OK, I'll use the same model I use for text. The zeroth-order model is maxentropy, and the kth-order model is a k-gram model with a pseudocount of 2 (the alphabet size) allocated to the (k-1)th-order model.
In this case, since there's never before been a Thursday in which she did not call, we default to the 1st-order model, which says the probability is 3/4 that she will come on Friday.
OK, I'll use the same model I use for text. The zeroth-order model is maxentropy, and the kth-order model is a k-gram model with a pseudocount of 2 (the alphabet size) allocated to the (k-1)th-order model.
Is this a standard model? Does it have a name? a reference?
I see that the level 1 model is Laplace's rule of succession. Is there some clean statement about the level k model? Is this a bayesian update?
...In this case, since there's never before been a Thursday in which she did not call, we default to the 1st-order model, which says the probability is 3
We've had these for a year, I'm sure we all know what to do by now.
This thread is for the discussion of Less Wrong topics that have not appeared in recent posts. If a discussion gets unwieldy, celebrate by turning it into a top-level post.