I re-read a short paper of Andrew Gelman’s yesterday about multilevel modeling, and thought “That would make a nice example for PyMC”. The paper is “Multilevel (hierarchical) modeling: what it can and cannot do, and R code for it is on his website.
To make things even easier for a casual blogger like myself, the example from the paper is extended in the “ARM book”, and Whit Armstrong has already implemented several variants from this book in PyMC. Continue reading
Filed under MCMC, statistics
(Updated 9/2/2009, but still unfinished; see other’s work on this that I’ve collected)
I never took a statistics class, so I only know the kind of statistics you learn on the street. But now that I’m in global health research, I’ve been doing a lot of on-the-job learning. This post is about something I’ve been reading about recently, how to decide if a simple statistical model is sufficient or if the data demands a more complicated one. To keep the matter concrete (and controversial) I’ll focus on a claim from a recent paper in Nature that my colleague, Haidong Wang, choose for our IHME journal club last week: Advances in development reverse fertility declines. The title of this short letter boldly claims a causal link between total fertility rate (an instantaneous measure of how many babies a population is making) and the human development index (a composite measure of how “developed” a country is, on a scale of 0 to 1). Exhibit A in their case is the following figure:
An astute observer of this chart might ask, “what’s up with the scales on those axes?” But this post is not about the visual display of quantitative information. It is about deciding if the data has a piecewise linear relationship that Myrskyla et al claim, and doing it in a Bayesian framework with Python and PyMC. But let’s start with a figure where the axes have a familiar linear scale! Continue reading
Filed under MCMC, statistics
I’ve got an urge to write another introductory tutorial for the Python MCMC package PyMC. This time, I say enough to the comfortable realm of Markov Chains for their own sake. In this tutorial, I’ll test the waters of Bayesian probability.
Now, what better problem to stick my toe in than the one that inspired Reverend Thomas in the first place? Let’s talk about sex ratio. This is also convenient, because I can crib from Bayesian Data Analysis, that book Rif recommended me a month ago.
Bayes started this enterprise off with a question that has inspired many an evolutionary biologist: are girl children as likely as boy children? Or are they more likely or less likely? Laplace wondered this also, and in his time and place (from 1745 to 1770 in Paris) there were birth records of 241,945 girls and 251,527 boys. In the USA in 2005, the vital registration system recorded 2,118,982 male and 2,019,367 female live births . I’ll set up a Bayesian model of this, and ask PyMC if the sex ratio could really be 1.0.