A5023514231- Statistical Methods and Inference
- Vitamin D Research Studies
- Cancer Risks and Factors
- Wildlife Ecology and Conservation
- Statistical Distribution Estimation and Applications
- Statistical Methods and Bayesian Inference
- Ecology and Vegetation Dynamics Studies
- HIV, Drug Use, Sexual Risk
- Reliability and Maintenance Optimization
- Advanced Statistical Methods and Models
- HIV/AIDS Impact and Responses
- HIV/AIDS Research and Interventions
- Wildlife-Road Interactions and Conservation
- Sex work and related issues
- Soil Geostatistics and Mapping
- Crime Patterns and Interventions
- Genetic and phenotypic traits in livestock
- Financial Risk and Volatility Modeling
- Fatty Acid Research and Health
- Ecology and biodiversity studies
- Probabilistic and Robust Engineering Design
- Nutrition, Genetics, and Disease
- Health Systems, Economic Evaluations, Quality of Life
- Animal Behavior and Welfare Studies
- Liver Disease Diagnosis and Treatment
Université Laval
2015-2024
Cape Town HVTN Immunology Laboratory / Hutchinson Centre Research Institute of South Africa
2022
Fred Hutch Cancer Center
2022
Simon Fraser University
2022
Cancer Research Center
2022
Okanagan University College
2022
University of British Columbia
2022
Centre hospitalier universitaire de Québec
2011-2015
Hôtel-Dieu de Québec
2014
Hôpital du Saint-Sacrement
2007-2014
A trophic cascade recently has been reported among wolves, elk, and aspen on the northern winter range of Yellowstone National Park, Wyoming, USA, but mechanisms indirect interactions within this food chain have yet to be established. We investigated whether observed might a behavioral basis by exploring environmental factors influencing movements 13 female elk equipped with GPS radio collars. developed simple statistical approach that can unveil concurrent influence several features animal...
For gregarious animals the cost-benefit trade-offs that drive habitat selection may vary dynamically with group size, which plays an important role in foraging and predator avoidance strategies. We examined how by bison (Bison bison) varied as a function of size interpreted these patterns testing whether was more strongly driven competing demands forage intake vs. behavior. developed analytical framework integrated into resource functions (RSFs). These group-size-dependent RSFs were based on...
1. Resource selection functions (RSFs) are becoming a dominant tool in habitat studies. RSF coefficients can be estimated with unconditional (standard) and conditional logistic regressions. While the advantage of mixed-effects models is recognized for standard regression, mixed regression remains largely overlooked ecological 2. We demonstrate significance First, we use spatially explicit to illustrate how RSFs useful presence inter-individual heterogeneity when assumption independence from...
Animal movement has a fundamental impact on population and community structure dynamics. Biased correlated random walks (BCRW) step selection functions (SSF) are commonly used to study movements. Because no studies have contrasted the parameters statistical properties of their estimators for models constructed under these two Lagrangian approaches, it remains unclear whether or not they allow similar inference. First, we Weak Law Large Numbers demonstrate that log-likelihood function...
Abstract This paper considers inference methods for case‐control logistic regression in longitudinal setups. The motivation is provided by an analysis of plains bison spatial location as a function habitat heterogeneity. sampling done according to matched design which, at certain time points, exactly one case, the actual animal, number controls, alternative locations that could have been reached. We develop conditional model this setup, which can be formulated within generalized estimating...
Summary 1. The selection for particular habitat patches can vary as a function of local and regional levels anthropogenic disturbance. Although such functional responses better reveal loss species precarious status faced with dwindling resources, they remain rarely used in conservation planning. We show that occur at multiple levels, even nested hierarchies, explain the plasticity observed threatened forest‐dwelling caribou Rangifer tarandus , within among home‐ranges. 2. Twenty‐seven were...
Abstract Background High prostate eicosapentaenoic fatty acid (EPA) levels were associated with a significant reduction of upgrading to grade group (GG) ≥ 2 cancer in men under active surveillance. We aimed evaluate the effect MAG-EPA long-chain omega-3 dietary supplement on proliferation. Methods A phase II double-blind randomized placebo-controlled trial was conducted 130 diagnosed GG and undergoing radical prostatectomy between 2015–2017 (Clinicaltrials.gov: NCT02333435). Participants...
In this article, we discuss the challenge of determining number classes in a family finite mixture models with intent improving specification latent class for criminal trajectories. We argue that traditional method using either Proc Traj or Mplus package to compute and maximize Bayesian Information Criterion (BIC) is problematic: do not always MLE (and hence BIC) accurately, furthermore, BIC on its own does indicate reasonable-seeming groups even when computed correctly. As an alternative,...
Conditional logistic regression (CLR) is widely used to analyze habitat selection and movement of animals when resource availability changes over space time. Observations for these analyses are typically autocorrelated, which biases model-based variance estimation CLR parameters. This bias can be corrected using generalized estimating equations (GEE), an approach that requires partitioning the data into independent clusters. Here we establish link between clustering rules in GEE their...
Abstract Purpose: Recognized prognostic factors do not adequately predict outcomes of head and neck cancer (HNC) patients after their initial treatment. We identified from the literature nine potential serum markers assessed whether they improve outcome prediction. Experimental Design: A pretreatment sample was obtained 527 540 HNC who participated in a randomized controlled trial. During follow-up, 115 had recurrence, 110 second primary (SPC), 216 died. measured markers: prolactin, soluble...
As one way of assessing the impact Avahan, India AIDS Initiative Bill & Melinda Gates Foundation, we examined association between HIV prevention program indicators and changes in prevalence among female sex workers (FSWs) 2005 2009.We conducted a secondary data analysis from 2 large cross-sectional surveys (2005-2006 2008-2009) across 24 districts south (n = 11,000 per round). A random-effect multilevel logistic regression was performed using as outcome, with individual independent variables...
Summary The paper investigates angular regressions that express the angles of an animal’s motion in terms time varying directions and distances to environmental features could influence its displacement. mean direction proposed is a compromise between several possible targets. Conditions for identifiability regression parameters are provided. Maximum likelihood estimators derived under two von Mises error structures. Robust sandwich parameter variance–covariance matrix obtained. statistical...
In this paper we propose inference methods based on the EM algorithm for estimating parameters of a weakly parameterised competing risks model with masked causes failure and second‐stage data. With carefully chosen definition complete data, maximum likelihood estimation cause‐specific hazard functions masking probabilities is performed via an algorithm. Both E‐ M‐steps can be solved in closed form under full some restricted models interest. We illustrate flexibility method by showing how...
This study contributed to the criminal trajectory literature using a Canadian-based sample of offenders and examined childhood adolescent predictors group membership. The comprised 378 males who had been sentenced as youth, between 1986 1996, one two open custody facilities in Toronto, Canada. Official records were obtained from late early adolescence into adulthood for an average follow-up 12.1 years. Childhood reflecting individual, family, peer, school domains extracted client files....
The analysis of data generated by animal habitat selection studies, family studies genetic diseases, or longitudinal follow-up households often involves fitting a mixed conditional logistic regression model to composed clusters matched case-control strata. estimation parameters maximum likelihood is especially difficult when the number cases per stratum greater than one. In this case, denominator each cluster contribution complex integral in high dimension, which leads convergence problems...
The authors propose a class of procedures for local likelihood estimation from data that are either interval-censored or have been aggregated into bins. One such procedure relies on an algorithm generalizes existing self-consistency algorithms by introducing kernel smoothing at each step the iteration. entire yields estimates obtained as solutions fixed point equations. By discretizing and applying numerical integration, use theory to study convergence class. Rapid is effected implementation...
Purpose It is estimated that only 5% of patients with cancer participate in a clinical trial. Barriers to participation may relate available protocols, physicians, and patients, but few data exist on barriers related care environments protocol characteristics. Methods The primary objective was identify characteristics trial protocols associated low recruitment into breast trials. Secondary objectives were determine yearly fraction onto trials from 1997 2002 Ontario, Canada, compare among...
A multi-state version of an animal movement analysis method based on conditional logistic regression, called Step Selection Function (SSF), is proposed. In ecology SSF developed from a comparison between the observed location and randomly sampled locations at each time step. Interpretation parameters in model impact different sampling schemes for random are discussed. We prove equivalence new walk plane. This allows one to use both pure local discrete choice behaviors identifying model's...
Factors affecting wildland-fire size distribution include weather, fuels, and fire suppression activities. We present a novel application of survival analysis to quantify the effects these factors on sample sizes lightning-caused fires from Alberta, Canada. Two events were observed for each fire: at initial assessment (by first fighters arrive scene) "being held" (a state when no further increase in is expected). developed statistical classifier try predict cases where there will be growth...
Prostate cancer is the most commonly diagnosed in north-American men. Few dietary or lifestyle interventions have been tested to prevent prostate progression. Omega-3 fatty acid supplementation represents a promising intervention for patients. The aim of study evaluate effects long-chain omega-3 polyunsaturated acids (LCn3), more precisely eicosapentaenoic monoacylglyceride (MAG-EPA) supplementation, on proliferation, inflammation mediators and quality life among men who will undergo radical...
Landings from fisheries are often underreported, that is, the true landings greater than those reported. Despite this bias, reported widely used in fish stock assessments, and might lead to overoptimistic exploitation strategies. We construct a statistical assessment model accounts for underreported using theory of censoring with sequential population analysis (SPA). The new is developed implemented specifically cod ( Gadus morhua ) southern Gulf St. Lawrence (Canada). This known have...