Category Archives: probabilistic programming
(Updated 2016-05-08, to provide reference for plateaus of ML functions in vicinity of MLE.) Simpson’s Paradox is one of those phenomena of data which really give Statistics a substance and a role, beyond the roles it inherits from, say, theoretical … Continue reading
Source: Grid shading by simulated annealing (or what I did on my holidays), aka “fun with GCHQ job adverts”, by Martyn Plummer, developer of JAGS. Excerpt: I wanted to solve the puzzle but did not want to sit down with … Continue reading
Inspired by the extensive and excellent work in approximate Bayesian computation (see also), especially that done by Professors Christian Robert and colleagues (see also), and Professor Simon Wood (see also), it occurred to me that the complaints regarding lack of … Continue reading
What will the energy landscape look like after utility companies are either dead, dying, or revert to a tiny portion of their territory? Silicon Valley CCE Partnership gives us all a clue. It’s been described in the San Francisco Chronicle, … Continue reading
Australia’s first grid-connected solar power project with cloud predicting technology launched at Karratha Airport, WA, in bid to smooth solar supply. Source: Solar array with cloud predicting technology launched in WA
Originally posted on Open Mind:
To all the readers who make this blog worth writing: Thank you. Thank you for sharing my work. One of the things that makes me proud is that often my blog posts are used as…
Cauchy Distribution: Evil or Angel?. From Professor Christian Robert.
Originally posted on Xi'an's Og:
Over the past week, I wrote a short introduction to the Metropolis-Hastings algorithm, mostly in the style of our Introduction to Monte Carlo with R book, that is, with very little theory and…
Unbiased Bayes for Big Data: Path of partial posteriors.
Professor Christian Robert remarks on the amazing Gibbs sampler. Implicitly he’s also underscoring the power of properly done Bayesian computational analysis. For here we have a problem with a posterior distribution having two strong modes, so a point estimate, like … Continue reading
Originally posted on …and Then There's Physics:
Okay, I finally succumbed and actually waded through some of the new paper by Monckton, Soon, Legates & Briggs called Why models run hot: results from an irreducibly simple climate model. I…
This is from today’s news in Science. The full citation is: M. Bowling, N. Burch, M. Johanson, O. Tammelin, “Heads-up limit hold’em poker is solved”, Science, 9 January 2015, 347(6218), 145-149, http://dx.doi.org/10.1126/science.1259433. See also a University of Alberta site where … Continue reading
I’m digging into the internals of ABC, for professional and scientific reasons. I’ve linked a great tutorial elsewhere, and argued that this framework, advanced by Wood, and Wilkinson (Robert), and Wilkinson (Darren), and Hartig and colleagues, and Robert and colleagues, … Continue reading
Professor Darren Wilkinson offers a pithy insight on how to go about constructing statistical models, notably hierarchical ones: “… we want to model the process as we would simulate it ….” This appears in his blog post One-way ANOVA with … Continue reading
Climate modelers and models see as their frontier the problem of dealing with spontaneous dynamics in systems such as atmosphere or ocean which are not directly forced by boundary conditions such as radiative forcing due to increased greenhouse gas (“GHG”) … Continue reading
illustrating particle filters and Bayesian fusion using successive location estimates on the unit circle
Introduction Modern treatments of Bayesian integration to obtain posterior densities often use some form of Markov Chain Monte Carlo (“MCMC”), typically Gibbs sampling. Gibbs works well with many Bayesian hierarchical models. The standard problem-solving situation with these is that a … Continue reading
By Tomoharu Eguchi from 2008: “An Introduction to Bayesian Statistics Without Using Equations“.
This is based upon my solution of Exercise 2.3, page 18, R. Christensen, W. Johnson, A. Branscum, T. E. Hanson, Bayesian Ideas and Data Analysis, Chapman & Hall, 2011. The purpose is to show how information latent in a set … Continue reading
Consider trying to determine the length of a straight stick. Instead of the measurement errors being clustered about zero, suppose the errors are known to be always positive, that is, no measurement ever underestimates the length of the stick. Such … Continue reading
This is a sketch of how maths and statistics can do something called blind source separation, meaning to estimate the components of data given only their totals. Here, I use Bayesian techniques for the purpose, sometimes called Bayesian inversion, using … Continue reading
Bayesians have all been there. Some of us don’t depend upon producing publications to assure our pay, so we less have the pressure of pleasing peer reviewers. Nonetheless, it’s all reacting to “What the hell are you doing? I don’t … Continue reading
How fast is JAGS?.
The New York Times has an article titled “How urban anonymity disappears when all data is tracked” by Quentin Hardy which appears in its “Bits” section. I just posted a comment on that article, which is reproduced below: I hope … Continue reading
The most common fallacy in discussing extreme weather events.
Good to see Dr Dave Gallo speaking about WHOI’s approach to AF447 and its similarity to MH370. Update. 2014-03-26. WHOI is getting ready to deploy their REMUS 6000 systems. Update. 2014-03-28. The Woods Hole Oceanographic Institution has offered its expertise … Continue reading
BUGS has a “zeros trick” (Lund, Jackson, Best, Thomas, Spiegelhalter, 2013, pages 204-206; see also an online illustration) for specifying a new distribution which is not in the standard set. The idea is to couple an invented-for-the-moment Poisson density to … Continue reading
Happened across this today … I could not agree more: “Data-driven science is a failure of imagination” by Petr Keil. I look forward to reading his posts on Bayesian statistics.