Category Archives: Uncategorized
While watching the ending to the Texas/Cincinnati NCAA tournament game, it felt like deja vu. Because it was. In other big games this season, Texas’ deficit followed a similar course.
This is game-flow data (moving left to right) compared to the advantage/deficit in points at a particular time during the game.
A classical problem in probability, which I learned about from Freedman, Pisani, and Purves’ book Statistics (pp. 238-240 in the fourth edition) is that of Galileo’s dice. Galileo was asked why, when rolling three fair dice, a sum of ten occurs more often than a sum of nine; he answered this question in Concerning an Investigation on Dice (from the University of York’s history of statistics page). It had previously been argued that since
10 = 6 + 3 + 1 = 6 + 2 + 2 = 5 + 4 + 1 = 5 + 3 + 2 = 4 + 4 + 2 = 4 + 3 + 3
and
9 = 6 + 2 + 1 = 5 + 3 + 1 = 5 + 2 + 2 = 4 + 4 + 1 = 4 + 3 + 2 = 3 + 3 + 3
View original post 575 more words
Super Bowl Squares
I received an email this morning from a friend: “Is there any sort of a statistical breakdown for which are the best numbers to have in a Super Bowl squares pool (for entertainment purposes only)?”
Now, if my friend were going to use this information to gamble, it would be highly unethical. However, since he clearly stated that it was for “entertainment purposes only,” I feel that I can conduct a study with a clear conscience.
If he had wanted to gamble on it, here is a quick explanation of how that usually takes place. (According to that website: “Basically, if you are at a party where you don’t have betting squares you are a Communist.”)
Anyway, using data from football-reference.com I created a ten by ten frequency table (using R, of course) of exactly how many times each outcome has occurred in the history of the NFL. You can find the graph here.
Somethings to note:
- 2-2 is the worst square by far. It’s only happened 5 times in the history of the league. The fair odds for this square are over 2800-to-1.
- The best squares are, no surprise, 7-0 and 0-7, occurring 581 and 577 times, respectively.
- The other great squares to have are in order, 0-3, 0-4, 4-7, and 7-4. All of these have occurred over 480 times each.
- These 6 outcomes (7-0, 0-7, 0-3, 0-4, 4-7, and 7-4) account for almost 23% of all the NFL games ever played.
Cheers.
Rule for Variance Inflation Factors
A quote from here:
“Goldberger (1991) notes that while the number of pages in econometrics
texts devoted to the problem of multi-collinearity in multiple regression is
large the same books have little to say about sample size. Goldberger states:
“Perhaps that imbalance is attributable to the lack of an exotic polysyllabic
name for ‘small sample size.’ If so, we can remove that impediment by introducing the term micronumerosity” (Goldberger, 1991: 248–249).”
Cheers.
NFL Rankings – After Week 17
Rankings updated as of 1/1/2012; Records updated as of 1/1/2012; CHFF rankings as of 12/28/2011
AFC NFC
Playoff team
Division Champ
Eliminated from Playoffs
| Team | Rank | Change | Record | CHFF Rank |
| New England | 1 | – | 13-3 | 3 |
| Pittsburgh | 2 | ↑ | 12-4 | 1 |
| Green Bay | 3 | ↓ | 15-1 | 6 |
| Baltimore | 4 | – | 12-4 | 5 |
| Atlanta | 5 | – | 10-6 | 11 |
| 6 | ↑ | 8-8 | 2 | |
| New Orleans | 7 | ↓ | 13-3 | 15 |
| 8 | – | 8-8 | 23 | |
| Detroit | 9 | ↑↑ | 10-6 | 10 |
| San Francisco | 10 | – | 13-3 | 4 |
| NY Giants | 11 | ↓↓ | 9-7 | 8 |
| 12 | – | 8-8 | 12 | |
| 13 | – | 8-8 | 18 | |
| 14 | ↑ | 4-12 | 14 | |
| 15 | ↑↑ | 7-9 | 30 | |
| 16 | ↑↑↑↑ | 7-9 | 9 | |
| 17 | ↓↓↓ | 8-8 | 26 | |
| Cincinnati | 18 | ↓↓ | 9-7 | 22 |
| 19 | ↑↑ | 8-8 | 7 | |
| 20 | ↑↑ | 9-7 | 19 | |
| 21 | ↓↓↓ | 6-10 | 13 | |
| Houston | 22 | ↓↓↓ | 10-6 | 20 |
| 23 | – | 6-10 | 24 | |
| 24 | ↑ | 2-14 | 16 | |
| Denver | 25 | ↓ | 8-8 | 30 |
| 26 | ↑↑↑↑ | 5-11 | 28 | |
| 27 | ↓ | 3-13 | 27 | |
| 28 | ↓ | 4-12 | 21 | |
| 29 | ↓ | 8-8 | 29 | |
| 30 | ↓ | 5-11 | 25 | |
| 31 | – | 6-10 | 17 | |
| 32 | – | 2-14 | 32 |
BCS: My offer still stands…….if you want to contact me you can send me a tweet @StatsInTheWild.
Cheers.
Yates and significance tests
I was reading the newest issue of Significance Magazine last night, and I came across this quote in a letter that someone had written to the magazine:
The emphasis given to formal tests of significance throughout [R.A. Fisher’s] Statistical Methods…has caused scientific research workers to pay undue attention to the results of the tests of significance they perform on their data, particularly data derived from experiments, and too little to the estimates of the magnitude of the effects they are investigating.” … “The emphasis on tests of significance and the consideration of the results of each experiment in isolation, have had the unfortunate consequence that scientific workers have often regarded the execution of a test of significance on an experiment as the ultimate objective. (Yates 1951)
I feel like this is extremely relevant today where it seems that the only thing anyone ever cares about in studies is the p-value and whether or not it is less than the mythical 0.05 cut-off. But what strikes me most about this quote is that it was written sixty years ago in 1951.
Cheers.
Statisticians are special because…..
From Andrew Gelman’s Blog: “P.S. Statisticians are special because, deep in our bones, we know about uncertainty. Economists know about incentives, physicists know about reality, movers can fit big things in the elevator on the first try, evolutionary psychologists know how to get their names in the newspaper, lawyers know you should never never never talk to the cops, and statisticians know about uncertainty. Of that, I’m sure.”
Stats in the Wild 
