MCMSki IV, Jan. 6-8, 2014, Chamonix (news #5)

More exciting news about MCMSki IV!

First thing first, the 16 contributed sessions are now all-set, having gotten the stamp of approval from the scientific committee! Thanks to everyone who submitted a session proposal. (There were so many proposals that we alas had to reject some, as well as every single talk proposal… Sorry people: we hope to hear about your research advances via your posters!) See the MCMSki IV website for the whole list. Apart from the plenary lectures, and the round table on software held on the second evening, there will be three parallel sessions on the remaining three slots for each day of the conference, which means 25 sessions total!

Second, the “call for posters” is open, simply meaning that anyone wishing to present a poster at MCMSki IV on Monday evening (or Tuesday night if we cannot accommodate all posters within a single evening!) is welcome to do so! This will take place in the conference centre as well (with an open bar to keep up with traditions) To this effect, if you intend to present a poster, (a) tick the box in the registration form and (b) …wait for further instructions on the MCMSki IV website about sending your abstract as we are trying to find an easy way to store and publish posters there. Simple as AB(C)!

Last, the registration page is now open! So fell free to register at your earliest convenience. The deadline for early bird registration is October 15, 2013 however hotel rooms are likely to vanish much earlier than that, leaving you on your own to find accommodation in Chamonix (not such a terrible task, actually!)

BayesComp homepage

Today, the BayesComp section of ISBA launched its website. It is organised as a wiki and members of the section are strongly incited to take part into the construction of the website. To quote from Peter Green’s introduction:

This new Wikidot site aims to be a community-edited resource on all aspects of Bayesian computation, available for all to read; here ‘community’ means members of the section – we hope that interested members will help us create pages of information and advice to help disseminate new research ideas in an accessible way, and promote good practice. Members can also submit links to a directory of papers, slides, videos and software, and to a diary of upcoming events such as conferences and workshops, all through easy-to-use forms.

Please visit BayesComp, read the Quick Start Guide there, actively contribute to the site’s content, and let us have feedback using the blog facility provided. Once you have editing credentials on the site, you do not need permission to make edits, just do it! Section officers may tidy things up later, if no one else does, but we won’t delete anything unless it is offensive or plainly wrong.

Thanks to the inputs of Peter Green and of Nicolas Chopin, this could be a wonderful exchange tool for the community, but only if this community strives to keep it alive!

painful truncnorm

As I wanted to simulate truncated normals in a hurry, I coded the inverse cdf approach:

truncnorm=function(a,b,mu,sigma){
  u=runif(1)
  u=qnorm(pnorm((a-mu)/sigma)*(1-u)+u*pnorm((b-mu)/sigma))
  return(mu+sigma*u)
  }

instead of using my own accept-reject algorithm. Poor shortcut as the method fails when a and b are too far from μ

> truncnorm(1,2,3,4)
[1] -0.4912926
> truncnorm(1,2,13,1)
[1] Inf

So I introduced a control (and ended up wasting more time than if I had used my optimised accept-reject version!)

truncnorm=function(a,b,mu,sigma){
  u=runif(1)
  if (pnorm((b-mu)/sigma)-pnorm((a-mu)/sigma)>0){
    u=qnorm(pnorm((a-mu)/sigma)*(1-u)+u*pnorm((b-mu)/sigma))
  }else{
    u=-qnorm(pnorm(-(a-mu)/sigma)*(1-u)-u*pnorm(-(b-mu)/sigma))}
  return(mu+sigma*u)
  }

As shown by the above, it works, even when a=1, b=2 and μ=20. However, this eventually collapses as well and I ended up installing the msm R package that includes rtnorm, an R function running my accept-reject version. (This package was written by Chris Jackson from the MRC Unit in Cambridge.)

CHANCE: special issue on George Casella’s books

The special issue of CHANCE on George Casella’s books has now appeared and it contains both my earlier post on George passing away and  reviews of several of his books, as follows:

• Andrew Gelman on Introducing Monte Carlo Methods with R
• Bill Strawderman on Statistical Inference
• Jean-Louis Foulley on Variance Components
• Larry Wasserman on Theory of Point Estimation
• Xiao-Li Meng on Monte Carlo Statistical Methods

Although all of those books have appeared between twenty and five years ago, the reviews are definitely worth reading! (Disclaimer: I am the editor of the Books Review section who contacted friends of George to write the reviews, as well as the co-author of two of those books!) They bring in my (therefore biased) opinion a worthy evaluation of the depths and impacts of those major books, and they also reveal why George was a great teacher, bringing much into the classroom and to his students… (Unless I am confused the whole series of reviews is available to all, and not only to CHANCE subscribers. Thanks, Sam!)

off to Florida

Today I am off (again!) to Florida, taking part in the Winter Workshop at the University of Florida, Gainesville. The theme this year is New Directions in Monte Carlo Methods. I am quite excited to meet again with many old friends (this almost sounds like a rehearsal for MCMSki 4!), but also sad that George Casella who would have been my oldest friend there will be missing. Dearly missing and missed. At the same time, I appreciate that this workshop gives me the opportunity to meet at last with George’s family (with whom I share so many memories) and his colleagues at UFL. I am sure we will have plenty of pizzas, wine(s), and laughs in remembrance of the numerous good times we all had with George. And I will run the streets we ran together, quite a while ago…