Statistics

Coin, queries, and screening

Work has caught up with me yet again, so here are three interesting stories to wile the time away.

The probability of a coin flip

Reader Ari Schwartz sent in this link, from Slate, a book excerpt from David Adler. He quotes from Persi Diaconis and Susan Holmes, who discover that coin flips are predictable if you know their initial conditions. Regular readers won’t be shocked by this (Persi was briefly my advisor at Cornell, and Susan is his wife; they are now at Stanford).

Three academics—Persi Diaconis, Susan Holmes, and Richard Montgomery—through vigorous analysis made an interesting discovery at Stanford University. As they note in their published results, “Dynamical Bias in the Coin Toss,” laws of mechanics govern coin flips, meaning, “their flight is determined by their initial conditions.”

I’m not keen all of Adler’s language, but the story is worth reading.

Screening for terrorists

The BBC ran a piece that shows that false positives and false negatives in screening for terrorists are important. This is the standard Bayes Theory introduction, and is never stale. Here it is on mammograms.

How do you spell condescension?

Charles Murray has a new book on why so many people shouldn’t go to college. We talked about this here and here.

In an earlier interview, Murray states what I have always found obvious: some people are smarter than others (we only disagree on the validity of “IQ” as a measure of this). His Times interlocutor—her superiority liquid and dripping—says, “I believe that given the opportunity, most people could do most anything.”

This is utterly false and a fact so well known it is always breathtaking to hear somebody utter it.

Categories: Statistics

5 replies »

  1. The paper looks interesting.

    But certain people…can make it come out heads (or tails) 100 percent of the time. Diaconis…is one of the people with this amazing talent.

    I guess there are X-men among us. I am willing to pay to see a demonstration by Diaconis.

  2. My high school math teacher told me about “the gambler’s” falicy. If a coin has come up heads 10 times in a row, what is the chance it will come up heads on the 11th flip? He told me 50%.

    He couldn’t be more wrong. If a coin comes up 10 row, there is probably something going on that you haven’t been told.

  3. “His Times interlocutor…says, “I believe that given the opportunity, most people could do most anything.” ” Don’t worry; she may pay lip service to this proposition but you can be confident that she lives her life in contradiction of it.

  4. I’m sure if I’d only been given the opportunity, I could be a successful quarterback for the Chicago Bears. Unfortunately, I was deprived of the appropriate athletic training, growth hormone and steroids as a child.

  5. Gee, I wonder what the probability was that a black Harvard professor of English and Afro American Studies, a recipient of racial profiling affirmative action programs, would not accuse a white cop of racial profiling before his arrest for disorderly porch conduct?

Leave a Reply

Your email address will not be published. Required fields are marked *