Why "naive Bayes" is not Bayesian
Explains why the so-called “naive Bayes” classifier is not Bayesian. The setup is okay, but estimating probabilities by doing relative frequencies instead of using Dirichlet conjugate priors or integration strays from The Path.
While it is described as “The mathematical (and other) thoughts of a (now retired) math teacher”, this is false humility, as it chronicles the present and past life and times of mathematicians in their context. Recommended.
Darren Wilkinson's introduction to ABC
Darren Wilkinson’s introduction to approximate Bayesian computation (“ABC”). See also his post about summary statistics for ABC https://darrenjw.wordpress.com/2013/09/01/summary-stats-for-abc/
Isaac Held's blog
In the spirit of Ray Pierrehumbert’s “big ideas come from small models” in his textbook, PRINCIPLES OF PLANETARY CLIMATE, Dr Held presents quantitative essays regarding one feature or another of the Earth’s climate and weather system.
The Keeling Curve
The first, and one of the best programs for creating a spatially significant long term time series of atmospheric concentrations of CO2. Started amongst great obstacles by one, smart determined guy, Charles David Keeling.
I have used dlm almost exclusively, except when extreme efficiency was required. Since Jouni Helske's KFAS was rewritten, though, I'm increasingly drawn to it, because the noise sources it supports are more diverse than dlm's. KFAS uses the notation and approaches of Durbin, Koopman, and Harvey.
``The real problem is that programmers have spent far too much time worrying about efficiency in the wrong places and at the wrong times; premature optimization is the root of all evil (or at least most of it) in programming.'' Professor Donald Knuth, 1974