arXiv subjects

Anthony C. Davison

Publications and source records attributed to Anthony C. Davison.

At least 19 recordsLinked to original sources

arXiv2026

Choosing the threshold in extreme value analysis

One of the two dominant approaches for univariate extreme value analysis is to model exceedances above a large threshold, the choice of which has a large impact on inference and whose uncertainty is often subsequently ignored. In this article we review more than 40 threshold selection procedures, including semiparametric methods based on Hill's estimator, visual diagnostics, goodness-of-fit tests, and others based on extended generalized Pareto models. Starting with the statistical properties underlying the various proposals, we provide a critical assessment of their strengths and weaknesses, discuss how they might be automated and describe the results of an extensive simulation study used to identify the most promising procedures. The approaches are compared using a long time series of daily rainfall totals from Padova.

stat.ME↗

arXiv2026

How long should a block be?

The block maximum method, which is widely used in extreme value analysis, uses a generalized extreme value distribution to approximate that of the maximum of m observations. The quality of this approximation depends on the value of m and may be poor if m is too small. Surprisingly little attention has been paid to the choice of the block length, although a good choice is crucial to the success of the method. In this paper we assess the effect of taking excessively long blocks in terms of asymptotic relative efficiency, and propose likelihood-based approaches and graphical diagnostics to determine whether a proposed block length is suitable, allowing for potential rounding and left-censoring of observations. We investigate our ideas using simulation and illustrate them using wind speed, river flow and rainfall data.

stat.ME↗

arXiv2025

Heavy-tailed max-linear structural equation models in networks with hidden nodes

Recursive max-linear vectors provide models for causal dependence between large values of random variables that are supported on directed acyclic graphs, but the standard assumption that all nodes of such a graph are observed can be unrealistic. We give necessary and sufficient conditions for a partially observed recursive max-linear vector to be representable as a recursive max-linear (sub-)model and provide a graphical algorithm to construct the latter. Our conditions concern the max-weighted paths of a directed acyclic graph and its minimal representation, which play a key role for such models. In the framework of regular variation we translate these conditions into checkable criteria and establish a connection between max-weighted paths and the extremal dependence measure of transformed variables for pairs of nodes. We propose a statistical algorithm to detect bivariate regularly varying recursive max-linear models among the node variables of a directed acyclic graph and show consistency and asymptotic normality of the estimators of the extremal dependence measure under a thresholding procedure. Simulations show that our algorithm performs satisfactorily. We apply it to nutrition intake data.

math.ST↗

arXiv2025

Inference on the Miss Distance in a Conjunction

Over the last quarter-century, spacecraft conjunction assessment has focused on a quantity associated by its advocates with collision probability. This quantity has a well-known dilution feature, where it is small when uncertainty is large, giving rise to false confidence that a conjunction is safe when it is not. An alternative approach to conjunction assessment is to assess the missed detection probability that the best available information indicates the conjunction to be safe, when it is actually unsafe. In other words, the alternative seeks to answer the question of whether unknowable errors in the best available data might be especially unlucky. A proper implementation of this alternative avoids dilution and false confidence. Implementations of the alternative use either significance probabilities (p-values) associated with a null hypothesis that the miss distance is small, or confidence intervals on the miss distance. Both approaches rely on maximum likelihood principles to deal with nuisance variables, rather than marginalization. This paper discusses the problems with the traditional approach, and summarizes other work that developed the alternative approach. The paper presents examples of application of the alternatives using data from actual conjunctions experienced in operations, including synthetic scaling to highlight contrasts between the alternative and the traditional approach.

stat.AP↗

arXiv2025

Statistical Inference on the Miss Distance Compared to Collision Probability for Conjunction Analysis

Satellite conjunctions involving near misses of space objects are increasingly common, especially with the growth of satellite constellations and space debris. Accurate risk analysis for these events is essential to prevent collisions and manage space traffic. Traditional methods for assessing collision risk, such as calculating the so-called collision probability, are widely used but have limitations, including counterintuitive interpretations when uncertainty in the state vector is large. To address these limitations, we build on an alternative approach proposed by Elkantassi and Davison (2022) that uses a statistical model allowing inference on the miss distance between two objects in the presence of nuisance parameters. This model provides significance probabilities for a null hypothesis that assumes a small miss distance and allows the construction of confidence intervals, leading to another interpretation of collision risk. In this study, we compare this approach with the traditional use of pc across a large, NASA-provided dataset of real conjunctions, in order to evaluate its reliability and to refine the statistical framework to improve its suitability for operational decision-making. We also discuss constraints that could limit the practical use of such alternative approaches.

stat.AP↗

arXiv2024

Space-time extremes of severe US thunderstorm environments

Severe thunderstorms cause substantial economic and human losses in the United States. Simultaneous high values of convective available potential energy (CAPE) and storm relative helicity (SRH) are favorable to severe weather, and both they and the composite variable $\mathrm{PROD}=\sqrt{\mathrm{CAPE}} \times \mathrm{SRH}$ can be used as indicators of severe thunderstorm activity. Their extremal spatial dependence exhibits temporal non-stationarity due to seasonality and large-scale atmospheric signals such as El Niño-Southern Oscillation (ENSO). In order to investigate this, we introduce a space-time model based on a max-stable, Brown--Resnick, field whose range depends on ENSO and on time through a tensor product spline. We also propose a max-stability test based on empirical likelihood and the bootstrap. The marginal and dependence parameters must be estimated separately owing to the complexity of the model, and we develop a bootstrap-based model selection criterion that accounts for the marginal uncertainty when choosing the dependence model. In the case study, the out-sample performance of our model is good. We find that extremes of PROD, CAPE and SRH are generally more localized in summer and, in some regions, less localized during El Niño and La Niña events, and give meteorological interpretations of these phenomena.

stat.AP↗

arXiv2023

Bayesian modeling of insurance claims for hail damage

Despite its importance for insurance, there is almost no literature on statistical hail damage modeling. Statistical models for hailstorms exist, though they are generally not open-source, but no study appears to have developed a stochastic hail impact function. In this paper, we use hail-related insurance claim data to build a Gaussian line process with extreme marks to model both the geographical footprint of a hailstorm and the damage to buildings that hailstones can cause. We build a model for the claim counts and claim values, and compare it to the use of a benchmark deterministic hail impact function. Our model proves to be better than the benchmark at capturing hail spatial patterns and allows for localized and extreme damage, which is seen in the insurance data. The evaluation of both the claim counts and value predictions shows that performance is improved compared to the benchmark, especially for extreme damage. Our model appears to be the first to provide realistic estimates for hail damage to individual buildings.

stat.AP↗

arXiv2022

Causal Modelling of Heavy-Tailed Variables and Confounders with Application to River Flow

Confounding variables are a recurrent challenge for causal discovery and inference. In many situations, complex causal mechanisms only manifest themselves in extreme events, or take simpler forms in the extremes. Stimulated by data on extreme river flows and precipitation, we introduce a new causal discovery methodology for heavy-tailed variables that allows the effect of a known potential confounder to be almost entirely removed when the variables have comparable tails, and also decreases it sufficiently to enable correct causal inference when the confounder has a heavier tail. We also introduce a new parametric estimator for the existing causal tail coefficient and a permutation test. Simulations show that the methods work well and the ideas are applied to the motivating dataset.

stat.ME↗

arXiv2022

Bayesian nonparametric mixture inconsistency for the number of components: How worried should we be in practice?

We consider the Bayesian mixture of finite mixtures (MFMs) and Dirichlet process mixture (DPM) models for clustering. Recent asymptotic theory has established that DPMs overestimate the number of clusters for large samples and that estimators from both classes of models are inconsistent for the number of clusters under misspecification, but the implications for finite sample analyses are unclear. The final reported estimate after fitting these models is often a single representative clustering obtained using an MCMC summarisation technique, but it is unknown how well such a summary estimates the number of clusters. Here we investigate these practical considerations through simulations and an application to gene expression data, and find that (i) DPMs overestimate the number of clusters even in finite samples, but only to a limited degree that may be correctable using appropriate summaries, and (ii) misspecification can lead to considerable overestimation of the number of clusters in both DPMs and MFMs, but results are nevertheless often still interpretable. We provide recommendations on MCMC summarisation and suggest that although the more appealing asymptotic properties of MFMs provide strong motivation to prefer them, results obtained using MFMs and DPMs are often very similar in practice.

stat.ME↗

arXiv2022

The Tangent Exponential Model

The likelihood function is central to both frequentist and Bayesian formulations of parametric statistical inference, and large-sample approximations to the sampling distributions of estimators and test statistics, and to posterior densities, are widely used in practice. Improved approximations have been widely studied and can provide highly accurate inferences when samples are small or there are many nuisance parameters. This article reviews improved approximations based on the tangent exponential model developed in a series of articles by D.~A.~S.~Fraser and co-workers, attempting to explain the theoretical basis of this model and to provide a guide to the associated literature, including a partially-annotated bibliography.

stat.ME↗

arXiv2022

Functional Peaks-over-threshold Analysis

Peaks-over-threshold analysis using the generalized Pareto distribution is widely applied in modelling tails of univariate random variables, but much information may be lost when complex extreme events are studied using univariate results. In this paper, we extend peaks-over-threshold analysis to extremes of functional data. Threshold exceedances defined using a functional $r$ are modelled by the generalized $r$-Pareto process, a functional generalization of the generalized Pareto distribution that covers the three classical regimes for the decay of tail probabilities, and that is the only possible continuous limit for $r$-exceedances of a properly rescaled process. We give construction rules, simulation algorithms and inference procedures for generalized $r$-Pareto processes, discuss model validation, and use the new methodology to study extreme European windstorms and heavy spatial rainfall.

stat.ME↗

arXiv2021

Tail risk inference via expectiles in heavy-tailed time series

Expectiles define the only law-invariant, coherent and elicitable risk measure apart from the expectation. The popularity of expectile-based risk measures is steadily growing and their properties have been studied for independent data, but further results are needed to use extreme expectiles with dependent time series such as financial data. In this paper we establish a basis for inference on extreme expectiles and expectile-based marginal expected shortfall in a general $β$-mixing context that encompasses ARMA, ARCH and GARCH models with heavy-tailed innovations. Simulations and applications to financial returns show that the new estimators and confidence intervals greatly improve on existing ones when the data are dependent.

stat.ME↗

arXiv2021

Is there a cap on longevity? A statistical review

There is sustained and widespread interest in understanding the limit, if any, to the human lifespan. Apart from its intrinsic and biological interest, changes in survival in old age have implications for the sustainability of social security systems. A central question is whether the endpoint of the underlying lifetime distribution is finite. Recent analyses of data on the oldest human lifetimes have led to competing claims about survival and to some controversy, due in part to incorrect statistical analysis. This paper discusses the particularities of such data, outlines correct ways of handling them and presents suitable models and methods for their analysis. We provide a critical assessment of some earlier work and illustrate the ideas through reanalysis of semi-supercentenarian lifetime data. Our analysis suggests that remaining life-length after age 109 is exponentially distributed, and that any upper limit lies well beyond the highest lifetime yet reliably recorded. Lower limits to 95% confidence intervals for the human lifespan are around 130 years, and point estimates typically indicate no upper limit at all.

stat.AP↗

arXiv2020

Human mortality at extreme age

We use a combination of extreme value theory, survival analysis and computer-intensive methods to analyze the mortality of Italian and French semi-supercentenarians for whom there are validated records. After accounting for the effects of the sampling frame, there appears to be a constant rate of mortality beyond age 108 years and no difference between countries and cohorts. These findings are consistent with previous work based on the International Database on Longevity and suggest that any physical upper bound for humans is so large that it is unlikely to be approached. There is no evidence of differences in survival between women and men after age 108 in the Italian data and the International Database on Longevity; however survival is lower for men in the French data.

stat.AP↗

arXiv2020

Improved inference on risk measures for univariate extremes

We discuss the use of likelihood asymptotics for inference on risk measures in univariate extreme value problems, focusing on estimation of high quantiles and similar summaries of risk for uncertainty quantification. We study whether higher-order approximation based on the tangent exponential model can provide improved inferences, and conclude that inference based on maxima is generally robust to mild model misspecification and that profile likelihood-based confidence intervals will often be adequate, whereas inferences based on threshold exceedances can be badly biased but may be improved by higher-order methods, at least for moderate sample sizes. We use the methods to shed light on catastrophic rainfall in Venezuela, flooding in Venice, and the lifetimes of Italian semi-supercentenarians.

stat.ME↗

arXiv2020

A global-local approach for detecting hotspots in multiple-response regression

We tackle modelling and inference for variable selection in regression problems with many predictors and many responses. We focus on detecting hotspots, i.e., predictors associated with several responses. Such a task is critical in statistical genetics, as hotspot genetic variants shape the architecture of the genome by controlling the expression of many genes and may initiate decisive functional mechanisms underlying disease endpoints. Existing hierarchical regression approaches designed to model hotspots suffer from two limitations: their discrimination of hotspots is sensitive to the choice of top-level scale parameters for the propensity of predictors to be hotspots, and they do not scale to large predictor and response vectors, e.g., of dimensions $10^3-10^5$ in genetic applications. We address these shortcomings by introducing a flexible hierarchical regression framework that is tailored to the detection of hotspots and scalable to the above dimensions. Our proposal implements a fully Bayesian model for hotspots based on the horseshoe shrinkage prior. Its global-local formulation shrinks noise globally and hence accommodates the highly sparse nature of genetic analyses, while being robust to individual signals, thus leaving the effects of hotspots unshrunk. Inference is carried out using a fast variational algorithm coupled with a novel simulated annealing procedure that allows efficient exploration of multimodal distributions.

stat.AP↗

arXiv2019

An Unethical Optimization Principle

If an artificial intelligence aims to maximise risk-adjusted return, then under mild conditions it is disproportionately likely to pick an unethical strategy unless the objective function allows sufficiently for this risk. Even if the proportion $η$ of available unethical strategies is small, the probability ${p_U}$ of picking an unethical strategy can become large; indeed unless returns are fat-tailed ${p_U}$ tends to unity as the strategy space becomes large. We define an Unethical Odds Ratio Upsilon ($Υ$) that allows us to calculate ${p_U}$ from $η$, and we derive a simple formula for the limit of $Υ$ as the strategy space becomes large. We give an algorithm for estimating $Υ$ and ${p_U}$ in finite cases and discuss how to deal with infinite strategy spaces. We show how this principle can be used to help detect unethical strategies and to estimate $η$. Finally we sketch some policy implications of this work.

q-fin.RM↗

arXiv2019

Trends in the extremes of environments associated with severe US thunderstorms

Severe thunderstorms can have devastating impacts. Concurrently high values of convective available potential energy (CAPE) and storm relative helicity (SRH) are known to be conducive to severe weather, so high values of PROD=$\sqrt{\mathrm{CAPE}} \times$SRH have been used to indicate high risk of severe thunderstorms. We consider the extreme values of these three variables for a large area of the contiguous US over the period 1979-2015, and use extreme-value theory and a multiple testing procedure to show that there is a significant time trend in the extremes for PROD maxima in April, May and August, for CAPE maxima in April, May and June, and for maxima of SRH in April and May. These observed increases in CAPE are also relevant for rainfall extremes and are expected in a warmer climate, but have not previously been reported. Moreover, we show that the El Niño-Southern Oscillation explains variation in the extremes of PROD and SRH in February. Our results suggest that the risk from severe thunderstorms in April and May is increasing in parts of the US where it was already high, and that the risk from storms in February tends to be higher over the main part of the region during La Niña years. Our results differ from those obtained in earlier studies using extreme-value techniques to analyze a quantity similar to PROD.

stat.AP↗