> > > > >If one method gives a 10% improvement over another then it might > > >make all the difference. > > > > > > > > So how would you know that one method was 10% better than another? > >
Well if the new "calculated" ranking goes into the model for estimating an outcome, with other parameters remaining equal, and the forecasts are 10% more accurate, that is 10% more results are preduicted correctly, then in the "real world" I would think it fair to suggest that the ranking was 10% more accurate. > Very good question! > > What sport are was this discussion about, > where there was any carry-over effect at all? > > It has been shown pretty well that there is no such thing > as a 'hot hand' in basketball, for one evening or across games. > Points-scored in basketball is (at least) a continuous outcome, > which makes it easier to research (that is, smaller N is needed) > than dichotomous outcomes. > > Having hits in baseball doesn't carry over, or hitting homers. > > Historical winning streaks in team sports seem to match > the number of consecutive games that you would expect > by chance, without much in the way of assumptions.... Not American ones - particularly baseball where the "World Series" includes two team from Canada. I heard that they were going to rename it the "Milky Way Series" for greater impact :) There must be a valid way of ranking one team over another or others? I am not interested in winning streaks per se. I am not trying to predict the odds of the Mets winning their next five games. How come the same teams keep winning trophies - it's not by chance is it? Cheers . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
