Salaheddine El Adlouni

Comparison of methodologies to assess the convergence of Markov chain Monte Carlo methods

One major challenge with the modelization of complex problems using Markov chain Monte Carlo (MCMC) methods is the determination of the length of the chain in order to reach convergence. This paper is devoted to parametric empirical methods testing the stationarity. We compare the methods of Gelman and Rubin, Yu and Mykland, Raftery and Lewis, Geweke, Riemann sums and the subsampling. These methods are tested using three examples: the simple case of the generation of a normal random variable, a bivariate mixture of normal models and a practical case taken from hydrology, namely the shifting level model. Results show that no method works in every case. We therefore suggest a joint use of these techniques. The importance of determining carefully the burn-in period is also highlighted.

Spatial variability of climate effects on ischemic heart disease hospitalization rates for the period 1989-2006 in Quebec, Canada

BackgroundStudies have suggested an association between climate variables and circulatory diseases. The short-term effect of climate conditions on the incidence of ischemic heart disease (IHD) over the 1989-2006 period was examined for Quebecs 18 health regions.MethodsAnalyses were carried out for two age groups. A GAM statistical model, that blends the properties of generalized linear models with additive models, was used to fit the standardized daily hospitalization rates for IHD and their relationship with climatic conditions up to two weeks prior to the day of admission, controlling for time trends, day of the season and gender.ResultsResults show that, in most of Quebecs regions, cold temperatures during winter months and hot episodes during the summer months are associated with an increase of up to 12% in the daily hospital admission rate for IHD but also show decreased risks in some areas. The risk of hospitalization is higher for men and women of 45-64 years and varies spatially. In most regions, exposure to a continuous period of cold or hot temperature was more harmful than just one isolated day of extreme weather. Men aged 45-64 years showed higher risk levels of IHD than women of the same age group. In most regions, the annual maximum of daily IHD admissions for 65 years old was reached earlier in the season for both genders and both seasons compared to younger age groups. The effects of meteorological variables on the daily IHD admissions rate were more pronounced in regions with high smoking prevalence and high deprivation index.ConclusionThis study highlights the differential effects of cold and hot periods on IHD in Quebec health regions depending on age, sex, and other factors such as smoking, behaviour and deprivation levels.

Effects of climate on West Nile Virus transmission risk used for public health decision-making in Quebec

BackgroundIn 2002, major human epidemics of West Nile Virus (WNV) were reported in five cities in the North East region of North America. The present analysis examines the climatic conditions that were conducive to the WNV epidemic, in order to provide information to public health managers who eventually must decide on the implementation of a preventive larvicide spraying program in Quebec, Canada. Two sets of variables, the first observed in the summer of 2002 and the second in the preceding winter were analysed to study their potential as explanatory variables for the emergence of the virus at epidemic levels.ResultsResults show that the climatic conditions observed in the year 2002 have contributed to the emergence of the virus and can be observed once every forty years on average. The analysis has shown that the 2002 events observed in several North East North American cities are characterized by two main variables: the number of degree-days below -5°C in the winter (DD-5) and the number of degree-days greater than 25°C in the summer (DD25).ConclusionIn the context of a declining rate of human and aviary infection to WNV, this element contributed to the decision to suspend the use of preventive larvicides in the province of Quebec in 2006 and for the foreseeable future. The second part of this study indicates that it is very important to estimate the risk that extreme values can be observed simultaneously in the summer and in the winter preceding the appearance of the virus. The proposed models provide important information to public health officials, weeks before the appearance of the virus, and can therefore be useful to help prevent human epidemics.

A nested multivariate copula approach to hydrometeorological simulations of spring floods: the case of the Richelieu River (Québec, Canada) record flood

Floods have potentially devastating consequences on populations, industries and environmental systems. They often result from a combination of effects from meteorological, physiographic and anthropogenic natures. The analysis of flood hazards under a multivariate perspective is primordial to evaluate several of the combined factors. This study analyzes spring flood-causing mechanisms in terms of the occurrence, frequency, duration and intensity of precipitation as well as temperature events and their combinations previous to and during floods using frequency analysis as well as a proposed multivariate copula approach along with hydrometeorological indices. This research was initiated over the Richelieu River watershed (Quebec, Canada), with a particular emphasis on the 2011 spring flood, constituting one of the most damaging events over the last century for this region. Although some work has already been conducted to determine certain causes of this record flood, the use of multivariate statistical analysis of hydrologic and meteorological events has not yet been explored. This study proposes a multivariate flood risk model based on fully nested Archimedean Frank and Clayton copulas in a hydrometeorological context. Several combinations of the 2011 Richelieu River flood-causing meteorological factors are determined by estimating joint and conditional return periods with the application of the proposed model in a trivariate case. The effects of the frequency of daily frost/thaw episodes in winter, the cumulative total precipitation fallen between the months of November and March and the 90th percentile of rainfall in spring on peak flow and flood duration are quantified, as these combined factors represent relevant drivers of this 2011 Richelieu River record flood. Multiple plausible and physically founded flood-causing scenarios are also analyzed to quantify various risks of inundation.

Combining Communication Technology Utilization and Organizational Innovation: Evidence from Canadian Healthcare Decision Makers

Information and Communication Technology (ICT) and Organizational Innovation (OI) are seen as the miracle of post-modernity in organizations. In this way, they are supposed to resolve most organizational problems, efficiently and rapidly. OI is highly dependent on the capacity and the investment in knowledge management (internal and external) to support decision making process and to implement significant changes. We know what explains ICT utilization (ICTU) and what determines OI development (OID) in healthcare services. Moreover, the literature tends to link ICTU to OID and vice versa. However, this dependency has never been explored empirically through the lens of roles combination. To identify the existing combined roles profiles of ICTU and OID among healthcare decision makers and determine factors of the shift from a profile to another. We did the following: (1) a structured review of the literature on healthcare management by focusing on ICTU and OID which allowed us to build two indexes and a comprehensive framework; (2) a copula methodology to identify with high precision the thresholds for ICTU and OID; and (3) a cross-sectional study based on a survey done with a sample of 942 decision makers from Canadian healthcare organizations through a multinomial logit model to identify determinants of the shift. ICTU and OID are correlated at 22% (Kendal’s Tau). The joint distribution (combination) of ICTU and OID shows that four major profiles exist among decision makers in Canadian healthcare organizations: the traditional decision maker, the innovative decision maker, the technologic decision maker and the contemporary decision maker. We found out that classic factors act as barriers to the shift from one profile to the desired profile (from 1 to 4, from 2 to 4 and from 3 to 4). We have identified that the attitude toward research and relational capital are transversal barriers of shift. We have also found that some factors have a specific impact such as engaging in activities of research acquisition, the administrative position (being a manager), the preference for applied research results as source of information, the degree of novelty of research results, and the gender. Modern Canadian healthcare organizations need contemporary decision makers who use ICT and develop OI, if performance is the target. Our results let us suggest that the isolated administrative agents profile is no more effective in a dynamic and changing world. Contemporary decision makers need to be more active intellectually and to take risks in their decisions. Relying exclusively on research results and on their social network is no more helpful for a real shift. Moreover, the traditional factors, i.e. organization size, time, experience…are no more effective, especially when we consider combined roles. We propose some practical and theoretical recommendations to support these changes.

Étude de la loi conjointe débit-niveau par les copules : Cas de la rivière Châteauguay

Plusieurs catastrophes naturelles sont le resultat de l’occurrence simultanee de deux ou plusieurs evenements extremes. L’evaluation du risque d’apparition de ces catastrophes repose sur une bonne estimation de la probabilite conjointe de ces evenements. Le present travail etudie l’effet combine des debits extremes a l’embouchure de la riviere Châteauguay avec le niveau au Lac Saint-Louis. La modelisation de la loi conjointe de ces deux variables est basee sur la notion de copule qui permet de separer le choix des lois marginales de la structure de dependance. Les resultats montrent que le fait d’ignorer l’effet combine du debit de la riviere ou du niveau du lac, conduit a une sous-estimation des evenements extremes.

Nonstationary frequency analysis of extreme daily precipitation amounts in Southeastern Canada using a peaks-over-threshold approach

In this paper, a statistical inference of Southeastern Canada extreme daily precipitation amounts is proposed using a classical nonstationary peaks-over-threshold model. Indeed, the generalized Pareto distribution (GPD) is fitted to excess time series derived from annual averages of independent precipitation amount events above a fixed threshold, the 99th percentile. Only the scale parameter of the fitted distribution is allowed to vary as a function of a covariate. This variability is modeled using B-spline function. Nonlinear correlation and cross-wavelet analysis allowed identifying two dominant climate indices as covariates in the study area, Arctic Oscillation (AO) and Pacific North American (PNA). The nonstationary frequency analysis showed that there is an east-west behavior of the AO index effects on extreme daily precipitation amounts in the study area. Indeed, the higher quantiles of these events are conditional to the AO positive phase in Atlantic Canada, while those in the more southeastern part of Canada, especially in Southern Quebec and Ontario, are negatively related to AO. The negative phase of PNA also gives the best significant correlation in these regions. Moreover, a regression analysis between AO (PNA) index and conditional quantiles provided slope values for the positive phase of the index on the one hand and the negative phase and on the other hand. This statistic allows computing a slope ratio which permits to sustain the nonlinear relation assumption between climate indices and precipitation and the development of the nonstationary GPD model for Southeastern Canada extremes precipitation modeling.

Frequency Analysis Incorporating a Decision Support System for Hydroclimatic Variables

Statistical criteria used to evaluate the best distribution fit give large weights to the center of distributions. This is, however, not consistent with the objective of frequency analysis which is to estimate the quantiles with large return periods. In this study, the usefulness of a recently proposed decision support system (DSS), which defines the class of distributions prior to a model selection practice with respect to tail behavior of sample data, was investigated using three large hydroclimatic databases [Reference Hydrometric Basin Network (RHBN), precipitation, and UNESCO]. According to the DSS, although a considerable majority of RHBN flood sample data belonged to Class C (regularly varying distributions), a slight and great majority of UNESCO discharge as well as annual precipitation sample data, respectively, belonged to Class D (subexponential distributions). This difference in classification is attributed to the nature of studied variables: RHBN sample data represent extreme events with heav...

Atmospheric Predictors for Annual Maximum Precipitation in North Africa

AbstractThe high precipitation variability over North Africa presents a major challenge for the population and the infrastructure in the region. The last decades have seen many flood events caused by extreme precipitation in this area. There is a strong need to identify the most relevant atmospheric predictors to model these extreme events. In the present work, the effect of 14 different predictors calculated from NCEP–NCAR reanalysis, with daily to seasonal time steps, on the maximum annual precipitation (MAP) is evaluated at six coastal stations located in North Africa (Larache, Tangier, Melilla, Algiers, Tunis, and Gabes). The generalized extreme value (GEV) B-spline model was used to detect this influence. This model considers all continuous dependence forms (linear, quadratic, etc.) between the covariates and the variable of interest, thus providing a very flexible framework to evaluate the covariate effects on the GEV model parameters. Results show that no single set of covariates is valid for all s...

The 2011 flood event in the Richelieu River basin: Causes, assessment and damages

The 2011 Richelieu River (Québec, Canada) spring flood was unprecedented in terms of destruction of property and negative impacts on agricultural as well as fish habitat within its watershed, costing an estimated CAD