News for hackers. Stuff that matters.
Re:World Cup Follow-Up: Update of Winning Probabilities and ... by seabee on Friday June 27, 2014 @10:11AM (#7953957)
The probability of winning all games is inherently conditional on the probability of reaching the quarter finals. To equate this to common examples of probability, winning at the knockout stage is like flipping a biased coin and getting 4 heads in a row (= four matches won).

As such, there is no way the probability of winning can exceed the probability of reaching the quarter finals.

Re:World Cup Follow-Up: Update of Winning Probabilities and ... by Someone on Friday June 27, 2014 @01:47PM (#7955264)
This is a different situation.

We have

  P(Belgium reaches quarters) >= P(Belgium wins overall)

  P(USA reaches quarters) >= P(USA wins overall)

  P(USA reaches quarters) >= P(Belgium reaches quarter)
That does not imply

  P(USA wins overall) >= P(Belgium wins overall)
Re:World Cup Follow-Up: Update of Winning Probabilities and ... by StavrosK on Friday June 27, 2014 @10:39AM (#7954104)
The coin won't get any advantage from playing in its home field, for example. I specifically said that I'm not arguing that this is the case here, but one can conceive of an example where it would.
Re:World Cup Follow-Up: Update of Winning Probabilities and ... by seabee on Friday June 27, 2014 @12:50PM (#7954929)
I cannot conceive of an example. In fact I argued that it is impossible because of the fundamental rules of conditional probability.
Re:World Cup Follow-Up: Update of Winning Probabilities and ... by sp332 on Friday June 27, 2014 @01:01PM (#7954993)
Probability of losing is not transitive. If A is likely to lose to B, and B is likely to lose to C, it does not follow that A is likely to lose to C.
Re:World Cup Follow-Up: Update of Winning Probabilities and ... by pedrosorio on Friday June 27, 2014 @01:40PM (#7955224)
Unless we're using ELO to determine these probabilities.
Re:World Cup Follow-Up: Update of Winning Probabilities and ... by sp332 on Friday June 27, 2014 @02:06PM (#7955384)
Aw, you're right. I didn't read closely enough to understand their model.