After losing both ends of a slow pitch softball double header this past Sunday, I showed up at my friend’s (Mike) house to watch football. Dejected, I brought over the remnants of a 12 pack of Miller Light from the previous weekend. The following exchange then took place:

Mike: “Ugh. Miller Light”
Me: “It all the same. Miller Light, Bud Light, Coors Light….”
Mike: “No way. It’s easy to tell the difference.”
Me: “Oh yeah. Prove it.”

This led to a trip to the the store for red plastic cups and pizza. I brought Miller Light, and he had Bud Light in his fridge. So it was the Bud Light versus Miller Light challenge.

So we set it up. A modern day frat house version of Fisher’s lady tasting tea experiment. 8 cups. 4 Bud Light. 4 Miller Light.

Now, Mike claimed that not only could he tell that there was a difference, he could tell which beer was which without any point of reference (besides his entire life experience). This meant he claimed to be able to drink the first cup and name which beer it was without contrasting it against any other cup. Quite the claim.

Out of 8 cups, Mike figured if he got 6 correct that should prove that he can tell the difference. However, correctly identifying 6 of 8 yields a one sided p-value of 0.243. Good, but hardly statistical proof. Usually a p-value of <.05 is required. So, Mike had to go 8 for 8 to prove it to me. (A p-value of 0.0143).

Well, after some dramatics and going back and changing a guess, our hero Michael did go 8 for 8. A true connoisseur of light beer. Congratulations. (Or condolences, depending on your view).

As for me, I can't tell the difference and went 2 for 8 cause it's all the same.

Cheers.

Looks like Brian Urlacher is out for the year. I wonder how much this injury will affect the Bears (0-1), who looked terrible with Mr. Cutler as their quarterback.

If only there was a place to look up this kind of information. Some sort of network of inter-connected ideas…..

I was poking around the Freakonomics blog, and they link to an article in the New York Times by Brian Barnwell who discusses the impact of injuries on football teams. The article is here.
And the Freakonomics post is here.

Cheers.

R graph gallery

Cheers.

Last year I challenged this guy in the department to a battle of picking colllege football games. We both started with a bankroll of $10,000 (play money of course because (1) we have no money (grad students) and (2) gambling is illegal (and immoral…)) and we had to pick at least five games every week and wager at least 5 percent of our bank roll each week. Long story short, this guy killed me last year. I ended the season with 0 (at the end of the season I was betting my whole bank roll every week to try to catch up), and he ended up not at zero for the victory. Of course I was essentially randomly choosing games and his picks were based on data.

So again this year I challenged him to the same competititon. He killed me in week one even though I went 4-1. So I’ve decided that what I need is a model. I don’t want to get too technical cause I jsut threw this thing to gether, but it seems to give reasonable results.

So I am using a Poisson regression model and I am modelling offense and defense as entirely separate teams. I am essentially using all of the 2008-09 season as my priors for team (offense and defense) parameters. Then, using week 1 results as my data, I draw values from the posterior predictive distribution of “games” (I consider one teams offense against another teams defense a “game” in the model.) I call WinBUGS from R and generate 6000 iterations (burning off the first 1000). Then I take the median score from the draws and that is my prediction for the game.

So here are some predictions for the week. We’ll see how this model works.
Top 25:
(1)Florida 20 Troy 10
(2)Texas 53 Wyoming 20
(3)USC 21 (8)Ohio State 11
(4) Alabama 30 FIU 17
Houston 21 (5) Oklahoma State 16
(6) Mississippi BYE
(7) Penn State 29 Syracuse 13
(10) California 26 Eastern Washington 15
Vanderbilt 40 (11) LSU 9
(12) Boise State 37 Miami (Ohio) 3
(13)Oklahoma 54 Idaho State 10
(14) Virginia Tech 46 Marshall 33
(15) Georgia Tech 48 Clemson 16 (GT won this game already)
(16) TCU 28 Virginia 3
(17) Utah 57 San Jose State 6
(18) Notre Dame 33 Michigan 7
(19) North Carolina 27 UConn 12
(20) Miami (FL) BYE
(21) Georgia 13 South Carolina 10
(22) Nebraska 18 Arkansas State 6
(23) Cincinnati 50 Southeast Missouri State 8
(24) Kansas 77 UTEP 7
(25) Missouri 69 Bowling Green State 18

Cheers.

Apparently more boys than girls are being born. Here is a full report by the CDC.

Cheers.

How do people around the world spend their money? If only there was some sort of interactive chart showing this.

Here is an interactive hart showing what the world spends its money on. (I saw this on chartporn.org)

Cheers.

My friend had an interview with Google during which they asked him this interesting question:
A man gets on a plane with n seats, but he has lost his ticket. So this man randomly chooses a seat. The next guy gets on the plane with his ticket. He goes to his seat, if it is empty, he sits there. If it is taken, he randomly chooses a seat. This continues until n-1 seats are filled. The n-th person enters the plane with his ticket. He goes to his seat. What is the probability that it is empty?

Answer

Cheers.

“A critique of Chernoff faces.”

Cheers.

“37 Data-ish Blogs You Should Know About.”

Cheers.

If graphical displays of data get you going, you should go to Chartporn.org.

Cheers.