Monthly Archives: August 2014

If you give a man a fish …

“If you give a man a fish he is hungry again in an hour.  If you teach him to catch a fish you do him a good turn.  But, if instead you convince him that catching fish is far too … Continue reading

Posted in Uncategorized | 3 Comments

Classic paper review: Tierney (1994) …

As I mentioned in the update to my previous post, I’ve lately been having a careful read through a classic paper on MCMC algorithms: Tierney (1994).  One interesting property of Tierney’s ‘Markov chains for exploring posterior distributions’ is that of its … Continue reading

Posted in Uncategorized | Leave a comment

“Mixed MCMC” …

It will be no surprise to my readers that this paper on astro ph today concerning “mixed MCMC” by Hu, Hendry & Heng got my back up since three of my pet hates appear early on in the manuscript: (i) the … Continue reading

Posted in Uncategorized | Leave a comment

The bitch is back again: the hubris of astronomers …

Yesterday I was having some back and forth on Facebook with Till Sawala about the relative standards of statistical practice in medicine and astronomy prompted by this article by Carlos Frenk in which he suggests the widespread problems identified recently in the … Continue reading

Posted in Uncategorized | 1 Comment

The bitch is back (to quote Elton John): on testing for bimodality …

I noticed this paper by Zafar et al. presenting “Evidence of bimodality in the [N/alpha] distribution” in damped Lyman alpha absorbers (accepted to MNRAS), which is to my mind quite indicative of the poor level of statistics in astronomy—both amongst practitioners … Continue reading

Posted in Uncategorized | Leave a comment

En vacances …

On holiday in the Ardeche this week where there is negligible internet and minimal motivation to check in with astro ph …… perhaps next week I will have recovered sufficiently to try mixture modelling in JAGS of the data (some … Continue reading

Posted in Uncategorized | Leave a comment