times isn't going to change things. Cornell will still be a 3 seed just about the same amount of times. I really don't know how else you'd like me to "prove" anything.

adamw

BearLover
I may be using the wrong terminology, but what do you mean you are not accounting for uncertainty? And would you put your money where your mouth is and assert that if this season were to be replicated from this point forward one million times, in 2/3 of those scenarios Cornell would finish with exactly the 3-seed? That Minn St would finish 3/4 of the time with exactly the 2-seed? That NoDak would finish 7/8 of the time with the 1-seed? Do you also believe Cornell is almost three times as likely to win the ECAC championship as Clarkson, and more likely to win it than the rest of the ECAC combined? I believe these numbers are quite a bit off, and a few years ago someone on here ran a regression [correct terminology?] showing that the tails of these models are off--the chances of a top team beating a bottom team are overstated by the model, which over the course of a lengthy stretch (in this case, ~12 remaining games) leads to significantly underrating volatility.

"uncertainty" in the mathematical sense, as I understand it, takes into consideration that only using relatively small sample sizes of past results, is too "precise" - so to speak - and therefore pulls things closer to the mean. This will account for the high odds you're talking about, and addresses your concerns - if we can get around to implementing it. I'm not the expert on this, however. The same dumb conversation from past years spurred us - i.e. John Whelan - to come up with an algorithm that adds uncertainty to the mix.

As others have said above, the model assumes that every team will perform as well as they have thus far--the third-best team will continue to perform as the third-best team, the second-best team will continue to perform as the second-best, etc. In reality, there is an extremely wide range of outcomes for how well a team can perform over its remaining games.

(Though, @Robb and @Tom Lento, why wouldn't each team have a 100% chance of finishing in exactly its current spot if what you are saying is true? And then what would be the point of running more than one simulation? I had understood that the possibility of the third-best team not performing as the third-best team going forward *is* built into the model, it just isn't weighted heavily enough.)

adamw
I do wonder - pray tell - how I'm supposed to put my money where my mouth is in regards to the season being played out 1,000,000 times. How are we supposed to test this hypothesis so that I can wager with you?

I wager $50 that Cornell finishes somewhere other than exactly third in NCAA seeding. You wager $100 that they finish exactly third. Would you make that bet?

adamw
As it stands, we play out the season 20,000 times - which is pretty stable. Doing it 1,000,000 times isn't going to change things. Cornell will still be a 3 seed just about the same amount of times. I really don't know how else you'd like me to "prove" anything.

I did not mean to suggest 1,000,000 simulations would yield a different result than 20,000. I just used one million as a random large number. 20,000 will do just fine.

BearLover
(Though, @Robb and @Tom Lento, why wouldn't each team have a 100% chance of finishing in exactly its current spot if what you are saying is true? And then what would be the point of running more than one simulation? I had understood that the possibility of the third-best team not performing as the third-best team going forward *is* built into the model, it just isn't weighted heavily enough.

Because according to KRACH, even the third-best team has a non-zero probability of losing to the worst team. That’s why there would be a range of final PWR ratings for each team - in some of the trials, Cornell will be unlucky and lose a bunch of games to worse teams, and in some trials they won’t. That’s where the histogram comes in - so you can see the range of possibilities and get an estimate of how likely each of those possibilities appears to be (again, assuming that each team really is exactly as good as it’s current KRACH rating).

Maybe it really is “most likely” that Cornell winds up 3rd, but if the range of possibilities is that we could end up anywhere from 1st to 20th, then 3rd might only happen in 15% of the trials, so then you’d get a sense that it’s far more likely that Cornell finishes worse than 3rd even though 3rd is the most likely individual result.

Cornell's KRACH SOS is 30; Other than Clarkson (42, also ECAC) you have to go down to #17 Lowell to find a weaker SOS. What this means is that we are on a steep slope and need to keep our footing. One "bad" loss or tie will drop us more than a bad loss by North Dakota or Minnesota State etc. Our percentages in these simulations will hold steady with wins but can change very quickly with a single loss.

KenP
What this means is that we are on a steep slope and need to keep our footing.

Perfect analogy. Very nice!

Robb
That’s why there would be a range of final PWR ratings for each team - in some of the trials, Cornell will be unlucky and lose a bunch of games to worse teams, and in some trials they won’t. That’s where the histogram comes in - so you can see the range of possibilities and get an estimate of how likely each of those possibilities appears to be (again, assuming that each team really is exactly as good as it’s current KRACH rating).

Maybe it really is “most likely” that Cornell winds up 3rd, but if the range of possibilities is that we could end up anywhere from 1st to 20th, then 3rd might only happen in 15% of the trials, so then you’d get a sense that it’s far more likely that Cornell finishes worse than 3rd even though 3rd is the most likely individual result.

The Matrix shows a possibility of Cornell finishing anywhere from 1 to 13, currently. I'm really bad with graphical thingies - so, thus, the Matrix, as opposed to a histogram. No difference really.

[www.collegehockeynews.com]

As I said above - the gaps in RPI are significant from 2 to 3 and, moreso, 3 to 4. That is one reason Cornell is pretty stable in that spot. Doesn't mean it will definitely happen.

But for the umpteenth straight year, BearLover is focusing on the wrong thing. The simulation is what it is. Obviously it only goes by past results. It can't do anything else. The gripe you have is with how KRACH works, not how the simulation works. Ratings are based on relatively small samples of past results, and can't possibly take into account many things. Therefore, adding an "uncertainty" node into the algorithm will smooth things out a bit -- though it's a somewhat generic addition, and isn't based on any sort of analysis of team strength, injuries, or whatever.

Getting hung up on trashing the simulations really misses the point. Though, as I've said, we're definitely trying to "improve" it.

If someone could create a better simulation, they would be getting rich from it and not posting to this board I suspect.

Also - to further answer the question which I thought was obvious, but I guess not ... things aren't 100%, because every game is "played" using KRACH as the weighted probability of a team winning that game. So, Team A has 600 KRACH ... Team B has 300 KRACH ... Team A has a 2/3 chance of winning that game. Play out every game for the rest of the season this way ... 20,000 times ... and you get your simulation.

The issue, then, is Cornell's chances of winning a game being overweighted if you think the KRACH differences aren't realistic.

But taking offense to the idea that the top 3 ends up exactly how it is now, without really understanding why the simulations come out that way, is silly.

Adam, I have a suggestion. Cornell has guaranteed itself an ECAC home playoff series, i.e. our worst-case ECAC rank is 8. Can you do something similar for NCAA participation? Specifically:

Create a worst-case simulation for each team. Set their games to losses, rerun the Monte Carlo simulation for the rest of the field, and grab the lowest PWR from the modified simulation. Add that as a

Everyone likes to know when their team officially "clinches" a playoff berth... this approach would give fans that answer.

P.S. other comments / suggestions:
* check your number formatting. Some values round up to "1.0%" while others round down to "1%"
* repeat table header at the bottom.
* not sure if you can have a slider bar at both the top and bottom but that would be nice too
* consider similar best case scenarios. playoffstatus.com has that which is why i saw Vermont is officially out of the race.
* for the best case and worse data... either show as additional columns or use that information and enter "x" for impossible year-end rankings. ("Impossible" may not be the right word given this is only 20,000 simulations.. but hopefully you and your readers will get the point.)

adamw

Robb
That’s why there would be a range of final PWR ratings for each team - in some of the trials, Cornell will be unlucky and lose a bunch of games to worse teams, and in some trials they won’t. That’s where the histogram comes in - so you can see the range of possibilities and get an estimate of how likely each of those possibilities appears to be (again, assuming that each team really is exactly as good as it’s current KRACH rating).

Maybe it really is “most likely” that Cornell winds up 3rd, but if the range of possibilities is that we could end up anywhere from 1st to 20th, then 3rd might only happen in 15% of the trials, so then you’d get a sense that it’s far more likely that Cornell finishes worse than 3rd even though 3rd is the most likely individual result.

The Matrix shows a possibility of Cornell finishing anywhere from 1 to 13, currently. I'm really bad with graphical thingies - so, thus, the Matrix, as opposed to a histogram. No difference really.

[www.collegehockeynews.com]

As I said above - the gaps in RPI are significant from 2 to 3 and, moreso, 3 to 4. That is one reason Cornell is pretty stable in that spot. Doesn't mean it will definitely happen.

But for the umpteenth straight year, BearLover is focusing on the wrong thing. The simulation is what it is. Obviously it only goes by past results. It can't do anything else. The gripe you have is with how KRACH works, not how the simulation works. Ratings are based on relatively small samples of past results, and can't possibly take into account many things. Therefore, adding an "uncertainty" node into the algorithm will smooth things out a bit -- though it's a somewhat generic addition, and isn't based on any sort of analysis of team strength, injuries, or whatever.

Getting hung up on trashing the simulations really misses the point. Though, as I've said, we're definitely trying to "improve" it.

Sorry, I don't agree. KRACH is not meant to be predictive. Therefore, a simulation based entirely on KRACH to predict future outcomes is flawed. The simulation is called the "Pairwise Probability Matrix" and assigns a percentage to all possible outcomes. To a casual viewer, like me, there is no note or disclaimer anywhere on the page that suggests the model is NOT predictive. In fact, below the chart there is a line that reads: "these numbers accurately reflect each team's possible finish to a high rate of precision."

I do not believe almost anyone reading the matrix understands it is limited to extrapolating existing KRACH over the rest of the season, or what this reliance on KRACH entails. I have seen dozens of posts on this forum over the past several years that look to the percentages as good predictive data. I don't think the simulation provides good predictive data.

I don't mean to sound overly harsh. CHN is one of my most-visited websites and I'd love to see the simulation improved. But in its current form, the simulation is not particularly helpful and I'd argue it is actively misleading.

BearLover

As others have said above, the model assumes that every team will perform as well as they have thus far--the third-best team will continue to perform as the third-best team, the second-best team will continue to perform as the second-best, etc. In reality, there is an extremely wide range of outcomes for how well a team can perform over its remaining games.

There really isn't much else to be done, though. Models as to what's going to happen in the future rely on what's happened in the past.

Could things be more complex? Sure. You could use goal differentials or advanced possession/shot metrics to estimate team quality. You could also weight for recency (Cornell's been weaker over the last month or so than the rest of the season, so maybe we're "worse" than our total record). But that's all more complicated and not necessarily more accurate.

How do you go about introducing "uncertainty" other than taking an existing model and blurring the results by some factor?

BearLover

adamw

Robb
That’s why there would be a range of final PWR ratings for each team - in some of the trials, Cornell will be unlucky and lose a bunch of games to worse teams, and in some trials they won’t. That’s where the histogram comes in - so you can see the range of possibilities and get an estimate of how likely each of those possibilities appears to be (again, assuming that each team really is exactly as good as it’s current KRACH rating).

Maybe it really is “most likely” that Cornell winds up 3rd, but if the range of possibilities is that we could end up anywhere from 1st to 20th, then 3rd might only happen in 15% of the trials, so then you’d get a sense that it’s far more likely that Cornell finishes worse than 3rd even though 3rd is the most likely individual result.

The Matrix shows a possibility of Cornell finishing anywhere from 1 to 13, currently. I'm really bad with graphical thingies - so, thus, the Matrix, as opposed to a histogram. No difference really.

[www.collegehockeynews.com]

As I said above - the gaps in RPI are significant from 2 to 3 and, moreso, 3 to 4. That is one reason Cornell is pretty stable in that spot. Doesn't mean it will definitely happen.

But for the umpteenth straight year, BearLover is focusing on the wrong thing. The simulation is what it is. Obviously it only goes by past results. It can't do anything else. The gripe you have is with how KRACH works, not how the simulation works. Ratings are based on relatively small samples of past results, and can't possibly take into account many things. Therefore, adding an "uncertainty" node into the algorithm will smooth things out a bit -- though it's a somewhat generic addition, and isn't based on any sort of analysis of team strength, injuries, or whatever.

Getting hung up on trashing the simulations really misses the point. Though, as I've said, we're definitely trying to "improve" it.

Sorry, I don't agree. KRACH is not meant to be predictive. Therefore, a simulation based entirely on KRACH to predict future outcomes is flawed. The simulation is called the "Pairwise Probability Matrix" and assigns a percentage to all possible outcomes. To a casual viewer, like me, there is no note or disclaimer anywhere on the page that suggests the model is NOT predictive. In fact, below the chart there is a line that reads: "these numbers accurately reflect each team's possible finish to a high rate of precision."

I do not believe almost anyone reading the matrix understands it is limited to extrapolating existing KRACH over the rest of the season, or what this reliance on KRACH entails. I have seen dozens of posts on this forum over the past several years that look to the percentages as good predictive data. I don't think the simulation provides good predictive data.

I don't mean to sound overly harsh. CHN is one of my most-visited websites and I'd love to see the simulation improved. But in its current form, the simulation is not particularly helpful and I'd argue it is actively misleading.

KRACH has two main assumptions: (a) all games and results are reflective of overall quality of each team, and (b) that quality is consistent through the entire season including future games. You may wish for a system that incorporates more data to address those assumptions... but given those two statements KRACH absolutely is meant to be predictive.

KenP

BearLover

adamw

Robb
That’s why there would be a range of final PWR ratings for each team - in some of the trials, Cornell will be unlucky and lose a bunch of games to worse teams, and in some trials they won’t. That’s where the histogram comes in - so you can see the range of possibilities and get an estimate of how likely each of those possibilities appears to be (again, assuming that each team really is exactly as good as it’s current KRACH rating).

Maybe it really is “most likely” that Cornell winds up 3rd, but if the range of possibilities is that we could end up anywhere from 1st to 20th, then 3rd might only happen in 15% of the trials, so then you’d get a sense that it’s far more likely that Cornell finishes worse than 3rd even though 3rd is the most likely individual result.

The Matrix shows a possibility of Cornell finishing anywhere from 1 to 13, currently. I'm really bad with graphical thingies - so, thus, the Matrix, as opposed to a histogram. No difference really.

[www.collegehockeynews.com]

As I said above - the gaps in RPI are significant from 2 to 3 and, moreso, 3 to 4. That is one reason Cornell is pretty stable in that spot. Doesn't mean it will definitely happen.

But for the umpteenth straight year, BearLover is focusing on the wrong thing. The simulation is what it is. Obviously it only goes by past results. It can't do anything else. The gripe you have is with how KRACH works, not how the simulation works. Ratings are based on relatively small samples of past results, and can't possibly take into account many things. Therefore, adding an "uncertainty" node into the algorithm will smooth things out a bit -- though it's a somewhat generic addition, and isn't based on any sort of analysis of team strength, injuries, or whatever.

Getting hung up on trashing the simulations really misses the point. Though, as I've said, we're definitely trying to "improve" it.

Sorry, I don't agree. KRACH is not meant to be predictive. Therefore, a simulation based entirely on KRACH to predict future outcomes is flawed. The simulation is called the "Pairwise Probability Matrix" and assigns a percentage to all possible outcomes. To a casual viewer, like me, there is no note or disclaimer anywhere on the page that suggests the model is NOT predictive. In fact, below the chart there is a line that reads: "these numbers accurately reflect each team's possible finish to a high rate of precision."

I do not believe almost anyone reading the matrix understands it is limited to extrapolating existing KRACH over the rest of the season, or what this reliance on KRACH entails. I have seen dozens of posts on this forum over the past several years that look to the percentages as good predictive data. I don't think the simulation provides good predictive data.

I don't mean to sound overly harsh. CHN is one of my most-visited websites and I'd love to see the simulation improved. But in its current form, the simulation is not particularly helpful and I'd argue it is actively misleading.

KRACH has two main assumptions: (a) all games and results are reflective of overall quality of each team, and (b) that quality is consistent through the entire season including future games. You may wish for a system that incorporates more data to address those assumptions... but given those two statements KRACH absolutely is meant to be predictive.

Okay, pardon me for my poor verbiage. Practically speaking though, KRACH is meant to be used as a way of ranking/seeding teams, which depends entirely on past performance. It does a terrible job of predicting future outcomes (at least over a sample as small as 25 or so games).

To me Bracketology is just something fun to check out this time of year for amusement, nothing more than that.

Too many people seem to put way too much stock in this stuff (Adam excluded because it's what he does for a living--or at least part of a living).

scoop85
To me Bracketology is just something fun to check out this time of year for amusement, nothing more than that.

Too many people seem to put way too much stock in this stuff (Adam excluded because it's what he does for a living--or at least part of a living).

yeah i look at bracketology and say "neat. that would be ___ for us."

BearLover
Sorry, I don't agree. KRACH is not meant to be predictive. Therefore, a simulation based entirely on KRACH to predict future outcomes is flawed. The simulation is called the "Pairwise Probability Matrix" and assigns a percentage to all possible outcomes. To a casual viewer, like me, there is no note or disclaimer anywhere on the page that suggests the model is NOT predictive. In fact, below the chart there is a line that reads: "these numbers accurately reflect each team's possible finish to a high rate of precision."

I do not believe almost anyone reading the matrix understands it is limited to extrapolating existing KRACH over the rest of the season, or what this reliance on KRACH entails. I have seen dozens of posts on this forum over the past several years that look to the percentages as good predictive data. I don't think the simulation provides good predictive data.

I don't mean to sound overly harsh. CHN is one of my most-visited websites and I'd love to see the simulation improved. But in its current form, the simulation is not particularly helpful and I'd argue it is actively misleading.

I think you get way too hung up on this. Most people do, in fact, know this. Since most people probably know that there's nothing that can be done to entirely accurately predict the future. As someone else pointed out, it IS predictive - just not perfectly so - nothing is. The only thing anyone can do is to try to get better and better data to feed into the machine. There is literally no other way to predict the future any better.

I just don't know what you're looking for, or what you expect to find with any model that predicts future results. My guess is, you probably don't really know. I think you are getting hung up, and lack an understanding over what is being done, or can be done.

If you have data that's better than KRACH to rely upon - let me know.

Dafatone
Could things be more complex? Sure. You could use goal differentials or advanced possession/shot metrics to estimate team quality. You could also weight for recency (Cornell's been weaker over the last month or so than the rest of the season, so maybe we're "worse" than our total record). But that's all more complicated and not necessarily more accurate.

I do actually want to add in a "recency bias" - working on it. But, like you say, that's a subjective decision being introduced into the model, and there's no way of knowing that it's more or less accurate. Anything that tries to predict the future is going to be incomplete, obviously. Until future species master quantum mechanics.

adamw

Dafatone
Could things be more complex? Sure. You could use goal differentials or advanced possession/shot metrics to estimate team quality. You could also weight for recency (Cornell's been weaker over the last month or so than the rest of the season, so maybe we're "worse" than our total record). But that's all more complicated and not necessarily more accurate.

I do actually want to add in a "recency bias" - working on it. But, like you say, that's a subjective decision being introduced into the model, and there's no way of knowing that it's more or less accurate. Anything that tries to predict the future is going to be incomplete, obviously. Until future species master quantum mechanics.

Two thoughts: (1) add discrete events to split up a season, e.g. "New BU Goalie" or "Player Injured". Somehow identify the difference in KRACH pre- and post-event? (2) I think there are statistical tests to look at the data and determine if more than one regression line is appropriate. Paired t-test? You'd have to ask an actual statistician. But potentially you could pinpoint those pivot moments and identify the "recent" bias from the data.

BearLover
Okay, pardon me for my poor verbiage. Practically speaking though, KRACH is meant to be used as a way of ranking/seeding teams, which depends entirely on past performance. It does a terrible job of predicting future outcomes (at least over a sample as small as 25 or so games).

It's not that KRACH does a poor job .... EVERYTHING does a poor job predicting the future. KRACH is the best tool we have. If you had anything better, you'd win a lot of money in Vegas.

KenP
Adam, I have a suggestion. Cornell has guaranteed itself an ECAC home playoff series, i.e. our worst-case ECAC rank is 8. Can you do something similar for NCAA participation? Specifically:

Create a worst-case simulation for each team. Set their games to losses, rerun the Monte Carlo simulation for the rest of the field, and grab the lowest PWR from the modified simulation. Add that as a

Everyone likes to know when their team officially "clinches" a playoff berth... this approach would give fans that answer.

P.S. other comments / suggestions:
* check your number formatting. Some values round up to "1.0%" while others round down to "1%"
* repeat table header at the bottom.
* not sure if you can have a slider bar at both the top and bottom but that would be nice too
* consider similar best case scenarios. playoffstatus.com has that which is why i saw Vermont is officially out of the race.
* for the best case and worse data... either show as additional columns or use that information and enter "x" for impossible year-end rankings. ("Impossible" may not be the right word given this is only 20,000 simulations.. but hopefully you and your readers will get the point.)

All good suggestions. I'm not minimizing them. Just - time is an issue.

BearLover

adamw

Robb
That’s why there would be a range of final PWR ratings for each team - in some of the trials, Cornell will be unlucky and lose a bunch of games to worse teams, and in some trials they won’t. That’s where the histogram comes in - so you can see the range of possibilities and get an estimate of how likely each of those possibilities appears to be (again, assuming that each team really is exactly as good as it’s current KRACH rating).

Maybe it really is “most likely” that Cornell winds up 3rd, but if the range of possibilities is that we could end up anywhere from 1st to 20th, then 3rd might only happen in 15% of the trials, so then you’d get a sense that it’s far more likely that Cornell finishes worse than 3rd even though 3rd is the most likely individual result.

The Matrix shows a possibility of Cornell finishing anywhere from 1 to 13, currently. I'm really bad with graphical thingies - so, thus, the Matrix, as opposed to a histogram. No difference really.

[www.collegehockeynews.com]

As I said above - the gaps in RPI are significant from 2 to 3 and, moreso, 3 to 4. That is one reason Cornell is pretty stable in that spot. Doesn't mean it will definitely happen.

But for the umpteenth straight year, BearLover is focusing on the wrong thing. The simulation is what it is. Obviously it only goes by past results. It can't do anything else. The gripe you have is with how KRACH works, not how the simulation works. Ratings are based on relatively small samples of past results, and can't possibly take into account many things. Therefore, adding an "uncertainty" node into the algorithm will smooth things out a bit -- though it's a somewhat generic addition, and isn't based on any sort of analysis of team strength, injuries, or whatever.

Getting hung up on trashing the simulations really misses the point. Though, as I've said, we're definitely trying to "improve" it.

Sorry, I don't agree....

Just "add" nauseam and repeat.

Here's an example of the issue with using KRACH to predict final pairwise:

Cornell (KRACH Rating: 526) is playing St Lawrence (KRACH Rating: 11) in a few weeks. My understanding is that the ratings can be used to come up with a pseudo-record between the two teams (Cornell with 526 wins, St Lawrence with 11). The Monte Carlo simulation uses this record to determine how often Cornell wins. In this case, the model predicts they win 98% of the time.

jfeath's regression analysis from 2 years ago shows that a team with a KRACH winning percentage of 100% theoretically wins about 83.4% of the time, 14.5% lower than what KRACH states for the Cornell-St Lawrence game.

I think it makes sense for 83.4% to be an upper bound on winning percentage. Any goalie can have an incredible/incredibly bad day. Also, the fact that there are ties in hockey means that the winning percentage should be more weighted to 50% than a sport where you can't have ties.

Ideally, jfeath's regression analysis would be an in-between step in the Pairwise probability matrix to convert the KRACH winning percentages (which show what happened to date) to predictive winning percentages.

marty

BearLover

adamw

Robb
That’s why there would be a range of final PWR ratings for each team - in some of the trials, Cornell will be unlucky and lose a bunch of games to worse teams, and in some trials they won’t. That’s where the histogram comes in - so you can see the range of possibilities and get an estimate of how likely each of those possibilities appears to be (again, assuming that each team really is exactly as good as it’s current KRACH rating).

Maybe it really is “most likely” that Cornell winds up 3rd, but if the range of possibilities is that we could end up anywhere from 1st to 20th, then 3rd might only happen in 15% of the trials, so then you’d get a sense that it’s far more likely that Cornell finishes worse than 3rd even though 3rd is the most likely individual result.

The Matrix shows a possibility of Cornell finishing anywhere from 1 to 13, currently. I'm really bad with graphical thingies - so, thus, the Matrix, as opposed to a histogram. No difference really.

[www.collegehockeynews.com]

As I said above - the gaps in RPI are significant from 2 to 3 and, moreso, 3 to 4. That is one reason Cornell is pretty stable in that spot. Doesn't mean it will definitely happen.

But for the umpteenth straight year, BearLover is focusing on the wrong thing. The simulation is what it is. Obviously it only goes by past results. It can't do anything else. The gripe you have is with how KRACH works, not how the simulation works. Ratings are based on relatively small samples of past results, and can't possibly take into account many things. Therefore, adding an "uncertainty" node into the algorithm will smooth things out a bit -- though it's a somewhat generic addition, and isn't based on any sort of analysis of team strength, injuries, or whatever.

Getting hung up on trashing the simulations really misses the point. Though, as I've said, we're definitely trying to "improve" it.

Sorry, I don't agree....

Just "add" nauseam and repeat.

marty

BearLover

adamw

Robb
That’s why there would be a range of final PWR ratings for each team - in some of the trials, Cornell will be unlucky and lose a bunch of games to worse teams, and in some trials they won’t. That’s where the histogram comes in - so you can see the range of possibilities and get an estimate of how likely each of those possibilities appears to be (again, assuming that each team really is exactly as good as it’s current KRACH rating).

Maybe it really is “most likely” that Cornell winds up 3rd, but if the range of possibilities is that we could end up anywhere from 1st to 20th, then 3rd might only happen in 15% of the trials, so then you’d get a sense that it’s far more likely that Cornell finishes worse than 3rd even though 3rd is the most likely individual result.

The Matrix shows a possibility of Cornell finishing anywhere from 1 to 13, currently. I'm really bad with graphical thingies - so, thus, the Matrix, as opposed to a histogram. No difference really.

[www.collegehockeynews.com]

As I said above - the gaps in RPI are significant from 2 to 3 and, moreso, 3 to 4. That is one reason Cornell is pretty stable in that spot. Doesn't mean it will definitely happen.

But for the umpteenth straight year, BearLover is focusing on the wrong thing. The simulation is what it is. Obviously it only goes by past results. It can't do anything else. The gripe you have is with how KRACH works, not how the simulation works. Ratings are based on relatively small samples of past results, and can't possibly take into account many things. Therefore, adding an "uncertainty" node into the algorithm will smooth things out a bit -- though it's a somewhat generic addition, and isn't based on any sort of analysis of team strength, injuries, or whatever.

Getting hung up on trashing the simulations really misses the point. Though, as I've said, we're definitely trying to "improve" it.

Sorry, I don't agree....

Just "add" nauseam and repeat.

Most people enjoy a good magic show. Some people look at it and think 'It all is just fake' and dismiss it. They will never be satisfied until the magic is real, and critics of predictive tools will never be satisfied unless they are perfect. Magic will never be real, and predictive tools will never be perfect, and those types will live their lives unsatisfied.

KGR11
Here's an example of the issue with using KRACH to predict final pairwise:

Cornell (KRACH Rating: 526) is playing St Lawrence (KRACH Rating: 11) in a few weeks. My understanding is that the ratings can be used to come up with a pseudo-record between the two teams (Cornell with 526 wins, St Lawrence with 11). The Monte Carlo simulation uses this record to determine how often Cornell wins. In this case, the model predicts they win 98% of the time.

jfeath's regression analysis from 2 years ago shows that a team with a KRACH winning percentage of 100% theoretically wins about 83.4% of the time, 14.5% lower than what KRACH states for the Cornell-St Lawrence game.

I think it makes sense for 83.4% to be an upper bound on winning percentage. Any goalie can have an incredible/incredibly bad day. Also, the fact that there are ties in hockey means that the winning percentage should be more weighted to 50% than a sport where you can't have ties.

Ideally, jfeath's regression analysis would be an in-between step in the Pairwise probability matrix to convert the KRACH winning percentages (which show what happened to date) to predictive winning percentages.

1st - this kind of disparity is extreme. St. Lawrence is historically lousy right now. I'd venture to say, Cornell probably would win 98% of the time.

2nd - ties are taken into consideration with a hard-coded 19% chance - which is already acting as a smoothing mechanism. It's probably not accurate to hard-code that value for every matchup - but it does act as a "smoother," so to speak. This lowers Cornell's chance of a win to closer to the 83% you're referring to. Cornell is winning 98% of the 81% percent of non-ties. So, 80% - plus 9.5%'s worth of win value (i.e. points) via the tie.

adamw

KGR11
Here's an example of the issue with using KRACH to predict final pairwise:

Cornell (KRACH Rating: 526) is playing St Lawrence (KRACH Rating: 11) in a few weeks. My understanding is that the ratings can be used to come up with a pseudo-record between the two teams (Cornell with 526 wins, St Lawrence with 11). The Monte Carlo simulation uses this record to determine how often Cornell wins. In this case, the model predicts they win 98% of the time.

jfeath's regression analysis from 2 years ago shows that a team with a KRACH winning percentage of 100% theoretically wins about 83.4% of the time, 14.5% lower than what KRACH states for the Cornell-St Lawrence game.

I think it makes sense for 83.4% to be an upper bound on winning percentage. Any goalie can have an incredible/incredibly bad day. Also, the fact that there are ties in hockey means that the winning percentage should be more weighted to 50% than a sport where you can't have ties.

Ideally, jfeath's regression analysis would be an in-between step in the Pairwise probability matrix to convert the KRACH winning percentages (which show what happened to date) to predictive winning percentages.

1st - this kind of disparity is extreme. St. Lawrence is historically lousy right now. I'd venture to say, Cornell probably would win 98% of the time.

2nd - ties are taken into consideration with a hard-coded 19% chance - which is already acting as a smoothing mechanism. It's probably not accurate to hard-code that value for every matchup - but it does act as a "smoother," so to speak. This lowers Cornell's chance of a win to closer to the 83% you're referring to. Cornell is winning 98% of the 81% percent of non-ties. So, 80% - plus 9.5%'s worth of win value (i.e. points) via the tie.

Hard-coding ties like that is a huge deal. You effectively changed the maximum winning percentage from 100% to 90%. That makes the simulation framework way better than I thought, since your max winning percentage is closer to jfeath's maximum winning percentage of 83%. The next time you publish a primer for the probability matrix, it might be worth including this.

I pointed to an extreme-disparity game because those are the games where KRACH overestimates the favorite team's winning percentage (per jfeath's analysis). That analysis shows that KRACH lines up pretty well when the favorite has a projected winning percentage of 70% or less. Somewhat of a moot point given the 19% tie input.

I'm tempted to propose a 50-1 bet for the Cornell-SLU game. Best case scenario, Cornell wins and I lose $2. Worst case scenario, Cornell loses and I win $100. Just seems a bit sacrilege.

KGR11

adamw

KGR11
Here's an example of the issue with using KRACH to predict final pairwise:

Cornell (KRACH Rating: 526) is playing St Lawrence (KRACH Rating: 11) in a few weeks. My understanding is that the ratings can be used to come up with a pseudo-record between the two teams (Cornell with 526 wins, St Lawrence with 11). The Monte Carlo simulation uses this record to determine how often Cornell wins. In this case, the model predicts they win 98% of the time.

jfeath's regression analysis from 2 years ago shows that a team with a KRACH winning percentage of 100% theoretically wins about 83.4% of the time, 14.5% lower than what KRACH states for the Cornell-St Lawrence game.

I think it makes sense for 83.4% to be an upper bound on winning percentage. Any goalie can have an incredible/incredibly bad day. Also, the fact that there are ties in hockey means that the winning percentage should be more weighted to 50% than a sport where you can't have ties.

Ideally, jfeath's regression analysis would be an in-between step in the Pairwise probability matrix to convert the KRACH winning percentages (which show what happened to date) to predictive winning percentages.

1st - this kind of disparity is extreme. St. Lawrence is historically lousy right now. I'd venture to say, Cornell probably would win 98% of the time.

2nd - ties are taken into consideration with a hard-coded 19% chance - which is already acting as a smoothing mechanism. It's probably not accurate to hard-code that value for every matchup - but it does act as a "smoother," so to speak. This lowers Cornell's chance of a win to closer to the 83% you're referring to. Cornell is winning 98% of the 81% percent of non-ties. So, 80% - plus 9.5%'s worth of win value (i.e. points) via the tie.

Hard-coding ties like that is a huge deal. You effectively changed the maximum winning percentage from 100% to 90%. That makes the simulation framework way better than I thought, since your max winning percentage is closer to jfeath's maximum winning percentage of 83%. The next time you publish a primer for the probability matrix, it might be worth including this.

I pointed to an extreme-disparity game because those are the games where KRACH overestimates the favorite team's winning percentage (per jfeath's analysis). That analysis shows that KRACH lines up pretty well when the favorite has a projected winning percentage of 70% or less. Somewhat of a moot point given the 19% tie input.

I'm tempted to propose a 50-1 bet for the Cornell-SLU game. Best case scenario, Cornell wins and I lose $2. Worst case scenario, Cornell loses and I win $100. Just seems a bit sacrilege.

Betting to profit off our misery is the plot of “The Big Short,” so now I’m glad Topher is back tonight.

a couple interesting games this weekend.. Minn is now up to 16 and winning the B10 so that drops lowell out for now..

Minn-PSU this weekend..

PSU sweeps and that knocks Minn probably out of PWR contentio and takes them out of the B10 lead. PSU then done for the regular season

Minn Sweeps how far does PSU fall with only the playoffs left can they fall out of the top 15 with a bad playoff run.

minn then plays Mich, and with the 3 pt win rules and almost anyone can still win that B10.

Ice hockey is exclusively played on ice. Bracketology can be [and is] played on cell phones.

osorojo
Ice hockey is exclusively played on ice. Bracketology can be [and is] played on cell phones.

And trolling is played on computers and cell phones.

KGR11
Here's an example of the issue with using KRACH to predict final pairwise:

Cornell (KRACH Rating: 526) is playing St Lawrence (KRACH Rating: 11) in a few weeks. My understanding is that the ratings can be used to come up with a pseudo-record between the two teams (Cornell with 526 wins, St Lawrence with 11). The Monte Carlo simulation uses this record to determine how often Cornell wins. In this case, the model predicts they win 98% of the time.

jfeath's regression analysis from 2 years ago shows that a team with a KRACH winning percentage of 100% theoretically wins about 83.4% of the time, 14.5% lower than what KRACH states for the Cornell-St Lawrence game.

I think it makes sense for 83.4% to be an upper bound on winning percentage. Any goalie can have an incredible/incredibly bad day. Also, the fact that there are ties in hockey means that the winning percentage should be more weighted to 50% than a sport where you can't have ties.

Ideally, jfeath's regression analysis would be an in-between step in the Pairwise probability matrix to convert the KRACH winning percentages (which show what happened to date) to predictive winning percentages.

Even if the Bradley-Terry model is "correct" (whatever that means) there are two potential problems with using KRACH to predict the outcome of a mismatch:

One, KRACH is a maximum-likelihood estimate of a team's Bradley-Terry strength, whereas any estimate of the Bradley-Terry parameters based on a finite amount of data has some uncertainty in it. Ordinarily that's not such a big deal for assigning probabilities to the outcome of one game: the ratio of Cornell's strength to Clarkson's might be higher or lower than our best guess, but that means we might have over- or under-estimated it, and so the uncertainty probably washes out. But when the best guess is something like 50-to-1, that uncertainty can make a big difference in a more careful estimate of the probabilities. As an oversimplified version, suppose the "correct" odds might be 100-to-1 or 25-to-1, but we don't know which. Then the probability of an upset would be the average of 1.0% and 3.8%, which is 2.4% or about 40-to-1 against, not 50-to-1. I.e., the uncertainty naturally biases our expectation of the true probability away from the extremes, because having maybe somewhat overestimated the magnitude of the upset is a bigger effect than having maybe somewhat underestimated it. This is the issue we addressed in this paper, with a specific example discussed on this forum of the Cornell-Quinnipiac quarterfinal series from a few years back: [dx.doi.org] [arxiv.org]

Two, the maximum-likelihood analysis doesn't take into account any prior expectations about the possible discrepancies in teams' strengths, which means it's equivalent to making your prior information completely noninformative. This is a well-known effect which leads to undefeated teams having infinite KRACH ratings, and it's why Ken Butler put the "fictitious games" into KRACH for a while (the maximum likelihood estimates with fictitious games turn out to be the maximum a posteriori estimates with a particular prior distribution). But this is almost always a pretty small effect by this point in the season, so we don't generally worry about it. (BTW, the basic problem is older than hockey, since LaPlace was working on it circa 1800. What's your best guess probability that an event will happen, given that it's never happened in some number of chances? If you use the fraction of times you've already seen it as an estimate, you get zero, but you probably don't want to say it's literally impossible. The Bayes-Laplace rule of succession is basically what you get if you at two extra "fictitious trials", one where it occurred and one where it didn't.)

Ties are a huge pain in the ass, and complicate everything, so it's often easier to pretend they don't exist (or rather that past ties are half wins and half losses and future ties are something we don't talk about), especially since they become impossible once the playoffs start.

jtwcornell91

KGR11
Here's an example of the issue with using KRACH to predict final pairwise:

Cornell (KRACH Rating: 526) is playing St Lawrence (KRACH Rating: 11) in a few weeks. My understanding is that the ratings can be used to come up with a pseudo-record between the two teams (Cornell with 526 wins, St Lawrence with 11). The Monte Carlo simulation uses this record to determine how often Cornell wins. In this case, the model predicts they win 98% of the time.

jfeath's regression analysis from 2 years ago shows that a team with a KRACH winning percentage of 100% theoretically wins about 83.4% of the time, 14.5% lower than what KRACH states for the Cornell-St Lawrence game.

I think it makes sense for 83.4% to be an upper bound on winning percentage. Any goalie can have an incredible/incredibly bad day. Also, the fact that there are ties in hockey means that the winning percentage should be more weighted to 50% than a sport where you can't have ties.

Ideally, jfeath's regression analysis would be an in-between step in the Pairwise probability matrix to convert the KRACH winning percentages (which show what happened to date) to predictive winning percentages.

Even if the Bradley-Terry model is "correct" (whatever that means) there are two potential problems with using KRACH to predict the outcome of a mismatch:

One, KRACH is a maximum-likelihood estimate of a team's Bradley-Terry strength, whereas any estimate of the Bradley-Terry parameters based on a finite amount of data has some uncertainty in it. Ordinarily that's not such a big deal for assigning probabilities to the outcome of one game: the ratio of Cornell's strength to Clarkson's might be higher or lower than our best guess, but that means we might have over- or under-estimated it, and so the uncertainty probably washes out. But when the best guess is something like 50-to-1, that uncertainty can make a big difference in a more careful estimate of the probabilities. As an oversimplified version, suppose the "correct" odds might be 100-to-1 or 25-to-1, but we don't know which. Then the probability of an upset would be the average of 1.0% and 3.8%, which is 2.4% or about 40-to-1 against, not 50-to-1. I.e., the uncertainty naturally biases our expectation of the true probability away from the extremes, because having maybe somewhat overestimated the magnitude of the upset is a bigger effect than having maybe somewhat underestimated it. This is the issue we addressed in this paper, with a specific example discussed on this forum of the Cornell-Quinnipiac quarterfinal series from a few years back: [dx.doi.org] [arxiv.org]

Two, the maximum-likelihood analysis doesn't take into account any prior expectations about the possible discrepancies in teams' strengths, which means it's equivalent to making your prior information completely noninformative. This is a well-known effect which leads to undefeated teams having infinite KRACH ratings, and it's why Ken Butler put the "fictitious games" into KRACH for a while (the maximum likelihood estimates with fictitious games turn out to be the maximum a posteriori estimates with a particular prior distribution). But this is almost always a pretty small effect by this point in the season, so we don't generally worry about it. (BTW, the basic problem is older than hockey, since LaPlace was working on it circa 1800. What's your best guess probability that an event will happen, given that it's never happened in some number of chances? If you use the fraction of times you've already seen it as an estimate, you get zero, but you probably don't want to say it's literally impossible. The Bayes-Laplace rule of succession is basically what you get if you at two extra "fictitious trials", one where it occurred and one where it didn't.)

Ties are a huge pain in the ass, and complicate everything, so it's often easier to pretend they don't exist (or rather that past ties are half wins and half losses and future ties are something we don't talk about), especially since they become impossible once the playoffs start.

I'm thinking LaPlace spent more time on this problem than he did arguing with Amoureux des Ours.

Question for either everyone or just those with admin powers:

Can we have a dedicated thread for all things KRACH, PWR, probablities etc? And if so, more. Importantly, can we move posts and or threads that drift into the theory and minutia debates over to there in the future as they crop up?

Less thread drift in this would be great, plus the historical info on the subjects would still be in the same threads for reference.

abmarks
And if so, more. Importantly, can we move posts and or threads that drift into the theory and minutia debates over to there in the future as they crop up?

This is silly. If you have a problem with drift ask somebody to move their own post. Don't burden the mods with it.

Trotsky

abmarks
And if so, more. Importantly, can we move posts and or threads that drift into the theory and minutia debates over to there in the future as they crop up?

This is silly. If you have a problem with drift ask somebody to move their own post. Don't burden the mods with it.

Maybe we need a thread to discuss thread drift.

nshapiro

Trotsky

abmarks
And if so, more. Importantly, can we move posts and or threads that drift into the theory and minutia debates over to there in the future as they crop up?

This is silly. If you have a problem with drift ask somebody to move their own post. Don't burden the mods with it.

Maybe we need a thread to discuss thread drift.

No, we should just discuss that in every thread...

Trotsky

nshapiro

Trotsky

abmarks
And if so, more. Importantly, can we move posts and or threads that drift into the theory and minutia debates over to there in the future as they crop up?

This is silly. If you have a problem with drift ask somebody to move their own post. Don't burden the mods with it.

Maybe we need a thread to discuss thread drift.

No, we should just discuss that in every thread...

I think what's missing is the statistical analysis of thread drift. One should be able to predict the direction and verbosity of the drift based on the number of times each registered user accesses eLynah. JTW might have some spare time to tackle this.

marty

Trotsky

nshapiro

Trotsky

abmarks
And if so, more. Importantly, can we move posts and or threads that drift into the theory and minutia debates over to there in the future as they crop up?

This is silly. If you have a problem with drift ask somebody to move their own post. Don't burden the mods with it.

Maybe we need a thread to discuss thread drift.

No, we should just discuss that in every thread...

I think what's missing is the statistical analysis of thread drift. One should be able to predict the direction and verbosity of the drift based on the number of times each registered user accesses eLynah. JTW might have some spare time to tackle this.

Only sissies use advanced metrics to predict thread drift. Real men use the eye test.

Trotsky

abmarks
And if so, more. Importantly, can we move posts and or threads that drift into the theory and minutia debates over to there in the future as they crop up?

This is silly. If you have a problem with drift ask somebody to move their own post. Don't burden the mods with it.

Fair enough. I'm used to mod-driven forums to assumed it was the same on here.

USCHO: Bracketology: Which bubble teams have a shot at playing for an NCAA hockey national championship?

Jayson's

Worcester

1 North Dakota
7 Clarkson
9 Northeastern
16 AIC

Allentown

2 Minnesota State
8 Massachusetts
10 Penn State
15 Minnesota

Albany

3 Cornell
6 Boston College
11 Arizona State
14 Maine

Loveland

4 Minnesota Duluth
5 Denver
12 Bemidji State
13 Ohio State

Jim's

Albany

1 North Dakota
7 Clarkson
9 Northeastern
16 AIC

Allentown

2 Minnesota State
8 Massachusetts
10 Penn State
15 Minnesota

Worcester

3 Cornell
6 Boston College
11 Arizona State
14 Maine

Loveland

4 Minnesota Duluth
5 Denver
12 Bemidji State
13 Ohio State

Jim Hyla
USCHO: Bracketology: Which bubble teams have a shot at playing for an NCAA hockey national championship?

Jayson's

Worcester

1 North Dakota
7 Clarkson
9 Northeastern
16 AIC

Allentown

2 Minnesota State
8 Massachusetts
10 Penn State
15 Minnesota

Albany

3 Cornell
6 Boston College
11 Arizona State
14 Maine

Loveland

4 Minnesota Duluth
5 Denver
12 Bemidji State
13 Ohio State

Jim's

Albany

1 North Dakota
7 Clarkson
9 Northeastern
16 AIC

Allentown

2 Minnesota State
8 Massachusetts
10 Penn State
15 Minnesota

Worcester

3 Cornell
6 Boston College
11 Arizona State
14 Maine

Loveland

4 Minnesota Duluth
5 Denver
12 Bemidji State
13 Ohio State

Marty says "North Dakota earned the right to stay out west!" And "Why give Duluth an easier path to three-peat?"

This also allows for less travel for the teams in Allentown and Worcester.

Albany

3 Cornell
14 Maine

8 U Mass
7 Clarkson


Allentown

4 Minnesota Duluth
13 tOSU

9 Northeastern
10 Penn State


Worcester

2 Minn State Mankato
15 Mass Lowell

6 Boston College
11 Arizona State


Loveland

1 North Dakota
16 AIC

5 Denver
12 Bemidji State

I've critiqued the Pairwise Probability Matrix the last couple of weeks, but I think it's worth stating that it is WAY better suited to answer the question posed in this week's USCHO bracketology post (Which bubble teams have a shot at playing for an NCAA hockey national championship?).

Has anyone ever used advanced statistical methods to determine the accuracy of past predictions of hockey game winners or the accuracy of past playoff seeding predictions? Please advise. I hate to waste my time studying inaccurate computations when I could be assessing promises made by presidential candidates.

osorojo
Has anyone ever used advanced statistical methods to determine the accuracy of past predictions of hockey game winners or the accuracy of past playoff seeding predictions? Please advise. I hate to waste my time studying inaccurate computations when I could be assessing promises made by presidential candidates.

Could you maybe move this to Twitter?

KGR11
I've critiqued the Pairwise Probability Matrix the last couple of weeks, but I think it's worth stating that it is WAY better suited to answer the question posed in this week's USCHO bracketology post (Which bubble teams have a shot at playing for an NCAA hockey national championship?).

The matrix never knows which shot hits the fricking post and goes in.

billhoward

KGR11
I've critiqued the Pairwise Probability Matrix the last couple of weeks, but I think it's worth stating that it is WAY better suited to answer the question posed in this week's USCHO bracketology post (Which bubble teams have a shot at playing for an NCAA hockey national championship?).

The matrix never knows which shot hits the fricking post and goes in.

Red pill or blue pill?

Jeff Hopkins '82

billhoward

KGR11
I've critiqued the Pairwise Probability Matrix the last couple of weeks, but I think it's worth stating that it is WAY better suited to answer the question posed in this week's USCHO bracketology post (Which bubble teams have a shot at playing for an NCAA hockey national championship?).

The matrix never knows which shot hits the fricking post and goes in.

Red pill or blue pill?

LET’S GO RED!!!!

osorojo
Has anyone ever used advanced statistical methods to determine the accuracy of past predictions of hockey game winners or the accuracy of past playoff seeding predictions? Please advise. I hate to waste my time studying inaccurate computations when I could be assessing promises made by presidential candidates.

Not exactly past predictions, but see Section 3.1 of [dx.doi.org] [arxiv.org]

Bracketology: Will top-end balance continue in NCAA hockey up until Selection Sunday?

Jim’s bracket

Allentown Regional
1. North Dakota (1)
2. Penn State (7)
3. Bemidji State (11)
4. American International (16)

Worcester Regional
1. Boston College (4)
2. Minnesota Duluth (5)
3. Northeastern (12)
4. Arizona State (13)

Loveland Regional
1. Minnesota State (2)
2. Denver (6)
3. Ohio State (9)
4. Western Michigan (15)

Albany Regional
1. Cornell (3)
2. Massachusetts (8)
3. Clarkson (10)
4. Minnesota (14)

Jayson’s bracket

Loveland Regional
1. North Dakota (1)
2. Denver (5)
3. Ohio State (9)
4. American International (16)

Worcester Regional
1. Boston College (4)
2. Minnesota Duluth (5)
3. Northeastern (12)
4. Arizona State (13)

Allentown Regional
1. Minnesota State (2)
2. Penn State (7)
3. Bemidji State (11)
4. Western Michigan (15)

Albany Regional
1. Cornell (3)
2. Massachusetts (8)
3. Clarkson (10)
4. Minnesota (14)

NCAA hockey bracket: 2020 projections a month from selections

The projected 2020 NCAA college hockey bracket (as of Feb. 23)

Albany Regional (Albany, NY — Host ECAC)
1. North Dakota vs. 16. AIC
8. Massachusetts vs. 9. Ohio State

Worcester Regional (Worcester, MA — Host Holy Cross)
4. Boston College vs. 13. Arizona State
5. Minnesota Duluth vs. 12. Northeastern

Allentown Regional (Allentown, PA — Host Penn State)
3. Cornell vs. 14. Minnesota
7. Penn State vs. 11. Bemidji State

Loveland Regional (Loveland, CO — Host Denver)
2. Minnesota State vs. 15. Western Michigan
6. Denver vs. 10. Clarkson

It would be nice to avoid Pedo State in Allentown.

Trotsky
It would be nice to avoid Pedo State in Allentown.

Do we imbue Penn State with greater powers than they have? They have failed to win 14 of their 34 games. Tambroni is not coaching hockey. In Albany the bracket du jour would allow only Cornell or Clarkson to get to the FF. I'd like to reprise 1970 in the finals. See if Kaldis is up to a third period hat trick.