[more than] everything you always wanted to know about marginal likelihood

Earlier this year, F. Llorente, L. Martino, D. Delgado, and J. Lopez-Santiago have arXived an updated version of their massive survey on marginal likelihood computation. Which I can only warmly recommend to anyone interested in the matter! Or looking for a base camp to initiate a graduate project. They break the methods into four families

1. Deterministic approximations (e.g., Laplace approximations)
2. Methods based on density estimation (e.g., Chib’s method, aka the candidate’s formula)
3. Importance sampling, including sequential Monte Carlo, with a subsection connecting with MCMC
4. Vertical representations (mostly, nested sampling)

Besides sheer computation, the survey also broaches upon issues like improper priors and alternatives to Bayes factors. The parts I would have done in more details are reversible jump MCMC and the long-lasting impact of Geyer’s reverse logistic regression (with the noise contrasting extension), even though the link with bridge sampling is briefly mentioned there. There is even a table reporting on the coverage of earlier surveys. Of course, the following postnote of the manuscript

The Christian Robert’s blog deserves a special mention , since Professor C. Robert has devoted several entries of his blog with very interesting comments regarding the marginal likelihood estimation and related topics.

does not in the least make me less objective! Some of the final recommendations

• use of Naive Monte Carlo [simulate from the prior] should be always considered [assuming a proper prior!]
  
• a multiple-try method is a good choice within the MCMC schemes
• optimal umbrella sampling estimator is difficult and costly to implement , so its best performance may not be achieved in practice
• adaptive importance sampling uses the posterior samples to build a suitable normalized proposal, so it benefits from localizing samples in regions of high posterior probability while preserving the properties of standard importance sampling
  
• Chib’s method is a good alternative, that provide very good performances [but is not always available]
• the success [of nested sampling] in the literature is surprising.

tree of the year 2015 felled for high speed train line

statistical inference and uncertainty quantification for complex process-based models using multiple data sets [postdoc in Warwick]

Applications are invited for a postdoctoral research fellow position to work on the project “Statistical inference and uncertainty quantification for complex process-based models using multiple data sets”.

The position is part of a project to develop, implement and apply methods for parameter inference of models of environmental processes: particularly approaches based on approximate Bayesian computation (ABC) and particle MCMC.

The project is funded through the UKRI Strategic Priorities Fund programme on “Landscape Decisions: Towards a new framework for using land assets”. This programme will address the challenge of delivering better, evidence-based decisions within UK landscapes through research collaboration with policy, business and land management partners to deliver an interdisciplinary decision-making framework to inform how land is used. The post holder will become part of the world-renowned Department of Statistics at the University of Warwick.

Informal enquires can be addressed to Dr Richard Everitt, with closing date 8 March 2020.

O’Bayes 2019 has now started!

The O’Bayes 2019 conference in Warwick University has now started, with about 100 participants meeting over four days (plus one of tutorials) in the Zeeman maths building of the University. Quite a change of location and weather when compared with the previous one in Austin. As an organiser I hope all goes well at the practical level and want to thank the other persons who helped me towards this goal, first and foremost Paula Matthews who solved web and lodging and planning issues all over these past months, as well as Mark Steel and Cristiano Villa. As a member of the scientific committee, I am looking forward the talks and discussants along the coming four days, again hoping all speakers and discussants show up and are not hindered by travel or visa issues…

O’Bayes 2019, more posters if you please!

As the announcement for O’Bayes 2019 appeared in the March issue of the IMS Bulletin I just received, let me call for further poster submissions to the meeting. The deadline for travel support submission is past, but poster submissions are welcomed till June 15. (Overlap with BNP12 is not an issue!) Submissions should be sent to me (gmail address: bayesianstatistics) as a one page pdf file. Registration is open, with accommodation options.