Weekly game probabilities for week 4 are now up at Sports on Earth. Probabilities are a blend of the pre-season team strength estimates with a strong dose of stats from weeks 1, 2 and 3.
Please remember that the projected scores are not to be taken terribly seriously. Do not bet the mortgage on them as they are not intended to graded against the spread. They are simply a "maximum-plausibility" estimate given respective team scoring tendencies.
- Home
- predictions
- Weekly Game Probabilities - Week 4
Subscribe to:
Post Comments (Atom)
Brian, I find the probabilities fascinating and I eagerly await them each week, so I just wanted to say thanks for doing them.
This site is great, thanks for publishing all this information. Question about offensive player stats, why are pass TDs not listed in the QB stats?
So the sample size in the NFL comes out to 20 NBA games. How many games would the teams need to play for statistical significance? Also, would that lead to more consistent stats?
> ... How many games would the teams need to play for statistical significance?
In general, when we talk about 'statistical significance' there's some difference over some sample. An average difference of 21 points per game over the course of a football season is probably more significant than an average difference of 1 point per game over the course of an NBA season.
the win probabilities and expected scores by Brian do not jibe with Vegas money line / point spread equivalents. Brian has favorites winning about as often as Vegas thinks, but by way more points than Vegas thinks. That's interesting. Take the favorites laying the points?