Bayesian score calibration at One World ABC’minar [only comes every 1462 days]

improved approximate-Bayesian model-choice method for estimating shared evolutionary history

“An appealing approach would be a comparative, Bayesian model-choice method for inferring the probability of competing divergence histories while integrating over uncertainty in mutational and ancestral processes via models of nucleotide substitution and lineage coalescence.” (p.2)

Jamies Oaks arXived (a few months ago now) a rather extensive Monte-Carlo study on the impact of prior modelling on the model-choice performances of ABC model choice. (Of which I only became aware recently.) As in the earlier paper I commented on the Óg, the issue here has much more to do with prior assessment and calibration than with ABC implementation per se. For instance, the above quote recaps the whole point of conducting Bayesian model choice. (As missed by Templeton.)

“This causes divergence models with more divergence-time parameters to integrate over a much greater parameter space with low likelihood yet high prior density, resulting in small marginal likelihoods relative to models with fewer divergence-time parameters.” (p.2)

This second quote is essentially stressing the point with Occam’s razor argument. Which I deem [to be] a rather positive feature of Bayesian model choice. A reflection on the determination of the prior distribution, getting away from uniform priors, thus sounds most timely! The current paper takes place within a rather extensive exchange between Oak’s group and Hickerson’s group on what makes Bayesian model choice (and the associated software msBayes) pick or not the correct model. Oak and coauthors objected to the use of “narrow, empirically informed uniform priors”, arguing that this leads to a bias towards models with less parameters, a “statistical issue” in their words, while Hickerson et al. (2014) think this is due to msBayes way of selecting models and their parameters at random. However it refrains from reproducing earlier criticisms of or replies to Hickerson et al.

The current paper claims to have reached a satisfactory prior modelling with ¨improved robustness, accuracy, and power” (p.3).  If I understand correctly, the changes are in replacing a uniform distribution with a Gamma or a Dirichlet prior. Which means introducing a seriously large and potentially crippling number of hyperparameters into the picture. Having a lot of flexibility in the prior also means a lot of variability in the resulting inference… In other words, with more flexibility comes more responsibility, to paraphrase Voltaire.

“I have introduced a new approximate-Bayesian model choice method.” (p.21)

The ABC part is rather standard, except for the strange feature that the divergence times are used to construct summary statistics (p.10). Strange because these times are not observed for the actual data. So I must be missing something. (And I object to the above quote and to the title of the paper since there is no new ABC technique there, simply a different form of prior.)

“ABC methods in general are known to be biased for model choice.” (p.21)

I do not understand much the part about (reshuffling) introducing bias as detailed on p.11: every approximate method gives a “biased” answer in the sense this answer is not the true and proper posterior distribution. Using a different (re-ordered) vector of statistics provides a different ABC outcome,  hence a different approximate posterior, for which it seems truly impossible to check whether or not it increases the discrepancy from the true posterior, compared with the other version. I must admit I always find annoying to see the word bias used in a vague meaning and esp. within a Bayesian setting. All Bayesian methods are biased. End of the story. Quoting our PNAS paper as concluding that ABC model choice is biased is equally misleading: the intended warning represented by the paper was that Bayes factors and posterior probabilities could be quite unrelated with those based on the whole dataset. That the proper choice of summary statistics leads to a consistent model choice shows ABC model choice is not necessarily “biased”… Furthermore, I also fail to understand why the posterior probability of model i should be distributed as a uniform (“If the method is unbiased, the points should fall near the identity line”) when the data is from model i: this is not a p-value but a posterior probability and the posterior probability is not the frequentist coverage…

My overall problem is that, all in all, this is a single if elaborate Monte Carlo study and, as such, it does not carry enough weight to validate an approach that remains highly subjective in the selection of its hyperparameters. Without raising any doubt about an hypothetical “fixing” of those hyperparameters, I think this remains a controlled experiment with simulated data where the true parameters are know and the prior is “true”. This obviously helps in getting better performances.

“With improving numerical methods (…), advances in Monte Carlo techniques and increasing efficiency of likelihood calculations, analyzing rich comparative phylo-geographical models in a full-likelihood Bayesian framework is becoming computationally feasible.” (p.21)

This conclusion of the paper sounds over-optimistic and rather premature. I do not know of any significant advance in computing the observed likelihood for the population genetics models ABC is currently handling. (The SMC algorithm of Bouchard-Côté, Sankaraman and Jordan, 2012, does not apply to Kingman’s coalescent, as far as I can tell.) This is certainly a goal worth pursuing and borrowing strength from multiple techniques cannot hurt, but it remains so far a lofty goal, still beyond our reach… I thus think the major message of the paper is to reinforce our own and earlier calls for caution when interpreting the output of an ABC model choice (p.20), or even of a regular Bayesian analysis, agreeing that we should aim at seeing “a large amount of posterior uncertainty” rather than posterior probability values close to 0 and 1.

checking ABC convergence via coverage

Dennis Prangle, Michael Blum, G. Popovic and Scott Sisson just arXived a paper on diagnostics for ABC validation via coverage diagnostics. Getting valid approximation diagnostics for ABC is clearly and badly needed and this was the last slide of my talk yesterday at the Winter Workshop in Gainesville. When simulation time is not an issue (!), our DIYABC software does implement a limited coverage assessment by computing the type I error, i.e. by simulating data under the null model and evaluating the number of time it is rejected at the 5% level (see sections 2.11.3 and 3.8 in the documentation). The current paper builds on a similar perspective.

The idea in the paper is that a (Bayesian) credible interval at a given credible level α should have a similar confidence level (at least asymptotically and even more for matching priors) and that simulating pseudo-data with a known parameter value allows for a Monte-Carlo evaluation of the credible interval “true” coverage, hence for a calibration of the tolerance. The delicate issue is about the generation of those “known” parameters. For instance, if the pair (θ_, y) is generated from the joint distribution prior x likelihood, and if the credible region is also based on the true posterior, the average coverage is the nominal one. On the other hand, if the credible interval is based on a poor (ABC) approximation to the posterior, the average coverage should differ from the nominal one. Given that ABC is always wrong, however, this may fail to be a powerful diagnostic. In particular, when using insufficient (summary) statistics, the discrepancy should make testing for uniformity harder, shouldn’t it? 

ABC in 1984

“Bayesian statistics and Monte Carlo methods are ideally suited to the task of passing many models over one dataset” D. Rubin, Annals of Statistics, 1984

Jean-Louis Foulley sent me a 1984 paper by Don Rubin that details in no uncertain terms the accept-reject algorithm at the core of the ABC algorithm! Namely,

Generate ;
Generate ;
Accept if

Obviously, ABC goes further by replacing the acceptance step with the tolerance condition

but this early occurence is worth noticing nonetheless. It is also interesting to see that Don Rubin does not promote this simulation method in situations where the likelihood is not available but rather as an intuitive way to understanding posterior distributions from a frequentist perspective, because ‘s from the posterior are those that could have generated the observed data. (The issue of the zero probability of the exact equality between simulated and observed data is not dealt with in the paper, maybe because the notion of a “match” between simulated and observed data is not clearly defined.) Apart from this historical connection, I recommend the entire paper as providing a very compelling argument for practical Bayesianism!