Discussion meetings

Discussion Meetings are events where articles ('papers for reading') appearing in the Journal of the Royal Statistical Society are presented and discussed. The discussion and authors' replies are then published in the relevant Journal series. About half of the meetings are organised by the Society's Research Section and the events are often preceded by an informal session on the issues raised by the papers. See our guidelines for papers for discussion.

Discussion Meetings are usually held in the early evening at the Society's premises in Errol Street, London. Any change in venue will be noted alongside the meeting details.

Preprints of journal papers are available to download to encourage discussion at our Discussion Meetings before publication in one of our journals. Other papers, such as Presidential addresses, are also available to download. All preprints available here are provisional and subject to later amendment by the authors.

Contact Judith Shorten if you would like to make a written contribution to a discussion meeting or receive a preprint for each meeting by email.

Click here to watch videos from past discussion meetings.

Preprint discussion papers

2020

Research Section Virtual Discussion Meeting, Wednesday, 13 May 2020
This discussion meeting will be held virtually; we will confirm details nearer the time.

The Discussion paper ‘Linear mixed effects models for non-Gaussian continuous repeated measurement data’ will be presented by the authors, Ozgur Asar, David Bolin, Peter J Diggle and Jonas Wallin.

The preprint for the paper is available below and we welcome your contributions in the usual way. 

Details

Research Section Discussion Meeting (rescheduled from April 2020; date tba)
The preprint for the Discussion paper originally planned for April 22 is available (see below) and a rescheduled date will be confirmed in due course.

‘Quasi-stationary Monte Carlo methods and the ScaLE algorithm' by Murray Pollock, Paul Fearnhead, Adam M. Johansen and Gareth O Roberts.
The preprint for the paper is available below and we welcome your contributions in the usual way. 

Details

Research Section Discussion Meeting, Wednesday, 12 February 2020
‘Graphical models for extremes'
Sebastian Engelke and Adrien S. Hitz

Details

Research Section Discussion Meeting, Wednesday, 11 December 2019
‘Unbiased Markov chain Monte Carlo methods with couplings’
Pierre E. Jacob, John O’Leary and Yves F. Atchadé

Pre-meeting (DeMO) at 3pm.
Presenters: Chris Sherlock and Pierre Jacob
Chair: Ioanna Manolopoulou
Details


Preprints

2020

Research Section Discussion Meeting, Wednesday, 13 May 2020
Ozgur Asar (Acıbadem Mehmet Ali Aydınlar University, Istanbul), David Bolin (King Abdullah University of Science and Technology, Thuwal, and University of Gothenburg), Peter J. Diggle (Lancaster University) and Jonas Wallin (Lund University)
‘Linear mixed effects models for non-Gaussian continuous repeated measurement data’

We consider the analysis of continuous repeated measurement outcomes that are collected longitudinally. A standard framework for analysing data of this kind is a linear Gaussian mixed effects model within which the outcome variable can be decomposed into fixed effects, time invariant and time-varying random effects, and measurement noise. We develop methodology that, for the first time, allows any combination of these stochastic components to be non-Gaussian, using multivariate normal variance–mean mixtures. To meet the computational challenges that are presented by large data sets, i.e. in the current context, data sets with many subjects and/or many repeated measurements per subject, we propose a novel implementation of maximum likelihood estimation using a computationally efficient subsampling-based stochastic gradient algorithm. We obtain standard error estimates by inverting the observed Fisher information matrix and obtain the predictive distributions for the random effects in both filtering (conditioning on past and current data) and smoothing (conditioning on all data) contexts. To implement these procedures, we introduce an R package: ngme. We reanalyse two data sets, from cystic fibrosis and nephrology research, that were previously analysed by using Gaussian linear mixed effects models.

To be published in Series C; for more information go to the Wiley Online Library

The preprint is available to download.
Linear mixed effects models for non-Gaussian continuous repeated measurement data

Research Section Discussion Meeting, (originally scheduled for 22 April 2020 - rescheduled date tba)
Murray Pollock (University of Warwick, Coventry), Paul Fearnhead (University of Lancaster) and Adam M. Johansen and Gareth O. Roberts (University of Warwick, Coventry)
‘Quasi-stationary Monte Carlo methods and the ScaLE algorithm'

The paper introduces a class of Monte Carlo algorithms which are based on the simulation of a Markov process whose quasi-stationary distribution coincides with a distribution of interest. This differs fundamentally from, say, current Markov chain Monte Carlo methods which simulate a Markov chain whose stationary distribution is the target. We show how to approximate distributions of interest by carefully combining sequential Monte Carlo methods with methodology for the exact simulation of diffusions. The methodology that is introduced here is particularly promising in that it is applicable to the same class of problems as gradient-based Markov chain Monte Carlo algorithms but entirely circumvents the need to conduct Metropolis-Hastings type accept-reject steps while retaining exactness: the paper gives theoretical guarantees ensuring that the algorithm has the correct limiting target distribution. Furthermore, this methodology is highly amenable to ‘big data’ problems. By employing a modification to existing naive subsampling and control variate techniques it is possible to obtain an algorithm which is still exact but has sublinear iterative cost as a function of data size.

To be published in Series B; for more information go to the Wiley Online Library

The preprint is available to download.
Quasi-stationary Monte Carlo methods and the ScaLE algorithm' (PDF)

Research Section Discussion Meeting, Wednesday, 12 February 2020
Sebastian Engelke (University of Geneva) and Adrien S. Hitz (University of Oxford and Materialize.X, Enterprise Laboratory, London)
‘Graphical models for extremes’

Conditional independence, graphical models and sparsity are key notions for parsimonious statistical models and for understanding the structural relationships in the data. The theory of multivariate and spatial extremes describes the risk of rare events through asymptotically justified limit models such as max-stable and multivariate Pareto distributions. Statistical modelling in this field has been limited to moderate dimensions so far, partly owing to complicated likelihoods and a lack of understanding of the underlying probabilistic structures. We introduce a general theory of conditional independence for multivariate Pareto distributions that enables the definition of graphical models and sparsity for extremes. A Hammersley–Clifford theorem links this new notion to the factorization of densities of extreme value models on graphs. For the popular class of Hüsler–Reiss distributions we show that, similarly to the Gaussian case, the sparsity pattern of a general extremal graphical model can be read off from suitable inverse covariance matrices. New parametric models can be built in a modular way and statistical inference can be simplified to lower dimensional marginals. We discuss learning of minimum spanning trees and model selection for extremal graph structures, and we illustrate their use with an application to flood risk assessment on the Danube river.

To be published in Series B; for more information go to the Wiley Online Library.

The preprint is available to download.
Graphical models for extremes’ (PDF) 
Computer code (zip) 

Research Section Discussion Meeting, Wednesday, 11 December 2019
Pierre E. Jacob and John O’Leary (Harvard University, Cambridge) and Yves F. Atchadé (Boston University)
‘Unbiased Markov chain Monte Carlo methods with couplings’

Markov chain Monte Carlo (MCMC) methods provide consistent approximations of integrals as the number of iterations goes to 1. MCMC estimators are generally biased after any fixed number of iterations. We propose to remove this bias by using couplings of Markov chains together with a telescopic sum argument of Glynn and Rhee. The resulting unbiased estimators can be computed independently in parallel. We discuss practical couplings for popular MCMC algorithms. We establish the theoretical validity of the estimators proposed and study their efficiency relative to the underlying MCMC algorithms. Finally, we illustrate the performance and limitations of the method on toy examples, on an Ising model around its critical temperature, on a high dimensional variable-selection problem, and on an approximation of the cut distribution arising in Bayesian inference for models made of multiple modules.

To be published in Series B; for more information go to the Wiley Online Library.

The preprint is available to download.
Unbiased Markov chain Monte Carlo methods with couplings’ (PDF)
Supporting information (PDF)