Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.soft-sys.math.mathematica > #12953
| From | Scott Hemphill <hemphill@hemphills.net> |
|---|---|
| Newsgroups | comp.soft-sys.math.mathematica |
| Subject | Re: Modeling of NFL game results |
| Date | 2012-12-27 10:03 +0000 |
| Message-ID | <kbh6da$iie$1@smc.vnet.net> (permalink) |
| References | <kbbitr$9oc$1@smc.vnet.net> |
| Organization | Time-Warner Telecom |
Scott Hemphill <hemphill@hemphills.net> writes: [snip] > I decided to rate each team with a single number, such that the > probability that a team rated "r1" has a probability beating a team > rated "r2" is given by: > > p = CDF[NormalDistribution[], r1-r2]; Hmmm. I guess my code actually implements "r2-r1" instead of "r1-r2". It doesn't matter, except one way high ratings are better than low ratings, and the other is vice versa. > filename="matrix.m"; > prec; I don't know how this line got shortened. My original has "prec". Scott -- Scott Hemphill hemphill@alumni.caltech.edu "This isn't flying. This is falling, with style." -- Buzz Lightyear
Back to comp.soft-sys.math.mathematica | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
Modeling of NFL game results Scott Hemphill <hemphill@hemphills.net> - 2012-12-25 07:00 +0000
Re: Modeling of NFL game results Ray Koopman <koopman@sfu.ca> - 2012-12-27 10:02 +0000
Re: Modeling of NFL game results Scott Hemphill <hemphill@hemphills.net> - 2012-12-28 10:32 +0000
Re: Modeling of NFL game results Ray Koopman <koopman@sfu.ca> - 2012-12-27 10:02 +0000
Re: Modeling of NFL game results Scott Hemphill <hemphill@hemphills.net> - 2012-12-27 10:03 +0000
Re: Modeling of NFL game results Ray Koopman <koopman@sfu.ca> - 2012-12-28 10:32 +0000
Re: Modeling of NFL game results Scott Hemphill <hemphill@hemphills.net> - 2012-12-28 10:32 +0000
Re: Modeling of NFL game results Scott Hemphill <hemphill@hemphills.net> - 2012-12-29 20:08 +0000
csiph-web