Someone sent me a link to this story about a mathematical model of a particular serial killer’s behavior. Two things struck me about it:

1. How much it sounded like the kind of bizarre model you’d see on Charline on Numb3rs come up with in order to crack the case.
2. That Cosma Shalizi would hate the model, since it’s the kind of a casual use of power laws he regularly criticizes. And here’s his analysis of the paper. He points out that, as in many other cases, a lognormal distribution provides a better fit.

From the request thread, I was hoping for a nice easy softball, maybe from an undergraduate or mathematical amateur. Apparently, though, I have finally scared off anyone other than procrastinating professional mathematicians, who want me to actually write the posts I promised.

In the comments here I promised a post explaining why most statistics satisfy the Central Limit Theorem. I thought I’d start slowly with an explanation of what a statistic is.

A statistic is just something you compute from the data. This definition is so uninteresting that statistics books are a little apologetic about how contentless the definition sounds. (This usage of the term “statistic” was coined by Fisher. There is a cutting quote by Pearson on the terminology that is impossible to Google for, since all I remember is that it’s about the word statistic, and it involves Fisher and Pearson, who are probably the two most famous statisticians.)

Probability distributions are mathematical abstractions, while statistics are numbers we compute from actual data. If we believe that we can model that data as if it is generated by a random variable, then we have to relate the statistic to some property of the probability distribution. Usually, we are interested in some property of the underlying distribution, and using statistics to estimate it. For example, we may be interested in the mean of the underlying random variable, which we can approximate by using the mean of data.

Approximating the mean of the random variable in this way is a special case of a general technique to compute a property of a random variable. A random sample drawn from a probability distribution can be thought of as a (discrete) probability distribution in its own right. The property for the sample distribution can be used as an estimate of the property for the true distribution — this is known as the plug-in estimate for the property. An analog of the law of large numbers shows that this estimate converges to the true value.

Next time: the analogue of the central limit theorem.

I promised a while back to write a post describing why so many statistics have a central limit theorem. I went to the library to look up the result I had in mind, to refresh my memory as to the details. The book I wanted was checked out. I thought about requesting the book, but it seemed a bit much to request a book just for a blog post. A couple of days later, I found out who had the book checked out: me.