Archive for convergence diagnostics

assessing MCMC convergence

Posted in Books, Statistics, University life with tags , , , , , , , , , , , on June 6, 2019 by xi'an

When MCMC became mainstream in the 1990’s, there was a flurry of proposals to check, assess, and even guarantee convergence to the stationary distribution, as discussed in our MCMC book. Along with Chantal Guihenneuc and Kerrie Mengersen, we also maintained for a while a reviewww webpage categorising theses. Niloy Biswas and Pierre Jacob have recently posted a paper where they propose the use of couplings (and unbiased MCMC) towards deriving bounds on different metrics between the target and the current distribution of the Markov chain. Two chains are created from a given kernel and coupled with a lag of L, meaning that after a while, the two chains become one with a time difference of L. (The supplementary material contains many details on how to induce coupling.) The distance to the target can then be bounded by a sum of distances between the two chains until they merge. The above picture from the paper is a comparison a Polya-Urn sampler with several HMC samplers for a logistic target (not involving the Pima Indian dataset!). The larger the lag L the more accurate the bound. But the larger the lag the more expensive the assessment of how many steps are needed to convergence. Especially when considering that the evaluation requires restarting the chains from scratch and rerunning until they couple again, rather than continuing one run which can only brings the chain closer to stationarity and to being distributed from the target. I thus wonder at the possibility of some Rao-Blackwellisation of the simulations used in this assessment (while realising once more than assessing convergence almost inevitably requires another order of magnitude than convergence itself!). Without a clear idea of how to do it… For instance, keeping the values of the chain(s) at the time of coupling is not directly helpful to create a sample from the target since they are not distributed from that target.

[Pierre also wrote a blog post about the paper on Statisfaction that is definitely much clearer and pedagogical than the above.]

revisiting the Gelman-Rubin diagnostic

Posted in Books, pictures, Statistics, Travel, University life with tags , , , , , , , , , , , , , on January 23, 2019 by xi'an

Just before Xmas, Dootika Vats (Warwick) and Christina Knudson arXived a paper on a re-evaluation of the ultra-popular 1992 Gelman and Rubin MCMC convergence diagnostic. Which compares within-variance and between-variance on parallel chains started from hopefully dispersed initial values. Or equivalently an under-estimating and an over-estimating estimate of the MCMC average. In this paper, the authors take advantage of the variance estimators developed by Galin Jones, James Flegal, Dootika Vats and co-authors, which are batch mean estimators consistently estimating the asymptotic variance. They also discuss the choice of a cut-off on the ratio R of variance estimates, i.e., how close to one need it be? By relating R to the effective sample size (for which we also have reservations), which gives another way of calibrating the cut-off. The main conclusion of the study is that the recommended 1.1 bound is too large for a reasonable proximity to the true value of the Bayes estimator (Disclaimer: The above ABCruise header is unrelated with the paper, apart from its use of the Titanic dataset!)

In fact, I have other difficulties than setting the cut-off point with the original scheme as a way to assess MCMC convergence or lack thereof, among which

  1. its dependence on the parameterisation of the chain and on the estimation of a specific target function
  2. its dependence on the starting distribution which makes the time to convergence not absolutely meaningful
  3. the confusion between getting to stationarity and exploring the whole target
  4. its missing the option to resort to subsampling schemes to attain pseudo-independence or scale time to convergence (albeit see 3. above)
  5. a potential bias brought by the stopping rule.

calibrating approximate credible sets

Posted in Books, Statistics with tags , , , , , , , on October 26, 2018 by xi'an

Earlier this week, Jeong Eun Lee, Geoff Nicholls, and Robin Ryder arXived a paper on the calibration of approximate Bayesian credible intervals. (Warning: all three authors are good friends of mine!) They start from the core observation that dates back to Monahan and Boos (1992) of exchangeability between θ being generated from the prior and φ being generated from the posterior associated with one observation generated from the prior predictive. (There is no name for this distribution, other than the prior, that is!) A setting amenable to ABC considerations! Actually, Prangle et al. (2014) relies on this property for assessing the ABC error, while pointing out that the test for exchangeability is not fool-proof since it works equally for two generations from the prior.

“The diagnostic tools we have described cannot be “fooled” in quite the same way checks based on the exchangeability can be.”

The paper thus proposes methods for computing the coverage [under the true posterior] of a credible set computed using an approximate posterior. (I had to fire up a few neurons to realise this was the right perspective, rather than the reverse!) A first solution to approximate the exact coverage of the approximate credible set is to use logistic regression, instead of the exact coverage, based on some summary statistics [not necessarily in an ABC framework]. And a simulation outcome that the parameter [simulated from the prior] at the source of the simulated data is within the credible set. Another approach is to use importance sampling when simulating from the pseudo-posterior. However this sounds dangerously close to resorting to an harmonic mean estimate, since the importance weight is the inverse of the approximate likelihood function. Not that anything unseemly transpires from the simulations.

 

Statistical rethinking [book review]

Posted in Books, Kids, R, Statistics, University life with tags , , , , , , , , , , , , , , , , , , , , , on April 6, 2016 by xi'an

Statistical Rethinking: A Bayesian Course with Examples in R and Stan is a new book by Richard McElreath that CRC Press sent me for review in CHANCE. While the book was already discussed on Andrew’s blog three months ago, and [rightly so!] enthusiastically recommended by Rasmus Bååth on Amazon, here are the reasons why I am quite impressed by Statistical Rethinking!

“Make no mistake: you will wreck Prague eventually.” (p.10)

While the book has a lot in common with Bayesian Data Analysis, from being in the same CRC series to adopting a pragmatic and weakly informative approach to Bayesian analysis, to supporting the use of STAN, it also nicely develops its own ecosystem and idiosyncrasies, with a noticeable Jaynesian bent. To start with, I like the highly personal style with clear attempts to make the concepts memorable for students by resorting to external concepts. The best example is the call to the myth of the golem in the first chapter, which McElreath uses as an warning for the use of statistical models (which almost are anagrams to golems!). Golems and models [and robots, another concept invented in Prague!] are man-made devices that strive to accomplish the goal set to them without heeding the consequences of their actions. This first chapter of Statistical Rethinking is setting the ground for the rest of the book and gets quite philosophical (albeit in a readable way!) as a result. In particular, there is a most coherent call against hypothesis testing, which by itself justifies the title of the book. Continue reading

importance sampling with infinite variance

Posted in pictures, R, Statistics, University life with tags , , , , , , , on November 13, 2015 by xi'an

“In this article it is shown that in a fairly general setting, a sample of size approximately exp(D(μ|ν)) is necessary and sufficient for accurate estimation by importance sampling.”

Sourav Chatterjee and Persi Diaconis arXived yesterday an exciting paper where they study the proper sample size in an importance sampling setting with no variance. That’s right, with no variance. They give as a starting toy example the use of an Exp(1) proposal for an Exp(1/2) target, where the importance ratio exp(x/2)/2 has no ξ order moment (for ξ≥2). So the infinity in the variance is somehow borderline in this example, which may explain why the estimator could be considered to “work”. However, I disagree with the statement “that a sample size a few thousand suffices” for the estimator of the mean to be close to the true value, that is, 2. For instance, the picture I drew above is the superposition of 250 sequences of importance sampling estimators across 10⁵ iterations: several sequences show huge jumps, even for a large number of iterations, which are characteristic of infinite variance estimates. Thus, while the expected distance to the true value can be closely evaluated via the Kullback-Leibler divergence between the target and the proposal (which by the way is infinite when using a Normal as proposal and a Cauchy as target), there are realisations of the simulation path that can remain far from the true value and this for an arbitrary number of simulations. (I even wonder if, for a given simulation path, waiting long enough should not lead to those unbounded jumps.) The first result is frequentist, while the second is conditional, i.e., can occur for the single path we have just simulated… As I taught in class this very morning, I thus remain wary about using an infinite variance estimator. (And not only in connection with the harmonic mean quagmire. As shown below by the more extreme case of simulating an Exp(1) proposal for an Exp(1/10) target, where the mean is completely outside the range of estimates.) Wary, then, even though I find the enclosed result about the existence of a cut-off sample size associated with this L¹ measure quite astounding. Continue reading

consistency of ABC

Posted in pictures, Statistics, Travel, University life with tags , , , , , , , , , on August 25, 2015 by xi'an

Along with David Frazier and Gael Martin from Monash University, Melbourne, we have just completed (and arXived) a paper on the (Bayesian) consistency of ABC methods, producing sufficient conditions on the summary statistics to ensure consistency of the ABC posterior. Consistency in the sense of the prior concentrating at the true value of the parameter when the sample size and the inverse tolerance (intolerance?!) go to infinity. The conditions are essentially that the summary statistics concentrates around its mean and that this mean identifies the parameter. They are thus weaker conditions than those found earlier consistency results where the authors considered convergence to the genuine posterior distribution (given the summary), as for instance in Biau et al. (2014) or Li and Fearnhead (2015). We do not require here a specific rate of decrease to zero for the tolerance ε. But still they do not hold all the time, as shown for the MA(2) example and its first two autocorrelation summaries, example we started using in the Marin et al. (2011) survey. We further propose a consistency assessment based on the main consistency theorem, namely that the ABC-based estimates of the marginal posterior densities for the parameters should vary little when adding extra components to the summary statistic, densities estimated from simulated data. And that the mean of the resulting summary statistic is indeed one-to-one. This may sound somewhat similar to the stepwise search algorithm of Joyce and Marjoram (2008), but those authors aim at obtaining a vector of summary statistics that is as informative as possible. We also examine the consistency conditions when using an auxiliary model as in indirect inference. For instance, when using an AR(2) auxiliary model for estimating an MA(2) model. And ODEs.

evaluating stochastic algorithms

Posted in Books, R, Statistics, University life with tags , , , , , , , , on February 20, 2014 by xi'an

Reinaldo sent me this email a long while ago

Could you recommend me a nice reference about 
measures to evaluate stochastic algorithms (in 
particular focus in approximating posterior 
distributions).

and I hope he is still reading the ‘Og, despite my lack of prompt reply! I procrastinated and procrastinated in answering this question as I did not have a ready reply… We have indeed seen (almost suffered from!) a flow of MCMC convergence diagnostics in the 90’s.  And then it dried out. Maybe because of the impossibility to be “really” sure, unless running one’s MCMC much longer than “necessary to reach” stationarity and convergence. The heat of the dispute between the “single chain school” of Geyer (1992, Statistical Science) and the “multiple chain school” of Gelman and Rubin (1992, Statistical Science) has since long evaporated. My feeling is that people (still) run their MCMC samplers several times and check for coherence between the outcomes. Possibly using different kernels on parallel threads. At best, but rarely, they run (one or another form of) tempering to identify the modal zones of the target. And instances where non-trivial control variates are available are fairly rare. Hence, a non-sequitur reply at the MCMC level. As there is no automated tool available, in my opinion. (Even though I did not check the latest versions of BUGS.)

As it happened, Didier Chauveau from Orléans gave today a talk at Big’MC on convergence assessment based on entropy estimation, a joint work with Pierre Vandekerkhove. He mentioned SamplerCompare which is an R package that appeared in 2010. Soon to come is their own EntropyMCMC package, using parallel simulation. And k-nearest neighbour estimation.

If I re-interpret the question as focussed on ABC algorithms, it gets both more delicate and easier. Easy because each ABC distribution is different. So there is no reason to look at the unreachable original target. Delicate because there are several parameters to calibrate (tolerance, choice of summary, …) on top of the number of MCMC simulations. In DIYABC, the outcome is always made of the superposition of several runs to check for stability (or lack thereof). But this tells us nothing about the distance to the true original target. The obvious but impractical answer is to use some basic bootstrapping, as it is generally much too costly.