A5079609969- Probability and Risk Models
- Insurance, Mortality, Demography, Risk Management
- Statistical Methods and Bayesian Inference
- Insurance and Financial Risk Management
- Nuclear reactor physics and engineering
- Optimal Experimental Design Methods
- Advanced Causal Inference Techniques
- Advanced Statistical Process Monitoring
- Statistical Methods and Inference
- Statistical Distribution Estimation and Applications
- Advanced Statistical Methods and Models
- Sleep and Work-Related Fatigue
- Bayesian Methods and Mixture Models
- Statistical Methods in Clinical Trials
- COVID-19 epidemiological studies
- Employment and Welfare Studies
- Health disparities and outcomes
HEC Montréal
2020-2025
McGill University
2015-2018
Traditionally, claim counts and amounts are assumed to be independent in non-life insurance. This paper explores how this often unwarranted assumption can relaxed a simple way while incorporating rating factors into the model. The approach consists of fitting generalized linear models marginal frequency conditional severity components total cost; dependence between them is induced by treating number claims as covariate model for average size. In addition being easy implement, modeling...
The goal of precision medicine is to tailor treatment strategies on an individual patient level. Although several estimation techniques have been developed for determining optimal rules, the majority methods focus case a dichotomous treatment, example being dynamic weighted ordinary least squares regression approach Wallace and Moodie. We propose extension aforementioned framework allow continuous with ultimate estimating dosing strategies. proposed method shown be doubly robust against...
Abstract Multi‐dimensional data frequently occur in many different fields, including risk management, insurance, biology, environmental sciences, and more. In analyzing multivariate data, it is imperative that the underlying modelling assumptions adequately reflect both marginal behaviour associations between components. This article focuses specifically on developing a new Poisson model appropriate for multi‐dimensional count data. The proposed formulation based convolutions of comonotonic...
A variant of the bivariate Poisson common shock model is proposed which, contrary to original, spans all possible degrees dependence. Its basic distributional properties are described, moment-based estimation studied, and its use illustrated on real data.
In this paper, we consider some potential pitfalls of the growing use quasi‐likelihood‐based information criteria for longitudinal data to select a working correlation structure in generalized estimating equation framework. particular, examine settings where fully conditional mean does not equal marginal as well hypothesis testing following selection matrix. Our results suggest that any criterion matrix is inappropriate when model assumption violated. We also find type I error differs from...
Comonotonicity and counter-monotonicity refer to the strongest possible form of dependence, namely perfect positive negative respectively. For continuous random vectors, comonotonicity implies a functional relation between components and, hence reduction in dimensionality problem. The case variables with discrete margins is much more complex, however. goal this article review notion particular emphasis on case, as well its implications for likelihood-based estimation.
Multi-dimensional data frequently occur in many different fields, including risk management, insurance, biology, environmental sciences, and more. In analyzing multivariate data, it is imperative that the underlying modelling assumptions adequately reflect both marginal behavior as well associations between components. This work focuses specifically on developing a new Poisson model appropriate for multi-dimensional count data. The proposed formulation based convolutions of comonotonic shock...
Journal Article Accepted manuscript No unmeasured confounding: Known unknowns or... not? Get access Juliana Schulz, Schulz HEC Montréal Department of Decision Sciences Montreal, QC, Canada 514-340-7041 Search for other works by this author on: Oxford Academic PubMed Google Scholar Erica E M Moodie, Moodie McGill University Epidemiology, Biostatistics, and Occupational Health 514-398-5520 Corresponding Author E-mail: erica.moodie@mcgill.ca Susan Shortreed Kaiser Permanente Washington Research...
Summary Multivariate count data arise naturally in practice. In analysing such data, it is critical to define a model that can accurately capture the underlying dependence structure between counts. To this end, paper develops multivariate wherein correlated Poisson margins are generated by comonotonic shock vector. The proposed allows for greater flexibility than of classical construction, which relies on convolution vectors common variables. Several probabilistic properties established, and...
ABSTRACT Introduction Research on the health of older Veterans in Canada is an emerging area. Few population-based studies have included as a specific group interest. This paper describes cohort self-identified within Canadian Longitudinal Study Aging (CLSA). Materials and Methods Using data from CLSA baseline assessment (2011-2015), we describe sociodemographic characteristics along with military-related variables Canada. We also estimate number non-Canadian living at time collection....