Archive for bootstrap

a bootstrap likelihood approach to Bayesian computation

Posted in Books, R, Statistics, University life with tags , , , , , , , , on October 16, 2014 by xi'an

This paper by Weixuan Zhu, Juan Miguel Marín [from Carlos III in Madrid, not to be confused with Jean-Michel Marin, from Montpellier!], and Fabrizio Leisen proposes an alternative to our 2013 PNAS paper with Kerrie Mengersen and Pierre Pudlo on empirical likelihood ABC, or BCel. The alternative is based on Davison, Hinkley and Worton’s (1992) bootstrap likelihood, which relies on a double-bootstrap to produce a non-parametric estimate of the distribution of a given estimator of the parameter θ. Including a smooth curve-fitting algorithm step, for which not much description is available from the paper.

“…in contrast with the empirical likelihood method, the bootstrap likelihood doesn’t require any set of subjective constrains taking advantage from the bootstrap methodology. This makes the algorithm an automatic and reliable procedure where only a few parameters need to be specified.”

The spirit is indeed quite similar to ours in that a non-parametric substitute plays the role of the actual likelihood, with no correction for the substitution. Both approaches are convergent, with similar or identical convergence speeds. While the empirical likelihood relies on a choice of parameter identifying constraints, the bootstrap version starts directly from the [subjectively] chosen estimator of θ. For it indeed needs to be chosen. And computed.

“Another benefit of using the bootstrap likelihood (…) is that the construction of bootstrap likelihood could be done once and not at every iteration as the empirical likelihood. This leads to significant improvement in the computing time when different priors are compared.”

This is an improvement that could apply to the empirical likelihood approach, as well, once a large enough collection of likelihood values has been gathered. But only in small enough dimensions where smooth curve-fitting algorithms can operate. The same criticism applying to the derivation of a non-parametric density estimate for the distribution of the estimator of θ. Critically, the paper only processes examples with a few parameters.

In the comparisons between BCel and BCbl that are produced in the paper, the gain is indeed towards BCbl. Since this paper is mostly based on examples and illustrations, not unlike ours, I would like to see more details on the calibration of the non-parametric methods and of regular ABC, as well as on the computing time. And the variability of both methods on more than a single Monte Carlo experiment.

I am however uncertain as to how the authors process the population genetic example. They refer to the composite likelihood used in our paper to set the moment equations. Since this is not the true likelihood, how do the authors select their parameter estimates in the double-bootstrap experiment? The inclusion of Crakel’s and Flegal’s (2013) bivariate Beta, is somewhat superfluous as this example sounds to me like an artificial setting.

In the case of the Ising model, maybe the pre-processing step in our paper with Matt Moores could be compared with the other algorithms. In terms of BCbl, how does the bootstrap operate on an Ising model, i.e. (a) how does one subsample pixels and (b)what are the validity guarantees?

A test that would be of interest is to start from a standard ABC solution and use this solution as the reference estimator of θ, then proceeding to apply BCbl for that estimator. Given that the reference table would have to be produced only once, this would not necessarily increase the computational cost by a large amount…

Statistics slides (3)

Posted in Books, Kids, Statistics, University life with tags , , , , , , , , , , on October 9, 2014 by xi'an

La Défense from Paris-Dauphine, Nov. 15, 2012Here is the third set of slides for my third year statistics course. Nothing out of the ordinary, but the opportunity to link statistics and simulation for students not yet exposed to Monte Carlo methods. (No ABC yet, but who knows?, I may use ABC as an entry to Bayesian statistics, following Don Rubin’s example! Surprising typo on the Project Euclid page for this 1984 paper, by the way…) On Monday, I had the pleasant surprise to see Shravan Vasishth in the audience, as he is visiting Université Denis Diderot (Paris 7) this month.

Monte Carlo simulation and resampling methods for social science [book review]

Posted in Books, Kids, R, Statistics, University life with tags , , , , , , on October 6, 2014 by xi'an

Monte Carlo simulation and resampling methods for social science is a short paperback written by Thomas Carsey and Jeffrey Harden on the use of Monte Carlo simulation to evaluate the adequacy of a model and the impact of assumptions behind this model. I picked it in the library the other day and browse through the chapters during one of my métro rides. Definitely not an in-depth reading, so be warned!

Overall, I think the book is doing a good job of advocating the use of simulation to evaluate the pros and cons of a given model (rephrased as data generating process) when faced with data. And doing it in R. After some rudiments in probability theory and in R programming, it briefly explains the use of resident random generators if not of how to handle new distributions and then spend a large part of the book on simulation around generalised and regular linear models. For instance, in the linear model, the authors test the impact of heterocedasticity, multicollinearity, measurement error, omitted variable(s), serial correlation, clustered data, and heavy-tailed errors. While this is a perfect way of exploring those semi-hidden hypotheses behind the linear model, I wonder at the impact on students of this exploration. On the one hand, they will perceive the importance of those assumptions and hopefully remember them. On the other hand, and this is a very recurrent criticism of mine, this implies a lot of maturity from the students, i.e., they have to distinguish the data, the model [maybe] behind the data, the finite if large number of hypotheses one can test, and the interpretation of the outcome of a simulation test… Given that they were introduced to basic probability just a few chapters before, this expectation [from the students] may prove unrealistic. (And a similar criticism applies to the following chapters, from GLM to jackknife and bootstrap.)

At the end of the book, the authors ask the question as to how could a reader use the information in this book towards one’s work. Drafting a generic protocol for this reader, who is supposed to consider “alterations to the data generating process” (p.272) and to “identify a possible problem or assumption violation” (p.271). Thus requiring a readership “who has some training in quantitative methods” (p.1). And then some more. But I definitely sympathise with the goal of confronting models and theory with the harsh reality of simulation output!

ABC model choice via random forests [expanded]

Posted in Statistics, University life with tags , , , , , , , , , , , on October 1, 2014 by xi'an

outofAfToday, we arXived a second version of our paper on ABC model choice with random forests. Or maybe [A]BC model choice with random forests. Since the random forest is built on a simulation from the prior predictive and no further approximation is used in the process. Except for the computation of the posterior [predictive] error rate. The update wrt the earlier version is that we ran massive simulations throughout the summer, on existing and new datasets. In particular, we have included a Human dataset extracted from the 1000 Genomes Project. Made of 51,250 SNP loci. While this dataset is not used to test new evolution scenarios, we compared six out-of-Africa scenarios, with a possible admixture for Americans of African ancestry. The scenario selected by a random forest procedure posits a single out-of-Africa colonization event with a secondary split into a European and an East Asian population lineages, and a recent genetic admixture between African and European lineages, for Americans of African origin. The procedure reported a high level of confidence since the estimated posterior error rate is equal to zero. The SNP loci were carefully selected using the following criteria: (i) all individuals have a genotype characterized by a quality score (GQ)>10, (ii) polymorphism is present in at least one of the individuals in order to fit the SNP simulation algorithm of Hudson (2002) used in DIYABC V2 (Cornuet et al., 2014), (iii) the minimum distance between two consecutive SNPs is 1 kb in order to minimize linkage disequilibrium between SNP, and (iv) SNP loci showing significant deviation from Hardy-Weinberg equilibrium at a 1% threshold in at least one of the four populations have been removed.

In terms of random forests, we optimised the size of the bootstrap subsamples for all of our datasets. While this optimisation requires extra computing time, it is negligible when compared with the enormous time taken by a logistic regression, which is [yet] the standard ABC model choice approach. Now the data has been gathered, it is only a matter of days before we can send the paper to a journal

a weird beamer feature…

Posted in Books, Kids, Linux, R, Statistics, University life with tags , , , , , , , , , , , , on September 24, 2014 by xi'an

As I was preparing my slides for my third year undergraduate stat course, I got a weird error that got a search on the Web to unravel:

! Extra }, or forgotten \endgroup.
\endframe ->\egroup
  \begingroup \def \@currenvir {frame}
l.23 \end{frame}
  \begin{slide}
?

which was related with a fragile environment

\begin{frame}[fragile]
\frametitle{simulation in practice}
\begin{itemize}
\item For a given distribution $F$, call the corresponding 
pseudo-random generator in an arbitrary computer language
\begin{verbatim}
> x=rnorm(10)
> x
 [1] -0.021573 -1.134735  1.359812 -0.887579
 [7] -0.749418  0.506298  0.835791  0.472144
\end{verbatim}
\item use the sample as a statistician would
\begin{verbatim}
> mean(x)
[1] 0.004892123
> var(x)
[1] 0.8034657
\end{verbatim}
to approximate quantities related with $F$
\end{itemize}
\end{frame}\begin{frame}

but not directly the verbatim part: the reason for the bug was that the \end{frame} command did not have a line by itself! Which is one rare occurrence where the carriage return has an impact in LaTeX, as far as I know… (The same bug appears when there is an indentation at the beginning of the line. Weird!) [Another annoying feature is wordpress turning > into > in the sourcecode environment…]

austerity in MCMC land

Posted in Statistics with tags , , , , , on April 28, 2013 by xi'an

Anoop Korattikara, Yutian Chen and Max Welling recently arXived a paper on the appeal of using only part of the data to speed up MCMC. This is different from the growing literature on unbiased estimators of the likelihood exemplified by Andrieu & Roberts (2009). Here, the approximation to the true target is akin to the approximation in ABC algorithms in that a value of the parameter is accepted if the difference in the likelihoods is larger than a given bound. Expressing this perspective as a test on the mean of the log likelihood leads the authors to use instead a subsample from the whole sample. (The approximation level ε is then a bound on the p-value.) While this idea only applies to iid settings, it is quite interesting and sounds a wee bit like a bootstrapped version of MCMC. Especially since it sounds as if it could provide an auto-evaluation of its error.

Michael Jordan’s course at CREST

Posted in Statistics, University life with tags , , , , , , , , on March 26, 2013 by xi'an

Next month, Michael Jordan will give an advanced course at CREST-ENSAE, Paris, on Recent Advances at the Interface of Computation and Statistics. The course will take place on April 4 (14:00, ENSAE, Room #11), 11 (14:00, ENSAE, Room #11), 15 (11:00, ENSAE, Room #11) and 18 (14:00, ENSAE, Room #11). It is open to everyone and attendance is free. The only constraint is a compulsory registration with Nadine Guedj (email: guedj[AT]ensae.fr) for security issues. I strongly advise all graduate students who can take advantage of this fantastic opportunity to grasp it! Here is the abstract to the course:

“I will discuss several recent developments in areas where statistical science meets computational science, with particular concern for bringing statistical inference into contact with distributed computing architectures and with recursive data structures :

  1. How does one obtain confidence intervals in massive data sets? The bootstrap principle suggests resampling data to obtain fluctuations in the values of estimators, and thereby confidence intervals, but this is infeasible computationally with massive data. Subsampling the data yields fluctuations on the wrong scale, which have to be corrected to provide calibrated statistical inferences. I present a new procedure, the “bag of little bootstraps,” which circumvents this problem, inheriting the favorable theoretical properties of the bootstrap but also having a much more favorable computational profile.

  2. The problem of matrix completion has been the focus of much recent work, both theoretical and practical. To take advantage of distributed computing architectures in this setting, it is natural to consider divide-and-conquer algorithms for matrix completion. I show that these work well in practice, but also note that new theoretical problems arise when attempting to characterize the statistical performance of these algorithms. Here the theoretical support is provided by concentration theorems for random matrices, and I present a new approach to matrix concentration based on Stein’s method.

  3. Bayesian nonparametrics involves replacing the “prior distributions” of classical Bayesian analysis with “prior stochastic processes.” Of particular value are the class of “combinatorial stochastic processes,” which make it possible to express uncertainty (and perform inference) over combinatorial objects that are familiar as data structures in computer science.”

References are available on Michael’s homepage.

Follow

Get every new post delivered to your Inbox.

Join 706 other followers