Blog Archives

Le Monde puzzle [48]

December 1, 2010
By
Le Monde puzzle [48]

This week(end), the Le Monde puzzle can be (re)written as follows (even though it is presented as a graph problem): Given a square 327×327 symmetric matrix A, where each non-diagonal entry is in {1,2,3,4,5} and , does there exist a triplet (i,j,k) such that Solving this problem in R is very easy. We can create

Read more »

Slices and crumbs [arXiv:1011.4722]

November 29, 2010
By
Slices and crumbs [arXiv:1011.4722]

An interesting note was arXived a few days ago by Madeleine Thompson and Radford Neal. Beside the nice touch of mixing crumbs and slices, the neat idea is to have multiple-try proposals for simulating within a slice and to decrease the dimension of the simulation space at each try. This dimension diminution is achieved via

Read more »

Computing evidence

November 28, 2010
By
Computing evidence

The book Random effects and latent variable model selection, edited by David Dunson in 2008 as a Springer Lecture Note. contains several chapters dealing with evidence approximation in mixed effect models. (Incidentally, I would be interested in the story behind the  Lecture Note as I found no explanation in the backcover or in the preface.

Read more »

Random graphs with fixed numbers of neighbours

November 24, 2010
By
Random graphs with fixed numbers of neighbours

In connection with Le Monde puzzle #46, I eventually managed to write an R program that generates graphs with a given number n of nodes and a given number k of edges leaving each of those nodes. (My early attempt was simply too myopic to achieve any level of success when n was larger than

Read more »

The joys of teaching R

November 23, 2010
By
The joys of teaching R

Just read a funny but much to the point blog entry on the difficulties of teaching proper programming skills to first year students! I will certainly make use of the style file as grading 180 exams is indeed a recurrent nightmare… Filed under: R,...

Read more »

Robust adaptive Metropolis algorithm [arXiv:10114381]

November 23, 2010
By
Robust adaptive Metropolis algorithm [arXiv:10114381]

Matti Vihola has posted a new paper on arXiv about adaptive (random walk) Metropolis-Hastings algorithms. The update in the (lower diagonal) scale matrix is where is the current acceptance probability and the target acceptance rate; is the current random noise for the proposal, ; is a step size sequence decaying to zero. The spirit of

Read more »

R.I.P. StatProb?

November 22, 2010
By
R.I.P. StatProb?

As posted in early August from JSM 2010 in Vancouver, StatProb was launched as a way to promote an on-line encyclopedia/wiki with the scientific backup of expert reviewers. This was completely novel and I was quite excited to take part in the venture as a representative of the Royal Statistical Society. Most unfortunately, the separation

Read more »

Graphical comparison of MCMC performance [arXiv:1011.445]

November 22, 2010
By
Graphical comparison of MCMC performance [arXiv:1011.445]

A new posting on arXiv by Madeleine Thompson on a graphical tool for assessing performance. She has developed a software called SamplerCompare, implemented in R and C. The graphical evaluation plots “log density evaluations per iteration times autocorrelation time against a tuning parameter in a grid of plots where rows represent distributions and columns represent

Read more »

Introducing Monte Carlo in PaRis [more slides]

November 17, 2010
By
Introducing Monte Carlo in PaRis [more slides]

The class started yesterday with a small but focussed and responsive audience! Given the background of the students, and in particular their clear proficiency in R!, I switched between the original slides of Introducing Monte Carlo Methods with R and those of my Monte Carlo Statistical Methods: course, updated by Olivier Cappé who is teaching

Read more »

Postdoc in Wharton

November 16, 2010
By
Postdoc in Wharton

Just received this email from José Bernardo about an exciting postdoc position in Wharton: POST-DOCTORAL FELLOW – DEPARTMENT OF STATISTICS, THE WHARTON SCHOOL The Department of Statistics at The Wharton School of the University of Pennsylvania is seeking candidates for a Post-Doctoral Fellowship. This research fellowship provides full funding without any teaching requirements at a

Read more »