John;

Hi!

Congrats on the new job (I guess) altho it sounds like a step down in some ways.

> I think Roger means this: assigning Don's predictions random dates instead of the dates Don actually specified gives 21 hits, on average, although once in 10,000 tries, the random choice yielded 40 hits.

Not quite. We're comparing a random number to a real probability and counting number of times random is smaller.

Roger