Antony Overstall, James McGree.

Source: Bayesian Analysis, Volume 15, Number 1, 103--131.

Abstract:
A Bayesian design is given by maximising an expected utility over a design space. The utility is chosen to represent the aim of the experiment and its expectation is taken with respect to all unknowns: responses, parameters and/or models. Although straightforward in principle, there are several challenges to finding Bayesian designs in practice. Firstly, the utility and expected utility are rarely available in closed form and require approximation. Secondly, the design space can be of high-dimensionality. In the case of intractable likelihood models, these problems are compounded by the fact that the likelihood function, whose evaluation is required to approximate the expected utility, is not available in closed form. A strategy is proposed to find Bayesian designs for intractable likelihood models. It relies on the development of an automatic, auxiliary modelling approach, using multivariate Gaussian process emulators, to approximate the likelihood function. This is then combined with a copula-based approach to approximate the marginal likelihood (a quantity commonly required to evaluate many utility functions). These approximations are demonstrated on examples of stochastic process models involving experimental aims of both parameter estimation and model comparison.

Nicolas Garcia Trillos, Daniel Sanz-Alonso.

Source: Bayesian Analysis, Volume 15, Number 1, 29--56.

Abstract:
The Bayesian update can be viewed as a variational problem by characterizing the posterior as the minimizer of a functional. The variational viewpoint is far from new and is at the heart of popular methods for posterior approximation. However, some of its consequences seem largely unexplored. We focus on the following one: defining the posterior as the minimizer of a functional gives a natural path towards the posterior by moving in the direction of steepest descent of the functional. This idea is made precise through the theory of gradient flows, allowing to bring new tools to the study of Bayesian models and algorithms. Since the posterior may be characterized as the minimizer of different functionals, several variational formulations may be considered. We study three of them and their three associated gradient flows. We show that, in all cases, the rate of convergence of the flows to the posterior can be bounded by the geodesic convexity of the functional to be minimized. Each gradient flow naturally suggests a nonlinear diffusion with the posterior as invariant distribution. These diffusions may be discretized to build proposals for Markov chain Monte Carlo (MCMC) algorithms. By construction, the diffusions are guaranteed to satisfy a certain optimality condition, and rates of convergence are given by the convexity of the functionals. We use this observation to propose a criterion for the choice of metric in Riemannian MCMC methods.

Gemma E. Moran, Veronika Ročková, Edward I. George.

Source: Bayesian Analysis, Volume 14, Number 4, 1091--1119.

Abstract:
Consider the problem of high dimensional variable selection for the Gaussian linear model when the unknown error variance is also of interest. In this paper, we show that the use of conjugate shrinkage priors for Bayesian variable selection can have detrimental consequences for such variance estimation. Such priors are often motivated by the invariance argument of Jeffreys (1961). Revisiting this work, however, we highlight a caveat that Jeffreys himself noticed; namely that biased estimators can result from inducing dependence between parameters a priori . In a similar way, we show that conjugate priors for linear regression, which induce prior dependence, can lead to such underestimation in the Bayesian high-dimensional regression setting. Following Jeffreys, we recommend as a remedy to treat regression coefficients and the error variance as independent a priori . Using such an independence prior framework, we extend the Spike-and-Slab Lasso of Ročková and George (2018) to the unknown variance case. This extended procedure outperforms both the fixed variance approach and alternative penalized likelihood methods on simulated data. On the protein activity dataset of Clyde and Parmigiani (1998), the Spike-and-Slab Lasso with unknown variance achieves lower cross-validation error than alternative penalized likelihood methods, demonstrating the gains in predictive accuracy afforded by simultaneous error variance estimation. The unknown variance implementation of the Spike-and-Slab Lasso is provided in the publicly available R package SSLASSO (Ročková and Moran, 2017).

Mengyang Gu.

Source: Bayesian Analysis, Volume 14, Number 3, 877--905.

Abstract:
Gaussian stochastic process (GaSP) has been widely used in two fundamental problems in uncertainty quantification, namely the emulation and calibration of mathematical models. Some objective priors, such as the reference prior, are studied in the context of emulating (approximating) computationally expensive mathematical models. In this work, we introduce a new class of priors, called the jointly robust prior, for both the emulation and calibration. This prior is designed to maintain various advantages from the reference prior. In emulation, the jointly robust prior has an appropriate tail decay rate as the reference prior, and is computationally simpler than the reference prior in parameter estimation. Moreover, the marginal posterior mode estimation with the jointly robust prior can separate the influential and inert inputs in mathematical models, while the reference prior does not have this property. We establish the posterior propriety for a large class of priors in calibration, including the reference prior and jointly robust prior in general scenarios, but the jointly robust prior is preferred because the calibrated mathematical model typically predicts the reality well. The jointly robust prior is used as the default prior in two new R packages, called “RobustGaSP” and “RobustCalibration”, available on CRAN for emulation and calibration, respectively.

Stefano Peluso, Siddhartha Chib, Antonietta Mira.

Source: Bayesian Analysis, Volume 14, Number 3, 727--751.

Abstract:
We develop a general Bayesian semiparametric change-point model in which separate groups of structural parameters (for example, location and dispersion parameters) can each follow a separate multiple change-point process, driven by time-dependent transition matrices among the latent regimes. The distribution of the observations within regimes is unknown and given by a Dirichlet process mixture prior. The properties of the proposed model are studied theoretically through the analysis of inter-arrival times and of the number of change-points in a given time interval. The prior-posterior analysis by Markov chain Monte Carlo techniques is developed on a forward-backward algorithm for sampling the various regime indicators. Analysis with simulated data under various scenarios and an application to short-term interest rates are used to show the generality and usefulness of the proposed model.

Quan Zhou, Yongtao Guan.

Source: Bayesian Analysis, Volume 14, Number 2, 573--594.

Abstract:
Bayesian variable selection regression (BVSR) is able to jointly analyze genome-wide genetic datasets, but the slow computation via Markov chain Monte Carlo (MCMC) hampered its wide-spread usage. Here we present a novel iterative method to solve a special class of linear systems, which can increase the speed of the BVSR model-fitting tenfold. The iterative method hinges on the complex factorization of the sum of two matrices and the solution path resides in the complex domain (instead of the real domain). Compared to the Gauss-Seidel method, the complex factorization converges almost instantaneously and its error is several magnitude smaller than that of the Gauss-Seidel method. More importantly, the error is always within the pre-specified precision while the Gauss-Seidel method is not. For large problems with thousands of covariates, the complex factorization is 10–100 times faster than either the Gauss-Seidel method or the direct method via the Cholesky decomposition. In BVSR, one needs to repetitively solve large penalized regression systems whose design matrices only change slightly between adjacent MCMC steps. This slight change in design matrix enables the adaptation of the iterative complex factorization method. The computational innovation will facilitate the wide-spread use of BVSR in reanalyzing genome-wide association datasets.

M. W. McLean, M. P. Wand.

Source: Bayesian Analysis, Volume 14, Number 2, 371--398.

Abstract:
We build on recent work concerning message passing approaches to approximate fitting and inference for arbitrarily large regression models. The focus is on regression models where the response variable is modeled to have an elaborate distribution, which is loosely defined to mean a distribution that is more complicated than common distributions such as those in the Bernoulli, Poisson and Normal families. Examples of elaborate response families considered here are the Negative Binomial and $t$ families. Variational message passing is more challenging due to some of the conjugate exponential families being non-standard and numerical integration being needed. Nevertheless, a factor graph fragment approach means the requisite calculations only need to be done once for a particular elaborate response distribution family. Computer code can be compartmentalized, including that involving numerical integration. A major finding of this work is that the modularity of variational message passing extends to elaborate response regression models.

Peter D. Hoff

Source: Bayesian Anal., Volume 6, Number 2, 179--196.

Abstract:
Modern datasets are often in the form of matrices or arrays, potentially having correlations along each set of data indices. For example, data involving repeated measurements of several variables over time may exhibit temporal correlation as well as correlation among the variables. A possible model for matrix-valued data is the class of matrix normal distributions, which is parametrized by two covariance matrices, one for each index set of the data. In this article we discuss an extension of the matrix normal model to accommodate multidimensional data arrays, or tensors. We show how a particular array-matrix product can be used to generate the class of array normal distributions having separable covariance structure. We derive some properties of these covariance structures and the corresponding array normal distributions, and show how the array-matrix product can be used to define a semi-conjugate prior distribution and calculate the corresponding posterior distribution. We illustrate the methodology in an analysis of multivariate longitudinal network data which take the form of a four-way array.

Adam R. Brentnall, Jack Cuzick.

Source: Statistical Science, Volume 35, Number 1, 14--30.

Abstract:
Strategies to prevent cancer and diagnose it early when it is most treatable are needed to reduce the public health burden from rising disease incidence. Risk assessment is playing an increasingly important role in targeting individuals in need of such interventions. For breast cancer many individual risk factors have been well understood for a long time, but the development of a fully comprehensive risk model has not been straightforward, in part because there have been limited data where joint effects of an extensive set of risk factors may be estimated with precision. In this article we first review the approach taken to develop the IBIS (Tyrer–Cuzick) model, and describe recent updates. We then review and develop methods to assess calibration of models such as this one, where the risk of disease allowing for competing mortality over a long follow-up time or lifetime is estimated. The breast cancer risk model model and calibration assessment methods are demonstrated using a cohort of 132,139 women attending mammography screening in the State of Washington, USA.

Pantelis Samartsidis, Shaun R. Seaman, Anne M. Presanis, Matthew Hickman, Daniela De Angelis.

Source: Statistical Science, Volume 34, Number 3, 486--503.

Abstract:
Researchers are often challenged with assessing the impact of an intervention on an outcome of interest in situations where the intervention is nonrandomised, the intervention is only applied to one or few units, the intervention is binary, and outcome measurements are available at multiple time points. In this paper, we review existing methods for causal inference in these situations. We detail the assumptions underlying each method, emphasize connections between the different approaches and provide guidelines regarding their practical implementation. Several open problems are identified thus highlighting the need for future research.

Daniele Durante, Tommaso Rigon.

Source: Statistical Science, Volume 34, Number 3, 472--485.

Abstract:
Variational Bayes (VB) is a common strategy for approximate Bayesian inference, but simple methods are only available for specific classes of models including, in particular, representations having conditionally conjugate constructions within an exponential family. Models with logit components are an apparently notable exception to this class, due to the absence of conjugacy among the logistic likelihood and the Gaussian priors for the coefficients in the linear predictor. To facilitate approximate inference within this widely used class of models, Jaakkola and Jordan ( Stat. Comput. 10 (2000) 25–37) proposed a simple variational approach which relies on a family of tangent quadratic lower bounds of the logistic log-likelihood, thus restoring conjugacy between these approximate bounds and the Gaussian priors. This strategy is still implemented successfully, but few attempts have been made to formally understand the reasons underlying its excellent performance. Following a review on VB for logistic models, we cover this gap by providing a formal connection between the above bound and a recent Pólya-gamma data augmentation for logistic regression. Such a result places the computational methods associated with the aforementioned bounds within the framework of variational inference for conditionally conjugate exponential family models, thereby allowing recent advances for this class to be inherited also by the methods relying on Jaakkola and Jordan ( Stat. Comput. 10 (2000) 25–37).

Yuan Ke, Stanislav Minsker, Zhao Ren, Qiang Sun, Wen-Xin Zhou.

Source: Statistical Science, Volume 34, Number 3, 454--471.

Abstract:
We provide a survey of recent results on covariance estimation for heavy-tailed distributions. By unifying ideas scattered in the literature, we propose user-friendly methods that facilitate practical implementation. Specifically, we introduce elementwise and spectrumwise truncation operators, as well as their $M$-estimator counterparts, to robustify the sample covariance matrix. Different from the classical notion of robustness that is characterized by the breakdown property, we focus on the tail robustness which is evidenced by the connection between nonasymptotic deviation and confidence level. The key insight is that estimators should adapt to the sample size, dimensionality and noise level to achieve optimal tradeoff between bias and robustness. Furthermore, to facilitate practical implementation, we propose data-driven procedures that automatically calibrate the tuning parameters. We demonstrate their applications to a series of structured models in high dimensions, including the bandable and low-rank covariance matrices and sparse precision matrices. Numerical studies lend strong support to the proposed methods.

Qingyuan Zhao, Jingshu Wang, Wes Spiller, Jack Bowden, Dylan S. Small.

Source: Statistical Science, Volume 34, Number 2, 317--333.

Abstract:
Instrumental variable analysis is a widely used method to estimate causal effects in the presence of unmeasured confounding. When the instruments, exposure and outcome are not measured in the same sample, Angrist and Krueger ( J. Amer. Statist. Assoc. 87 (1992) 328–336) suggested to use two-sample instrumental variable (TSIV) estimators that use sample moments from an instrument-exposure sample and an instrument-outcome sample. However, this method is biased if the two samples are from heterogeneous populations so that the distributions of the instruments are different. In linear structural equation models, we derive a new class of TSIV estimators that are robust to heterogeneous samples under the key assumption that the structural relations in the two samples are the same. The widely used two-sample two-stage least squares estimator belongs to this class. It is generally not asymptotically efficient, although we find that it performs similarly to the optimal TSIV estimator in most practical situations. We then attempt to relax the linearity assumption. We find that, unlike one-sample analyses, the TSIV estimator is not robust to misspecified exposure model. Additionally, to nonparametrically identify the magnitude of the causal effect, the noise in the exposure must have the same distributions in the two samples. However, this assumption is in general untestable because the exposure is not observed in one sample. Nonetheless, we may still identify the sign of the causal effect in the absence of homogeneity of the noise.

Yixin Wang, Andrew C. Miller, David M. Blei.

Source: Statistical Science, Volume 34, Number 2, 229--233.

Wenhua Jiang.

Source: Statistical Science, Volume 34, Number 2, 219--223.

Abstract:
This is a contribution to the discussion of the enlightening paper by Professor Efron. We focus on empirical Bayes interval estimation. We discuss the oracle interval estimation rules, the empirical Bayes estimation of the oracle rule and the computation. Some numerical results are reported.

Timothy J. Schoenfeld
May 1, 2013; 33:7770-7777
BehavioralSystemsCognitive

Subhash Kulkarni
Oct 31, 2018; 38:9346-9354
Symposium and Mini-Symposium

Vinod Venkatraman
Mar 9, 2011; 31:3712-3718
BehavioralSystemsCognitive

Peter M. Zygmunt
Jun 1, 2002; 22:4720-4727
Behavioral

Fatma Deniz
Sep 25, 2019; 39:7722-7736
BehavioralSystemsCognitive

Sebastian Onasch
Apr 15, 2020; 40:3186-3202
Systems/Circuits

Erin E. Hecht
Sep 25, 2019; 39:7748-7758
BehavioralSystemsCognitive

Ye Zhang
Sep 3, 2014; 34:11929-11947
Cellular

Masaki Yamamoto
May 22, 2019; 39:4179-4192
Neurobiology of Disease

Michele Bellesi
May 24, 2017; 37:5263-5273
Cellular

Régis Trapeau
Mar 28, 2018; 38:3252-3264
BehavioralSystemsCognitive

Gert Holstege
Oct 8, 2003; 23:9185-9193
BehavioralSystemsCognitive

Michael N. Shadlen
May 15, 1998; 18:3870-3896
Articles

Ye Zhang
Sep 3, 2014; 34:11929-11947
Cellular

Italian translation of Press Release about BIS General Manager Agustín Carstens giving a speech on "Money in the digital age: what role for central banks?" (6 February 2018)

Italian translation of the Press Release on the pre-release of two special chapters of the Annual Economic Report of the BIS, 17 June 2018. Trust is the missing link in today's cryptocurrencies - Cryptocurrencies' model of generating trust limits their potential to replace conventional money, the Bank for International Settlements (BIS) writes in its Annual Economic Report (AER), a new title launched this year.

French translation of the BIS press release about the BIS Quarterly Review, March 2018

Discurso del Dr. Agustín Carstens, Director General del Banco de Pagos Internacionales, en la Celebración del 25 Aniversario de la Autonomía del Banco de México, Ciudad de México, 22 de noviembre de 2019.

Apple's new iPhone SE delivers incredible value and performance, has a surprisingly good camera, and handles videos well. Reviewers were impressed by the phone's A13 chipset. However, criticisms include insufficient battery life, absence of night mode, and lack of 5G support. "For those of us concerned about money ... the SE provides the greatest bang for the buck," said tech analyst Rob Enderle.

People have been giving presentations for thousands of years, from Moses with his stone tablets to Elon Musk revealing his grand plans to colonize Mars. While the elements of a great pitchman generally have remained the same over the past 5,000 years -- conviction, charisma, credibility -- today's successful presenters do more than just get in front of an audience and talk.

02020-02-05: Snow in Pennsylvania and New York

Paper by Mr Luiz Awazu Pereira da Silva, Deputy General Manager of the BIS, Enisse Kharroubi, Emanuel Kohlscheen and Benoît Mojon based on remarks at the University of Basel, 5 May 2019.

Speech by Mr Agustín Carstens, General Manager of the BIS, at the Founding Ceremony, Swiss Centre BIS Innovation Hub, Zurich, 8 October 2019.

Based on remarks by Mr Luiz Awazu Pereira da Silva, Deputy General Manager of the BIS, with Jon Frost and Leonardo Gambacorta at the Santander International Banking Conference on "Banking on trust: Building confidence in the future", Madrid, 5 November 2019.

Interview with Luiz A Pereira da Silva, Deputy General Manager of the BIS, in Central Banking, conducted by Ms Rachael King and published on 16 February 2020.

Mitochondrial fission catalyzed by dynamin-related protein 1 (Drp1) is necessary for mitochondrial biogenesis and maintenance of healthy mitochondria. However, excessive fission has been associated with multiple neurodegenerative disorders, and we recently reported that mice with smaller mitochondria are sensitized to ischemic stroke injury. Although pharmacological Drp1 inhibition has been put forward as neuroprotective, the specificity and mechanism of the inhibitor used is controversial. Here, we provide genetic evidence that Drp1 inhibition is neuroprotective. Drp1 is activated by dephosphorylation of an inhibitory phosphorylation site, Ser637. We identify Bβ2, a mitochondria-localized protein phosphatase 2A (PP2A) regulatory subunit, as a neuron-specific Drp1 activator in vivo. Bβ2 KO mice of both sexes display elongated mitochondria in neurons and are protected from cerebral ischemic injury. Functionally, deletion of Bβ2 and maintained Drp1 Ser637 phosphorylation improved mitochondrial respiratory capacity, Ca²⁺ homeostasis, and attenuated superoxide production in response to ischemia and excitotoxicity in vitro and ex vivo. Last, deletion of Bβ2 rescued excessive stroke damage associated with dephosphorylation of Drp1 S637 and mitochondrial fission. These results indicate that the state of mitochondrial connectivity and PP2A/Bβ2-mediated dephosphorylation of Drp1 play a critical role in determining the severity of cerebral ischemic injury. Therefore, Bβ2 may represent a target for prophylactic neuroprotective therapy in populations at high risk of stroke.

SIGNIFICANCE STATEMENT With recent advances in clinical practice including mechanical thrombectomy up to 24 h after the ischemic event, there is resurgent interest in neuroprotective stroke therapies. In this study, we demonstrate reduced stroke damage in the brain of mice lacking the Bβ2 regulatory subunit of protein phosphatase 2A, which we have shown previously acts as a positive regulator of the mitochondrial fission enzyme dynamin-related protein 1 (Drp1). Importantly, we provide evidence that deletion of Bβ2 can rescue excessive ischemic damage in mice lacking the mitochondrial PKA scaffold AKAP1, apparently via opposing effects on Drp1 S637 phosphorylation. These results highlight reversible phosphorylation in bidirectional regulation of Drp1 activity and identify Bβ2 as a potential pharmacological target to protect the brain from stroke injury.

The cerebellum influences motor control through Purkinje target neurons, which transmit cerebellar output. Such output is required, for instance, for larval zebrafish to learn conditioned fictive swimming. The output cells, called eurydendroid neurons (ENs) in teleost fish, are inhibited by Purkinje cells and excited by parallel fibers. Here, we investigated the electrophysiological properties of glutamatergic ENs labeled by the transcription factor olig2. Action potential firing and synaptic responses were recorded in current clamp and voltage clamp from olig2⁺ neurons in immobilized larval zebrafish (before sexual differentiation) and were correlated with motor behavior by simultaneous recording of fictive swimming. In the absence of swimming, olig2⁺ ENs had basal firing rates near 8 spikes/s, and EPSCs and IPSCs were evident. Comparing Purkinje firing rates and eurydendroid IPSC rates indicated that 1-3 Purkinje cells converge onto each EN. Optogenetically suppressing Purkinje simple spikes, while preserving complex spikes, suggested that eurydendroid IPSC size depended on presynaptic spike duration rather than amplitude. During swimming, EPSC and IPSC rates increased. Total excitatory and inhibitory currents during sensory-evoked swimming were both more than double those during spontaneous swimming. During both spontaneous and sensory-evoked swimming, the total inhibitory current was more than threefold larger than the excitatory current. Firing rates of ENs nevertheless increased, suggesting that the relative timing of IPSCs and EPSCs may permit excitation to drive additional eurydendroid spikes. The data indicate that olig2⁺ cells are ENs whose activity is modulated with locomotion, suiting them to participate in sensorimotor integration associated with cerebellum-dependent learning.

SIGNIFICANCE STATEMENT The cerebellum contributes to movements through signals generated by cerebellar output neurons, called eurydendroid neurons (ENs) in fish (cerebellar nuclei in mammals). ENs receive sensory and motor signals from excitatory parallel fibers and inhibitory Purkinje cells. Here, we report electrophysiological recordings from ENs of larval zebrafish that directly illustrate how synaptic inhibition and excitation are integrated by cerebellar output neurons in association with motor behavior. The results demonstrate that inhibitory and excitatory drive both increase during fictive swimming, but inhibition greatly exceeds excitation. Firing rates nevertheless increase, providing evidence that synaptic integration promotes cerebellar output during locomotion. The data offer a basis for comparing aspects of cerebellar coding that are conserved and that diverge across vertebrates.

Hepatocyte growth factor (HGF) is a multifunctional protein that signals through the MET receptor. HGF stimulates cell proliferation, cell dispersion, neuronal survival, and wound healing. In the inner ear, levels of HGF must be fine-tuned for normal hearing. In mice, a deficiency of HGF expression limited to the auditory system, or an overexpression of HGF, causes neurosensory deafness. In humans, noncoding variants in HGF are associated with nonsyndromic deafness DFNB39. However, the mechanism by which these noncoding variants causes deafness was unknown. Here, we reveal the cause of this deafness using a mouse model engineered with a noncoding intronic 10 bp deletion (del10) in Hgf. Male and female mice homozygous for del10 exhibit moderate-to-profound hearing loss at 4 weeks of age as measured by tone burst auditory brainstem responses. The wild type (WT) 80 mV endocochlear potential was significantly reduced in homozygous del10 mice compared with WT littermates. In normal cochlea, endocochlear potentials are dependent on ion homeostasis mediated by the stria vascularis (SV). Previous studies showed that developmental incorporation of neural crest cells into the SV depends on signaling from HGF/MET. We show by immunohistochemistry that, in del10 homozygotes, neural crest cells fail to infiltrate the developing SV intermediate layer. Phenotyping and RNAseq analyses reveal no other significant abnormalities in other tissues. We conclude that, in the inner ear, the noncoding del10 mutation in Hgf leads to developmental defects of the SV and consequently dysfunctional ion homeostasis and a reduction in the EP, recapitulating human DFNB39 nonsyndromic deafness.

SIGNIFICANCE STATEMENT Hereditary deafness is a common, clinically and genetically heterogeneous neurosensory disorder. Previously, we reported that human deafness DFNB39 is associated with noncoding variants in the 3'UTR of a short isoform of HGF encoding hepatocyte growth factor. For normal hearing, HGF levels must be fine-tuned as an excess or deficiency of HGF cause deafness in mouse. Using a Hgf mutant mouse with a small 10 bp deletion recapitulating a human DFNB39 noncoding variant, we demonstrate that neural crest cells fail to migrate into the stria vascularis intermediate layer, resulting in a significantly reduced endocochlear potential, the driving force for sound transduction by inner ear hair cells. HGF-associated deafness is a neurocristopathy but, unlike many other neurocristopathies, it is not syndromic.