BBO Discussion Forums: Who will stop Italy? - BBO Discussion Forums

Jump to content

  • 5 Pages +
  • « First
  • 2
  • 3
  • 4
  • 5
  • You cannot start a new topic
  • You cannot reply to this topic

Who will stop Italy?

Poll: Who will stop Italy? (51 member(s) have cast votes)

Who will stop Italy?

  1. Somebody. (33 votes [64.71%])

    Percentage of vote: 64.71%

  2. Nobody. (18 votes [35.29%])

    Percentage of vote: 35.29%

Vote Guests cannot vote

#61 User is offline   bid_em_up 

  • PipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 2,351
  • Joined: 2006-March-21
  • Location:North Carolina

Posted 2007-October-08, 07:27

nickf, on Oct 7 2007, 08:48 PM, said:

whereagles, on Oct 8 2007, 08:36 AM, said:

SA is pwnzzoring italy ^^

Anyone who wants to back South Africa to beat Italy with me, despite the current score (48/96 boards played) please form an orderly queue.

nickf
sydney

So, how much did you lose?
Is the word "pass" not in your vocabulary?
So many experts, not enough X cards.
0

#62 User is offline   matmat 

  • ded
  • PipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 3,459
  • Joined: 2005-August-11
  • Gender:Not Telling

Posted 2007-October-08, 08:15

helene_t, on Oct 8 2007, 07:39 AM, said:

Quintistan: 5

I think Quintistan is overrated

I don't know about running monte-carlos to simulate outcomes, but it does strike me that this is more of a graph theory problem than anything (and, those who have their nose in math more than I do, can tell me how much I am wrong there).
0

#63 User is offline   MickyB 

  • PipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 3,290
  • Joined: 2004-May-03
  • Gender:Male
  • Location:London, England

Posted 2007-October-08, 09:37

helene_t, on Oct 8 2007, 01:39 PM, said:

hrothgar, on Oct 8 2007, 02:14 PM, said:

Bridge isn't transitive  (furthermore, I beleive that Helene's model does have transitivity assumptions built into it).

It is a linear model, i.e. if the coefficients are
Dekistan: 10
Oktistan: 8
Quintistan: 5

so Dekistan is expected to beat Oktistan by 2 IMPs and Oktistan to beat Quintistan by 3 IMPs, then it follows that Dekistan is expected to beat Quintistan by 2+3=5 IMPs.

It could be that the general response function is slightly convex (Dekistan will beat Qintistan by less than 5 IMPs) or concave (more than 5 IMPs).

I suspect it would be less than five imps.
0

#64 User is offline   MickyB 

  • PipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 3,290
  • Joined: 2004-May-03
  • Gender:Male
  • Location:London, England

Posted 2007-October-08, 09:42

It would be rather difficult to model the psychological issues, I think this would tend to increase the chances of a weaker team beating a stronger one.
0

#65 User is offline   bid_em_up 

  • PipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 2,351
  • Joined: 2006-March-21
  • Location:North Carolina

Posted 2007-October-08, 09:52

I suspect the whole premise is completely invalid.

Too many outside factors involved for any linear model to have any real merit, imo.
Is the word "pass" not in your vocabulary?
So many experts, not enough X cards.
0

#66 User is offline   pclayton 

  • PipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 9,151
  • Joined: 2003-June-11
  • Location:Southern California

Posted 2007-October-08, 11:03

Helene: is it possible to build in an error factor into this type of model?
"Phil" on BBO
0

#67 User is offline   helene_t 

  • The Abbess
  • PipPipPipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 17,402
  • Joined: 2004-April-22
  • Gender:Female
  • Location:Odense, Denmark
  • Interests:History, languages

Posted 2007-October-08, 11:56

pclayton, on Oct 8 2007, 07:03 PM, said:

Helene: is it possible to build in an error factor into this type of model?

There is an error term, epsilon. Or do you have something more fancy in mind?
The world would be such a happy place, if only everyone played Acol :) --- TramTicket
0

#68 User is offline   pclayton 

  • PipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 9,151
  • Joined: 2003-June-11
  • Location:Southern California

Posted 2007-October-08, 11:59

helene_t, on Oct 8 2007, 09:56 AM, said:

pclayton, on Oct 8 2007, 07:03 PM, said:

Helene: is it possible to build in an error factor into this type of model?

There is an error term, epsilon. Or do you have something more fancy in mind?

So the end result should have a range right?
"Phil" on BBO
0

#69 User is offline   matmat 

  • ded
  • PipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 3,459
  • Joined: 2005-August-11
  • Gender:Not Telling

Posted 2007-October-08, 11:59

helene_t, on Oct 8 2007, 12:56 PM, said:

pclayton, on Oct 8 2007, 07:03 PM, said:

Helene: is it possible to build in an error factor into this type of model?

There is an error term, epsilon. Or do you have something more fancy in mind?

but this epsilon... it is very small...
0

#70 User is offline   helene_t 

  • The Abbess
  • PipPipPipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 17,402
  • Joined: 2004-April-22
  • Gender:Female
  • Location:Odense, Denmark
  • Interests:History, languages

Posted 2007-October-08, 12:03

Yes, there is a standard deviation of 24 IMPs on the RR matches. This scales with the squareroot of the size so it becomes sqrt(8)*24 for 128 boards.
The world would be such a happy place, if only everyone played Acol :) --- TramTicket
0

#71 User is offline   whereagles 

  • PipPipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 14,900
  • Joined: 2004-May-11
  • Gender:Male
  • Location:Portugal
  • Interests:Everything!

Posted 2007-October-08, 13:50

bid_em_up, on Oct 8 2007, 01:27 PM, said:

nickf, on Oct 7 2007, 08:48 PM, said:

whereagles, on Oct 8 2007, 08:36 AM, said:

SA is pwnzzoring italy ^^

Anyone who wants to back South Africa to beat Italy with me, despite the current score (48/96 boards played) please form an orderly queue.

nickf
sydney

So, how much did you lose?

None, because I didn't get to see nick's offer before it was all over... :)
0

#72 User is offline   Mbodell 

  • PipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 2,871
  • Joined: 2007-April-22
  • Location:Santa Clara, CA

Posted 2007-October-08, 14:18

helene_t, on Oct 8 2007, 01:03 PM, said:

Yes, there is a standard deviation of 24 IMPs on the RR matches. This scales with the squareroot of the size so it becomes sqrt(8)*24 for 128 boards.

Answering other critics, that's not so small. That suggests std dev of ~68 IMPs. And for a 92% chance of winning (assuming normal distribution) versus South Africa that suggests on average Italy should win by 1.4 std dev, so by a mean of 95 IMPs (assuming they always play all segments at top form and don't stop if Italy is up triple digits early). Italy losing by at least 12 IMPs (since carry over wasn't counted) is thus a 5.68% event or a bit better than 1 in 20.
0

#73 User is offline   cherdano 

  • 5555
  • PipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 9,520
  • Joined: 2003-September-04
  • Gender:Male

Posted 2007-October-08, 14:29

hrothgar, on Oct 8 2007, 06:14 AM, said:

I think that the results of the South Africa - Italy match expose some of the limitations with the modeling techniques that folks have been using:

The approach that I have been advocating (and that Gerben and Alex implemented) is based on Monte Carlo simulation. To date, the model that we were using made an explicite assumption that the expected value and the variance for board results was constant across the length of a match. A more sophisitcated model should probably build in the notion of deliberately trading off expected value for variance when one is behind by a large amount. I don't think that this would be that much more difficult to program, however, parameterizing the model would become a lot more difficult.

From what I can tell, Helene's approach suffered from a different problem. A number of follks, myself included seemed to feel that Helene's model gave a bot too much credit to the Italians. In particular, the model suggested that the Italians were massive favorites against a number of teams that beat them in head-to-head matches during the Round Robin stage. (In defference to Helene, it seems clear that the Italians also believed that they were clear favorites to beat the SA team despite losing to SA in the RR). I suspect that Helene's model may have fallen victim to one of my favorite theories: Bridge isn't transitive (furthermore, I beleive that Helene's model does have transitivity assumptions built into it). While Italy lost to SA, they scored well against a number of teams that SA didn't fare quite so well against. In turn, this suggested that the Italy v SA was an outlier....

I think it is much simpler than that. Bridge maybe isn't transitive, but I would think this effect is very very small.
The simple explanation is:
1. South Africa played better in the quarter-final than in the Round Robin, and the Italians (well, maybe just one of their pairs) worse. I don't think Helene's model allowed for that.
2. South Africa had more luck than Italy in the quarter final.
The easiest way to count losers is to line up the people who talk about loser count, and count them. -Kieran Dyke
0

#74 User is offline   jdonn 

  • - - T98765432 AQT8
  • PipPipPipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 15,085
  • Joined: 2005-June-23
  • Gender:Male
  • Location:Las Vegas, NV

Posted 2007-October-08, 16:09

Arend, when you say SA had more luck, isn't that just what Richard was already saying with "this suggested that the Italy v SA was an outlier"?

Your point 1. is well taken though.
Please let me know about any questions or interest or bug reports about GIB.
0

#75 User is offline   cherdano 

  • 5555
  • PipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 9,520
  • Joined: 2003-September-04
  • Gender:Male

Posted 2007-October-08, 16:35

jdonn, on Oct 8 2007, 04:09 PM, said:

Arend, when you say SA had more luck, isn't that just what Richard was already saying with "this suggested that the Italy v SA was an outlier"?

Your point 1. is well taken though.

No, I think Richard was saying the exact opposite. He was saying that Helene's analysis wrongly assumed that the the win by SA vs Italy in the round robin was an outlier (probably implying that the quarter final result may have proven this wrong).

I have to say that in all the quarters I have been watching, the Italians were playing a bit better than the South Africans.
The easiest way to count losers is to line up the people who talk about loser count, and count them. -Kieran Dyke
0

#76 User is offline   hrothgar 

  • PipPipPipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 15,725
  • Joined: 2003-February-13
  • Gender:Male
  • Location:Natick, MA
  • Interests:Travel
    Cooking
    Brewing
    Hiking

Posted 2007-October-08, 16:49

cherdano, on Oct 9 2007, 01:35 AM, said:

jdonn, on Oct 8 2007, 04:09 PM, said:

Arend, when you say SA had more luck, isn't that just what Richard was already saying with "this suggested that the Italy v SA was an outlier"?

Your point 1. is well taken though.

No, I think Richard was saying the exact opposite. He was saying that Helene's analysis wrongly assumed that the the win by SA vs Italy in the round robin was an outlier (probably implying that the quarter final result may have proven this wrong).

Arend is correct: Italy scoring well against a large number of teams that - in turn - score well against South Africa.

Based on this, Helene's model assumed that Italy was significantly stronger than South Africa (the actual table results where South Africa beat Italy was an outlier)

Sorry if I wasn't clear earlier
Alderaan delenda est
0

#77 User is offline   Echognome 

  • Deipnosophist
  • PipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 4,386
  • Joined: 2005-March-22

Posted 2007-October-08, 16:52

Seems like this is turning into an econometrics debate (or statistics if you prefer more generally, although I feel this type of modeling is probably best described by the former). I wanted to add that Richard's advocacy of Monte Carlo methods will obviously work much better in his hypothetical tournament question, because he is not using any data for his estimation. Helene offered up a linear model of wins and losses based on actual data to predict future outcomes. She might have bootstrapped the errors rather than use normality, but I doubt that would have changed too much, especially given the small sample size. As such, I feel this is an unfair criticism. In regards to transitivity, I think this is just a matter of how you model it. I suggested an alternative method, but by no means do I feel that my alternative was the only "right" way to do it.

As per Phil's concern, normally estimated probabilities are reported along with standard errors. I'm sure Helene's omission was more for the sake of the readers than for her not considering it in the model.

As per South Africa winning, it does not make the model invalid. I think most of us felt that Italy were heavy favorites. The fact that 5% or 10% or 20% events happen should come as no surprise.
"Half the people you know are below average." - Steven Wright
0

#78 User is offline   awm 

  • PipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 8,743
  • Joined: 2005-February-09
  • Gender:Male
  • Location:Zurich, Switzerland

Posted 2007-October-08, 17:02

Perhaps something that's not being modeled is that the variance in matches depends on style and methods in use.

People say that playing "weird systems" is "high variance" but that's not really true. If my opponents are all playing forcing pass, the match will be much lower variance if I also play forcing pass. Playing similar methods/style tends to reduce the number of swings generated by bidding, whereas playing very different methods/style tends to increase the number of such swings. If one team is somehow inferior to another, the odds of the inferior team winning are much higher in a "high variance" match than in a "low variance" match because the swings due to bidding/style tend to be higher magnitude than the slow accumulation of imps by the team that plays/defends better.

Anyways, watching Italy/South Africa I noticed that very different bidding decisions were made on many hands. It seemed that the Italians bid a lot of games the South Africans didn't (failing on more than they made) and that the South Africans preempted on a lot of hands where the Italians didn't. While it's not obvious that one style is "better" than the other, the fact that the auction was almost always different at the two tables would seem to have helped the South Africans' chances, assuming that (as most seem to think) the Italians are generally superior card players.
Adam W. Meyerson
a.k.a. Appeal Without Merit
0

#79 User is offline   Echognome 

  • Deipnosophist
  • PipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 4,386
  • Joined: 2005-March-22

Posted 2007-October-08, 17:37

awm, on Oct 8 2007, 03:02 PM, said:

Perhaps something that's not being modeled is that the variance in matches depends on style and methods in use.

What are you talking about? It's already modelled in there. It's called the error term.

I mean seriously, how much do you expect to be modelled?

Should we model all of the possible pairings and who has seating rights?

The temperature of the closed vs the open rooms?

Whether one of the players gets laid the night before? (special thanks to JL for this example)

I mean if you can make the case that (1) this is significant and (2) can easily be modelled, that's one thing. But I think that what Helene was trying to accomplish was a simplistic model with readily available data.
"Half the people you know are below average." - Steven Wright
0

#80 User is offline   awm 

  • PipPipPipPipPipPipPipPipPip
  • Group: Advanced Members
  • Posts: 8,743
  • Joined: 2005-February-09
  • Gender:Male
  • Location:Zurich, Switzerland

Posted 2007-October-08, 17:56

The point is that it could easily be the case that:

(1) A will virtually always beat B.
(2) B will beat C most of the time.
(3) C has a substantial non-zero chance to beat A.

I think this is a fundamental flaw in any basically transitive model.

Another way to put it is, the result depends on both relative skill and the frequency and magnitude of random swings. This second frequency depends on which two teams are playing...
Adam W. Meyerson
a.k.a. Appeal Without Merit
0

  • 5 Pages +
  • « First
  • 2
  • 3
  • 4
  • 5
  • You cannot start a new topic
  • You cannot reply to this topic

1 User(s) are reading this topic
0 members, 1 guests, 0 anonymous users