at the centre of Bayes

2:14:04!!!

HW AMS & EPSRC MAG-MIGS CDT seminar

Some explanation for all these acronyms! I am giving a Actuarial Mathematics & Statistics (AMS) seminar at Heriot-Watt (HW) University, in Edinburgh, tomorow. But in the (new) Bayes Centre, at the University of Edinburgh, rather than on the campus of Heriot-Watt, as this is also the launching day of the Centre for Doctoral Training (CDT) on Mathematical Modelling, Analysis, & Computation (MAG) shared between Heriot-Watt, and the University of Edinburgh, funded by the EPSRC and located in the Maxwell Institute Graduate School (MIGS) in its Bayes Centre. My talk will be on ABC convergence and misspecification.

Nature worries

In the 29 August issue, worries about the collapse of the Italian government coalition for research (as the said government had pledge to return funding to 2009 [higher!] levels), Brexit as in every issue (and the mind of every EU researcher working in the UK), facial recognition technology that grows much faster than the legal protections which should come with it, thanks to big tech companies like Amazon and Google. In Western countries, not China… One acute point in the tribune being the lack of open source software to check for biases. More worries about Amazon, the real one!, with Bolsonaro turning his indifference if not active support of the widespread forest fires into a nationalist campaign. And cutting 80,000 science scholarships. Worries on the ethnic biases in genetic studies and the All of Us study‘s attempt to correct that (study run by a genetic company called Color, which purpose is to broaden the access to genetic counseling to under-represented populations). Further worries on fighting self-citations (with John Ioannidis involved in the analysis). With examples reaching a 94% rate for India’s most cited researcher.

ABC-SAEM

In connection with the recent PhD thesis defence of Juliette Chevallier, in which I took a somewhat virtual part for being physically in Warwick, I read a paper she wrote with Stéphanie Allassonnière on stochastic approximation versions of the EM algorithm. Computing the MAP estimator can be done via some adapted for simulated annealing versions of EM, possibly using MCMC as for instance in the Monolix software and its MCMC-SAEM algorithm. Where SA stands sometimes for stochastic approximation and sometimes for simulated annealing, originally developed by Gilles Celeux and Jean Diebolt, then reframed by Marc Lavielle and Eric Moulines [friends and coauthors]. With an MCMC step because the simulation of the latent variables involves an untractable normalising constant. (Contrary to this paper, Umberto Picchini and Adeline Samson proposed in 2015 a genuine ABC version of this approach, paper that I thought I missed—although I now remember discussing it with Adeline at JSM in Seattle—, ABC is used as a substitute for the conditional distribution of the latent variables given data and parameter. To be used as a substitute for the Q step of the (SA)EM algorithm. One more approximation step and one more simulation step and we would reach a form of ABC-Gibbs!) In this version, there are very few assumptions made on the approximation sequence, except that it converges with the iteration index to the true distribution (for a fixed observed sample) if convergence of ABC-SAEM is to happen. The paper takes as an illustrative sequence a collection of tempered versions of the true conditionals, but this is quite formal as I cannot fathom a feasible simulation from the tempered version and not from the untempered one. It is thus much more a version of tempered SAEM than truly connected with ABC (although a genuine ABC-EM version could be envisioned).

what if what???

[Here is a section of the Wikipedia page on Monte Carlo methods which makes little sense to me. What if it was not part of this page?!]

Monte Carlo simulation versus “what if” scenarios

There are ways of using probabilities that are definitely not Monte Carlo simulations – for example, deterministic modeling using single-point estimates. Each uncertain variable within a model is assigned a “best guess” estimate. Scenarios (such as best, worst, or most likely case) for each input variable are chosen and the results recorded.^[55]

By contrast, Monte Carlo simulations sample from a probability distribution for each variable to produce hundreds or thousands of possible outcomes. The results are analyzed to get probabilities of different outcomes occurring.^[56] For example, a comparison of a spreadsheet cost construction model run using traditional “what if” scenarios, and then running the comparison again with Monte Carlo simulation and triangular probability distributions shows that the Monte Carlo analysis has a narrower range than the “what if” analysis. This is because the “what if” analysis gives equal weight to all scenarios (see quantifying uncertainty in corporate finance), while the Monte Carlo method hardly samples in the very low probability regions. The samples in such regions are called “rare events”.

don’t be late for BayesComp’2020

An important reminder that October 14 is the deadline for regular registration to BayesComp 2020 as late fees will apply afterwards!!! The conference looks attractive enough to agree to pay more, but still…