Who will stop Italy?

[han]

Although Italy is not as dominant in the round robin as they were last time, I have a hard time imagining them not winning the Bermuda Bowl. What do you think?

[pclayton]

USA 1 is playing really well. So is Poland.

[fred]

Consider the math.

 

If Italy is 100% to make it to the quarter-finals, 10 to 1 to win their quarter-final match, and 5 to 1 to win both their semi-final and final matches, they are still less than 60% to win the whole thing.

 

And even though most people would probably consider Italy to be "clearly the best team", I suspect that most of these people would believe that there are several other teams that have a better than 1 in 5 chance of beating Italy in a given match.

 

So I think you need to work on your imagination B)

 

Fred Gitelman

Bridge Base Inc.

www.bridgebase.com

[matmat]

this is kind of a tiger woods situation, no?

[hrothgar]

I don't think that an Italian win is pre-ordained:

 

USA2 seems to be recovering from a fairly slow start. They're currently sitting in the middle of the pack with a fairly easy schedule for the next couple days (Egypt, New Zealand, Pakistan, Indonesia, and the Netherlands). The might be able to pick up 3-4 places and make it in to the finals.

 

On a good day, either USA1 or USA2 is a good match for the Italians.

[Aberlour10]

I would say.... in 96 or 128 boards match nobody this time.

 

Robert

[pclayton]

this is kind of a tiger woods situation, no?

Look at Tiger's match play record in the Ryder Cup. Not that impressive.

 

He played well in this year's President's Cup, although he lost an emotional head to head match to Mike Weir of Canada in the singles that didn't affect the result.

 

He also has a spotty record in the annual Match Play championship they have in the spring on the PGA tour.

 

Tiger versus the field is one thing. He's the best in the world and they guy you'd want to put your money on. Tiger vs. Player A, then Player B, etc.. is less impressive.

 

So, yeah, if you had to pick a favorite, its Italy at this point, but they are much worse than a 2:1 favorite at this point.

[ralph23]

USA-1, the Cinderella team !

[vang]

i'm a fan of Italy but i didn't like their start, so i hope someone will stop them. Poland i hope ;-)

[Mosene]

Re Tiger's match play record. If they were to play 72 holes it would be much better. So, the question is, are they going to play enough boards to all but eliminate what I will call the "randomness" factor.

[Halo]

Getting to the final and winning is certainly one of way of dealing with any opponent.

[helene_t]

Agree with Fred, even if Italy is the better team (I suppose they are), their chances are probably less than 50%, so I voted "someone". The chances could be

Italy: 35%%

USA1: 25%

Poland: 15%

USA2: 10%

Norway: 10%

Other: 5%

 

or some such. Actually my linear regression model could compute the chances, but one would have to make some assumptions. In the most simple case one could assume that the strength of the teams don't change during the event.

[NickToll]

Somebody will do. Any team you like.

 

You know, we Italians are very superstitious... B)

[Edmunte1]

Agree with Fred, even if Italy is the better team (I suppose they are), their chances are probably less than 50%, so I voted "someone". The chances could be

Italy: 35%%

USA1: 25%

Poland: 15%

USA2: 10%

Norway: 10%

Other: 5%

 

I also think Netherlands has a very good team

[Elianna]

Why is this in the Advanced/Expert forum?

[matmat]

Why is this in the Advanced/Expert forum?

because only advanced and expert players can answer questions of this magnitude.

[skjaeran]

I can understand why Italy are favourites in most people's eyes - that's very reasonable.

 

But there's several teams in the competition who's got a 40-50% chance of beating them in a head to head match, and has done so on more than one occasion over the last 5-6 years.

 

The Italian team haven't IMO looked quite as impressive as earlier the last year, and certainly not in the first part of the Round Robin. I'd give them 25-30% chance of winning the event now, after they have gotten their play more together now. I'd say USA1 20-25%, Poland and USA2 15%, Norway and Netherlands 10%, Other 10-20%.

[Cascade]

this is kind of a tiger woods situation, no?

Look at Tiger's match play record in the Ryder Cup. Not that impressive.

 

He played well in this year's President's Cup, although he lost an emotional head to head match to Mike Weir of Canada in the singles that didn't affect the result.

 

He also has a spotty record in the annual Match Play championship they have in the spring on the PGA tour.

 

Tiger versus the field is one thing. He's the best in the world and they guy you'd want to put your money on. Tiger vs. Player A, then Player B, etc.. is less impressive.

 

So, yeah, if you had to pick a favorite, its Italy at this point, but they are much worse than a 2:1 favorite at this point.

I think this is just an argument about the length of matches.

 

Tiger vs Player A etc over 18 holes is something of a lottery.

 

Tiger vs Player A etc over many more holes is a whole lot different.

 

Similarly in bridge anyone can and do win 16 board matches but when it comes to the longer matches in the knockout there will be more certainty on the outcome - the better team will win more often. Although quite possibly the matches aren't long enough to ensure that Italy is better than 5 to 1 on.

[barmar]

Consider the math.

 

If Italy is 100% to make it to the quarter-finals, 10 to 1 to win their quarter-final match, and 5 to 1 to win both their semi-final and final matches, they are still less than 60% to win the whole thing.

No offense, Fred, but the "math" you're considering assumes that all the events are random and independent. But bridge matches are not like rolling dice.

[helene_t]

Consider the math.

 

If Italy is 100% to make it to the quarter-finals, 10 to 1 to win their quarter-final match, and 5 to 1 to win both their semi-final and final matches, they are still less than 60% to win the whole thing.

No offense, Fred, but the "math" you're considering assumes that all the events are random and independent. But bridge matches are not like rolling dice.

Nope. They cannot win (or lose) the semi-final without having won the quarterfinal, so the "5 to 1" thing is a conditional probability. Hence dependency is mood.

 

Fred is right, as always :)

[Gerben42]

Why is USA 1 called the "Cinderella" team? Why is any team called that?

 

Anyway,

 

Italy: 62

USA1: 0

 

ouch!

 

In a KO system you always have to multiply probabilities, which makes it hard even for Roger Federer to win ALL tournaments he plays in.

 

Hup Holland hup! :)

[helene_t]

I have fitted my model to the 18 first rounds. These are the probabilities that Italy will beat each of the teams in a 128-board match:

 

[1] "ARGENTINA 0.953012302526452"

[1] "AUSTRALIA 0.868122124683079"

[1] "BRAZIL 0.97464322042772"

[1] "CANADA 0.999338396916119"

[1] "CHINA SMEG 0.931933653485224"

[1] "CHINESE TAIPEI 0.991064605855261"

[1] "EGYPT 0.977016518343036"

[1] "INDIA 0.994100216807085"

[1] "INDONESIA 0.963919841634841"

[1] "IRELAND 0.990826825344023"

[1] "ITALY 0.5"

[1] "JAPAN 0.949946849954086"

[1] "NETHERLANDS 0.862697553887635"

[1] "NEW ZEALAND 0.99931127274922"

[1] "NORWAY 0.848930973373835"

[1] "PAKISTAN 0.989478435183908"

[1] "POLAND 0.964036923004087"

[1] "SOUTH AFRICA 0.918083617456822"

[1] "SWEDEN 0.904883807753579"

[1] "TRINIDAD & TOBAGO 0.9999968845097"

[1] "USA 1 0.80075194242031"

[1] "USA 2 0.942098374182473"

[hrothgar]

I have fitted my model to the 18 first rounds. These are the probabilities that Italy will beat each of the teams in a 128-board match:

Silly question: My understanding is that you performed a simple linear regression based on total scores. I took a quick look at the results table that you looked at. From what I can tell, you have access to the total score for the match, as well as the number of boards. This gives you information about the mean result per board, but we don't have any informaion about the variance.

 

If you are generalizing your results to encompass longer matches, this variance assumption would seem to be critical. You can get arround this by assuming that the board results are normally distributed (hell, if you're using a linear regression, you pretty much made this same assumption). Even so, given how critical the variance assumption is to projecting forward to a 128 board match I'd be a bit leery.

 

I think that the monte carlo type techique that gerben and alex were using earlier this year is probably a better predictor than a simple extrapolation. I woder whether it will ever be possible to get board by board results.

 

(Justin, if you're reading this, send us all the board scores for the match between USA2 and Italy. We'll run it through the model and see what spits back out)

[helene_t]

I did not analyze this per board, only per match. I used the IMPs rather than the VPs because they are more accurate and because the linear model is more plausible for IMPs.

 

The residuals are normal distributed, but there could still be a number of issues related to the model, such as additivity and heteroscedasticity.

 

As for extrapolating the variance, I computed the residual variance from the 16-board matches. Now if a 128-board match can be seen as the aggregate of 8 independent 16-board matches, the variance and the IMP saldo are both expected to grow linearly, so the CV must be corrected by a factor sqrt(1/8). That's what I did.

[cherdano]

Helene, did you take carry-over into account?

(It is 1/2 of the RR result if the higher-ranking team won, 1/3 if the lower-ranking team won, and a maximum of 16 for 96-board matches, a maximum of 20 for 128-board matches.)