Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

McGill University

$62,000.00

Multivariate models and methods for risk assessment

FY 2024-25

Summary
The long-term goal of my research program is to develop stochastic models and statistical inference procedures for the study of dependence between heterogeneous risks, with a focus on cases where rare events could have major economic consequences or affect public safety. This topic is of great importance, e.g., in insurance and environmental science, where responsible risk management requires a careful assessment of the frequency and magnitude of large, interconnected claims or natural phenomena such as heavy rain and floods over vast domains. Multivariate analysis and extreme-value theory provide a broad array of useful techniques for modeling correlated risks and rare events. Copula modeling, which I have developed and promoted for nearly 40 years, is particularly flexible in describing relationships within large sets of heterogeneous variables, whose behavior may even depend on covariates. However, appropriate inference methods largely remain to be developed for this class of models when complex dependence patterns involve large sets of heterogeneous risks with a mix of discrete and continuous variables often exhibiting wildly different tail behavior. In addition to closing this gap, I will contribute to the development of new, hierarchical strategies for the construction of practical, interpretable, and scalable multivariate models for phenomena varying in time and space, with a particular attention to low-probability, high-impact events. I will also assess the sampling and predictive properties of parametric, semi- and non-parametric estimation techniques and testing procedures for the selection, adjustment and validation of such models, both within the classical and Bayesian paradigms. Finally, I will apply these techniques in various natural science and engineering contexts where the quantification of complex, interconnected risks is crucial to estimate the consequences of potentially catastrophic events and to develop mitigation measures, particularly in the wake of climate change. In the recent past, my work was largely motivated by concrete problems faced by risk managers from the public and private sector. This practice will continue. Overall, my research will help to improve ways in which statisticians, actuaries and other researchers model multivariate data. It will contribute to the growing statistical literature on high-dimensional, spatial dependence modeling of extreme phenomena and will have measurable impact in fields such as insurance, environmental science, and risk management. All new methodology will be made accessible to practitioners through the R Project for Statistical Computing.
Program
Discovery Grants Program - Individual
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2024-04088
Name nom
Genest, Christian
Department département
Mathematics and Statistics
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
62000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1508
Committee name en
Mathematics and Statistics
Committee name fr
Mathématiques et statistique
Area of application code
405
Area of application group en
Environment
Area of application group fr
Environnement
Area of application en
Modelling and mathematical simulation of natural processes
Area of application fr
Modélisation et simulation mathématique des processus naturels
Research subject code
3011
Research subject group en
Statistics and probability
Research subject group fr
Statistique et probabilité
Research subject en
Multivariate analysis
Research subject fr
Analyse multivariée
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Multivariate models and methods for risk assessment
Keywords
copula models; dependent risks; discrete data; empirical processes; extreme-value theory; hierarchical structures; multivariate analysis; nonparametric methods; rank-based inference; spatial statistics
Application summary
The long-term goal of my research program is to develop stochastic models and statistical inference procedures for the study of dependence between heterogeneous risks, with a focus on cases where rare events could have major economic consequences or affect public safety. This topic is of great importance, e.g., in insurance and environmental science, where responsible risk management requires a careful assessment of the frequency and magnitude of large, interconnected claims or natural phenomena such as heavy rain and floods over vast domains. Multivariate analysis and extreme-value theory provide a broad array of useful techniques for modeling correlated risks and rare events. Copula modeling, which I have developed and promoted for nearly 40 years, is particularly flexible in describing relationships within large sets of heterogeneous variables, whose behavior may even depend on covariates. However, appropriate inference methods largely remain to be developed for this class of models when complex dependence patterns involve large sets of heterogeneous risks with a mix of discrete and continuous variables often exhibiting wildly different tail behavior. In addition to closing this gap, I will contribute to the development of new, hierarchical strategies for the construction of practical, interpretable, and scalable multivariate models for phenomena varying in time and space, with a particular attention to low-probability, high-impact events. I will also assess the sampling and predictive properties of parametric, semi- and non-parametric estimation techniques and testing procedures for the selection, adjustment and validation of such models, both within the classical and Bayesian paradigms. Finally, I will apply these techniques in various natural science and engineering contexts where the quantification of complex, interconnected risks is crucial to estimate the consequences of potentially catastrophic events and to develop mitigation measures, particularly in the wake of climate change. In the recent past, my work was largely motivated by concrete problems faced by risk managers from the public and private sector. This practice will continue. Overall, my research will help to improve ways in which statisticians, actuaries and other researchers model multivariate data. It will contribute to the growing statistical literature on high-dimensional, spatial dependence modeling of extreme phenomena and will have measurable impact in fields such as insurance, environmental science, and risk management. All new methodology will be made accessible to practitioners through the R Project for Statistical Computing.