Good advice from Density Estimation for Statistics and Data Analysis by Bernard. W. Silverman:
Category Archives: statistics
A student came by interested in survey statistics and we go to talking about what an amazing person Leslie Kish must have been. We did some googling on it. Here are a few items we found:
I’ve got a fun class going this quarter, on “artificial intelligence for health metricians”, and the course content mixed with some of the student interest has got me looking at the options for doing Gaussian process regression in Python. `PyMC2` has some nice stuff, but the `sklearn` version fits with the rest of my course examples more naturally, so I’m using that instead.
But `sklearn` doesn’t have the fanciest of fancy covariance functions implemented, and at IHME we have been down the road of the Matern covariance function for over five years now. It’s in `PyMC`, so I took a crack at mash-up. (Took a mash at a mash-up?) There is some room for improvement, but it is a start. If you need to do non-parametric regression for something that is differentiable more than once, but less than infinity times, you could try starting here: http://nbviewer.ipython.org/gist/aflaxman/af7bdb56987c50f3812b
p.s. Chris Fonnesbeck has some great notes on doing stuff like this and much more here: http://nbviewer.ipython.org/github/fonnesbeck/Bios366/blob/master/notebooks/Section5_1-Gaussian-Processes.ipynb
Is there a nice, simple reference for just what exactly these graphical model figures mean? I want more of them.
I wanted to include some old-fashioned statistics in a paper recently, and did some websearching on how to calculate R^2 in Python. It’s all very touchy, it seems. Here’s what I found:
I eventually went with this:
%load_ext rmagic x = np.array(1/df.J) y = np.array(df.conc_rand) %Rpush x y %R print(summary(lm(y ~ x + 0)))
I should read some of these, and stash a few for the PGF journal club:
I like answering PyMC questions on Stack Overflow, but sometimes I give an answer and end up the one with the question. Like what would you model as the sum of a Poisson and a Negative Binomial?