F Bellavance

HEC Montréal - École des Hautes Études commerciales, Montréal, Quebec, Canada

Are you F Bellavance?

Claim your profile

Publications (86)223.46 Total impact

  • Marie-Ève Rancourt, François Bellavance, Jarrod Goentzel
    [Show abstract] [Hide abstract]
    ABSTRACT: Empirical research characterizing transportation markets in developing countries is scarce. By analyzing contracts between the World Food Programme and private carriers, we identify the determinants of transportation tariffs in Ethiopia and quantify their relative importance. The econometric models devised from our unique dataset provide insights for shippers to improve procurement processes, for carriers to develop competitive business models and for government authorities to define effective investments and policies. Results indicate that the number of carriers on a given lane significantly reduces transportation tariffs and that policies stimulating competition may be as important as road infrastructure investments in Ethiopia’s development strategy.
    Socio-Economic Planning Sciences 09/2014;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This project aims to assess the influence of using smart phones on pedestrians’ visual attention and safety. To do so, the developed methodology employs electroencephalography (EEG) and behavioral measures. Participants will be using the text messaging functionality of a smart phone while walking on a treadmill. The experiment will take place in an immersive 3D environment at the Optometry School of the University of Montréal. The experiment will take place during the month of May 2014. Twenty participants will be recruited (between 20 and 34 years old). They will have owned a smart phone for at least 6 months and use it occasionally while walking. The poster will present the complete methodology and acquisition setup along with preliminary results.
    Gmunden Retreat on NeuroIS 2014, Gmunden, Austria; 06/2014
  • Ahlem Hajjem, François Bellavance, Denis Larocque
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an extension of the random forest (RF) method to the case of clustered data. The proposed ‘mixed-effects random forest’ (MERF) is implemented using a standard RF algorithm within the framework of the expectation–maximization algorithm. Simulation results show that the proposed MERF method provides substantial improvements over standard RF when the random effects are non-negligible. The use of the method is illustrated to predict the first-week box office revenues of movies.
    Journal of Statistical Computation and Simulation 01/2014; 84(6). · 0.63 Impact Factor
  • François Bellavance, Suzanne Landry, Eduardo Schiehll
    [Show abstract] [Hide abstract]
    ABSTRACT: This study investigates the effect of subjectivity in performance evaluation on managerial perceptions of procedural justice. Using survey data from a sample of 317 managers, we examine two forms of subjectivity: use and weight of subjective performance measures and ex post flexibility in the weighting of multiple performance measures. We also examine the interaction effects of two contextual factors, superior–manager relationship quality and voice opportunity, on the association between subjectivity and perceived procedural justice. The results suggest that only the superior's use of ex post flexibility in weighting multiple performance measures adversely affects managers' perceptions of procedural justice. Moreover, superior–manager relationship quality reduces the negative effects of ex post flexibility in weighting multiple performance measures on procedural justice, whereas voice opportunity amplifies this negative effect. These findings have practical and theoretical implications, as they shed new light on the trade-off between the informative benefits and perceived unfairness of incorporating subjectivity into performance evaluation.
    The British Accounting Review 09/2013; 45(3):149–166.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cette étude s’intéresse aux risques liés à l’utilisation de téléphones intelligents par les travailleurs lors de déplacements piétonniers. Il est suggéré que le flow influence l’inattention visuelle (i.e., cécité attentionnelle) et qu’il est déterminé en partie par la position corporelle de l’utilisateur et du niveau d’interactivité de la tâche effectuée.
    Proceedings of the 2013 ASAC Conference; 06/2013
  • Source
    Ahlem Hajjem, François Bellavance, Denis Larocque
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an extension of the standard regression tree method to clustered data. Previous works extending tree methods to accommodate correlated data are mainly based on the multivariate repeated-measures approach. We propose a "mixed effects regression tree" method where the correlated observations are viewed as nested within clusters rather than as vectors of multivariate repeated responses. The proposed method can handle unbalanced clusters, allows observations within clusters to be split, and can incorporate random effects and observation-level covariates. We implemented the proposed method using a standard tree algorithm within the framework of the expectation-maximization (EM) algorithm. The simulation results show that the proposed regression tree method provides substantial improvements over standard trees when the random effects are non negligible. A real data example is used to illustrate the method.
    Statistics [?] Probability Letters 04/2011; 81(4):451-459. · 0.53 Impact Factor
  • Source
    Ahlem Hajjem, François Bellavance, Denis Larocque
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents the generalized mixed effects regression tree (GMERT) method, an extension of the mixed effects regression tree (MERT) methodology designed for continuous outcomes to other types of outcomes (e.g., binary outcomes, counts data, ordered categorical outcomes, and multicategory nominal scale outcomes). This extension uses the penalized quasi-likelihood (PQL) method for the estimation and the expectation-maximization (EM) algorithm for the computation. The simulation results in the binary response case show that, when random effects are present, the proposed generalized mixed effects regression tree method provides substantial improvements over standard classification trees. Index Terms—Tree based methods, clustered data, mixed effects, penalized quasi-likelihood (PQL) algorithm, expectation-maximization (EM) algorithm.
    01/2010;
  • José Bélanger, Alain Gosselin, François Bellavance
    [Show abstract] [Hide abstract]
    ABSTRACT: Over the past few years, an increasing number of authors in the human resource management field have developed an interest in the roles played by HR departments and HR executives in the formulation of the business strategy. However, it is relevant to examine in which context the use of these roles becomes legitimate. According to a number of authors, this is particularly the case when businesses are facing demanding human resource challenges. Therefore, taking into account the current context characterized by an economy under pressure, HR executives should be in a good position to benefit from such a context to become influential partners within their respective top management committee. However, very little is known about the extent to which members of the top management committee perceive HR executives as having a high capability to influence them. Also, so far, no one has addressed the gap that may exist between the perception of the top management committee members and the perception HR executives hold for themselves with regards to their capability to influence the latter.In this study, we chose to investigate HR executives who come mainly from the greater Montreal area. In total, we met 41 HR executives for whom we investigated their influence capability. Following the interview, we invited each HR executive to hand out a short questionnaire to each member of the top management committee that they had tried to influence over the last three years. Results show that, overall, HR executives tend to overestimate their influence capability when compared to the perception of their executive colleagues and chief officer. Finally, this study also confirmed that a good reputation, a solid credibility and high referent power can facilitate the capability of HR executives to influence others.
    12/2009;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Panic disorder has been associated with both an increased risk of coronary events as well as an increased risk of stroke. Hemoconcentration, with both a decrease in plasma volume and an increase in plasma viscosity, is a possible contributor to the risk of acute ischemic events. Our objectives were to demonstrate the process of hemoconcentration in response to induced panic symptoms and to assess the effect of pretreatment with ethinyl estradiol on panic-induced hemoconcentration. Fifteen male patients with panic disorder and 10 male healthy volunteers were included in a double-blind cross-over placebo-controlled design consisting of two injections of pentagastrin following randomized pretreatment with placebo and ethinyl estradiol. Plasma levels of hematocrit and hemoglobin were assessed at baseline and post-injections, and used to calculate an indirect estimation of the change in plasma volume. Pentagastrin-induced panic symptoms were associated with a mean decrease in plasma volume of 4.8% in the placebo pretreatment condition. Pretreatment with ethinyl estradiol attenuated this effect. The acute hemoconcentration observed in relation to pentagastrin-induced panic symptoms may be relevant to the increased risk of stroke and acute coronary events found in patients with panic disorder.
    Journal of Psychopharmacology 10/2009; 25(1):71-7. · 3.37 Impact Factor
  • Lalla Ilhame Sabbane, François Bellavance, Jean-Charles Chebat
    [Show abstract] [Hide abstract]
    ABSTRACT: This study focuses on the interactive effects of antismoking warnings and cigarette-brand familiarity on teenagers' smoking intent, attitudes toward the website, and sponsoring brand when exposed to entertainment websites sponsored by cigarette brands. Findings from a 3 (Warning Type) × 2 (Level of Cigarette-Brand Familiarity) factorial design experiment with nonsmoking teenagers demonstrated that text and picture warnings significantly reduced attitudes toward cigarette brands, compared to text-only or no warning. Warnings had assimilation effects on attitudes (toward brand and website) and on smoking intent in the case of familiar brands; and marginally significant contrast effects in the case of unfamiliar brands, which better reflects the repetition priming paradigm than the recency priming paradigm, and calls for attention to cigarette brands' familiarity.
    Journal of Applied Social Psychology 02/2009; 39(3):656 - 682. · 0.83 Impact Factor
  • Source
    Eduardo Schiehll, François Bellavance
    [Show abstract] [Hide abstract]
    ABSTRACT: This study documents that boards choose performance measures that best reflect the CEO's contribution to firm value, taking into account the firm's monitoring environment. This study therefore has policy implications regarding the need for enhanced disclosure of CEO compensation to improve investor understanding of the alignment between executive pay and firm performance. Agency theory states that any costless performance measure providing incremental information about the agent's effort will improve the efficiency of the contract with the agent. In contrast with most of the literature in this area, which investigates pay-performance sensitivity and governance structure, we examine an important component of pay-for-performance plans used to align and compensate executive actions that might not be reflected in traditional financial performance measures. The results provide evidence that the use of non-financial performance measures in the CEO bonus plan varies predictably. Growth opportunities are positively associated with the firm's choice to integrate non-financial information into the CEO bonus plan. The results are also sensitive to our proxy for board independence and CEO ownership in firms with high growth opportunities. This study examines the associations between the board of director's choice to integrate non-financial performance measures into the CEO bonus plan and two other governance mechanisms board independence and CEO ownership in a sample of publicly traded Canadian firms.
    Corporate Governance An International Review 01/2009; · 1.90 Impact Factor
  • Source
    Rim Makni, Claude Francoeur, François Bellavance
    [Show abstract] [Hide abstract]
    ABSTRACT: The possibility of measuring and comparing sustainability performance is generally taken for granted in management studies and practices based on the evaluation, selection and ranking of the supposedly best companies in the field. The purpose of this article is to question this basic assumption by analyzing the comparability of sustainability performance through a systematic review of 12 mining company reports using Global Reporting Initiative (GRI) guidelines. The analysis of information based on 92 GRI indicators raises serious questions concerning the hypothesis of measurability and comparability of sustainability performance, drawing attention to the main reasons that make it very difficult if not impossible to establish a credible and justifiable classification among organizations. La possibilité de mesurer et de comparer les performances de développement durable est généralement prise pour acquise tant dans les recherches en gestion que dans les pratiques de classement ou de sélection des meilleures entreprises dans ce domaine. L’objectif de cet article est d’examiner cette hypothèse de mesurabilité et de comparabilité des performances de développement durable à partir de l’étude systématique de 12 rapports d’entreprises minières utilisant le même guideline du Global Reporting Initiative (GRI). L’analyse des informations relatives aux 92 indicateurs du GRI utilisés remet en cause l’hypothèse de comparabilité des performances de développement durable en mettant en lumière les principales raisons qui rendent pratiquement impossible l’établissement d’un classement crédible et justifiable entre les entreprises.
    Journal of Business Ethics 01/2009; 89(3):409-422. · 0.96 Impact Factor
  • Abdessamad Dine, Denis Larocque, François Bellavance
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a tree-based method for multivariate outcomes consisting in a mixture of categorical and continuous responses. The split function for tree-growing is derived from a likelihood-based approach for a general location model (GLOM). One situation where the new approach should be appealing is when mixed types of multiple outcomes are used as surrogates for an unobserved latent outcome. Two illustrations of the application of the new method are given with health care data.
    Computational Statistics & Data Analysis 01/2009; · 1.30 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Side impacts are a serious automotive injury problem; they represent about 30% of all fatalities for passenger vehicle occupants. This literature review focuses on occupant injuries resulting from real lateral collisions. It emphasizes the interaction between injury patterns and crash factors, taking into account type of injuries and their severity. It highlights what is known on the subject and suggests further studies. We reviewed papers identified by searches in two electronic databases for the 1996-2009 publication period, and in specific journals and conference proceedings. Studies on the Primary Direction of Force (PDOF) have revealed that fatal crashes occur most frequently when the PDOF is at 3 or 9 o'clock. The risk of serious injury is two to three times higher for the near-side occupant than for the far-side occupant. Head injuries predominate in oblique impacts and thoracic injuries in perpendicular ones. A few results are also reported on side airbag protection. This literature review presents an overall picture of the injuries caused by lateral collisions, though each of the papers or articles examined focuses mostly on some particular aspect of the problem. The incidence of specific injuries depends on the data source used. Very few population-based analyses of lateral collision injuries were found. New studies are needed to evaluate new protective devices (e.g., lateral airbags, inflatable curtains). Without interfering with their care duties, Emergency Medical Technicians could be systematically trained to observe the collision's specific characteristics and to report all their relevant observations to the emergency physicians to increase the likelihood of prompt diagnosis and proper care.
    Journal of safety research 01/2009; 40(6):427-35. · 1.34 Impact Factor
  • Source
    François Bellavance, Georges Dionne, Martin Lebeau
    [Show abstract] [Hide abstract]
    ABSTRACT: The value of a statistical life (VSL) is a very controversial topic, but one which is essential to the optimization of governmental decisions. We see a great variability in the values obtained from different studies. The source of this variability needs to be understood, in order to offer public decision-makers better guidance in choosing a value and to set clearer guidelines for future research on the topic. This article presents a meta-analysis based on 39 observations obtained from 37 studies (from nine different countries) which all use a hedonic wage method to calculate the VSL. Our meta-analysis is innovative in that it is the first to use the mixed effects regression model [Raudenbush, S.W., 1994. Random effects models. In: Cooper, H., Hedges, L.V. (Eds.), The Handbook of Research Synthesis. Russel Sage Foundation, New York] to analyze studies on the value of a statistical life. We conclude that the variability found in the values studied stems in large part from differences in methodologies.
    Journal of Health Economics 12/2008; 28(2):444-64. · 1.60 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This research sets out to estimate the effects of vehicle incompatibility on the risk of death or major injury to drivers involved in two-vehicle collisions. Based on data for 2,999,395 drivers, logistic regression was used to model the risk of driver death or major injury (defined has being hospitalized). Our analyses show that pickup trucks, minivans and sport utility vehicles (SUVs) are more aggressive than cars for the driver of the other vehicle and more protective for their own drivers. The effect of the pickups is more pronounced in terms of aggressivity. The point estimates are comparable to those in the Toy and Hammitt study [Toy, E.L., Hammitt, J.K., 2003. Safety impacts of SUVs, minivans, and pickup trucks in two-vehicle crashes. Risk Analysis 23, 641-650], but, in contrast to that study, we are now able to establish that a greater number of these effects are statistically significant with a larger sample size. Like vehicle mass and type, other characteristics of drivers and the circumstances of the collision influence the driver's condition after impact. Male drivers, older drivers, drivers who are not wearing safety belts, collisions occurring in a higher speed zone and head-on collisions significantly increase the risk of death. Except for the driver's sex, all of these categories are also associated with an increased risk of death or of being hospitalized after being involved in a two-vehicle collision. For this risk, a significant increase is associated with female drivers.
    Accident; analysis and prevention 12/2008; 40(6):1987-95. · 1.65 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Women who suffer from premenstrual dysphoric disorder (PMDD) classically display depressive and anxiety symptoms in the premenstrum. Preclinical and clinical studies have suggested a role of glutamate in anxiety and depression. This investigation aims at demonstrating fluctuations of glutamate across the menstrual cycle in the medial prefrontal cortex of women who suffer from PMDD and healthy control subjects (HCs). Twelve PMDD women and 13 HCs were randomized to two single-voxel 3 Tesla proton magnetic resonance spectroscopy examinations of the medial prefrontal cortex during the follicular phase and the luteal phase. A phase effect was observed; the levels of glutamate/creatine plus phosphocreatine (Cr) were significantly lower during the luteal phase compared with the follicular phase. However, no statistically significant diagnosis or phase x diagnosis effects were found. The optimized stimulated echo acquisition mode (STEAM) pulse timings selected in this study (echo time [TE], mixing time [TM] = 240, 27 msec) allow us to interpret our results as the first report of alterations of brain glutamate levels across the menstrual cycle. Hormonal fluctuations associated with the menstrual cycle likely contribute to these glutamate level variations. Although PMDD women undergo a similar decrease in glutamate during the luteal phase as the HCs, PMDD women may display an increased behavioral sensitivity to those phase-related alterations. These menstrual cycle-related variations of glutamate levels may also contribute to the influence of the phases of the menstrual cycle in other neuropsychiatric disorders.
    Biological psychiatry 07/2008; 63(12):1178-84. · 8.93 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Objective: lb determine the test-retest reliability and concurrent criterion validity of a self-report ED screening questionnaire for adverse outcomes in elders.Methods: A cohort of 1,885 patients aged ≤ 65 years were recruited from the EDs of 4 Montreal hospitals. Patients were excluded if they could not be interviewed because of their clinical status or cognitive impairment and no informant was available. The screening questionnaire, administered in the ED, contained 27 items on social, physical, and mental risk factors, medical history, and use of hospital services, medications, and alcohol. A random sample of 404 patients were invited to participate in a clinical assessment 1–3 weeks after the ED visit, that included re-administration of the screening questionnaire, and standardized instruments to assess disability, social resources, depression, alcohol use and abuse, and current medications.Results: Study data were collected from 221 patients (54.7%), of whom 193 were included in the test-retest reliability analyses and 213 in the analyses of concurrent validity. The concordance correlation coefficient for test-retest reliability of the risk factor score was 0.78 (95% confidence interval: 0.71, 0.83; n= 193). Several screening questions showed moderately good agreement with the appropriate criterion standard, particularly those on visual and hearing impairment, depression, and use of medications. The best subset of 9 screening questions explained approximately half of the variance in the total disability score.Conclusions: The screening questionnaire score has good test-retest reliability, but individual screening questions have, at best, modest concurrent validity. The final set of screening questions should be selected based on their predictive validity.
    Academic Emergency Medicine 06/2008; 5(9):883 - 893. · 2.20 Impact Factor
  • Serge Tardif, François Bellavance, Constance Van Eeden
    [Show abstract] [Hide abstract]
    ABSTRACT: The authors propose nonparametric tests for the hypothesis of no direct treatment effects, as well as for the hypothesis of no carryover effects, for balanced crossover designs in which the number of treatments equals the number of periods p, where p ≥ 3. They suppose that the design consists of n replications of balanced crossover designs, each formed by m Latin squares of order p. Their tests are permutation tests which are based on the n vectors of least squares estimators of the parameters of interest obtained from the n replications of the experiment. They obtain both the exact and limiting distribution of the test statistics, and they show that the tests have, asymptotically, the same power as the F-ratio test.
    Canadian Journal of Statistics 11/2005; 33(4):471 - 488. · 0.59 Impact Factor
  • François Bellavance, Serge Tardif
    [Show abstract] [Hide abstract]
    ABSTRACT: Continuous data from crossover trials are often analysed using ordinary least squares with the assumption of independent errors. Because each experimental unit receives a sequence of treatment and repeated measurements are collected, it is more realistic to assume that the errors within an experimental unit are correlated. In this paper, we extend to crossover designs the conditions on the covariance structure of the errors, found by Huynh and Feldt (1970) for randomized block and split-plot designs, that will not invalidate the F-ratio tests for treatment and carryover effects. We also show that results on optimal crossover designs remain valid under this more general structure of the covariance matrix.
    05/2005: pages 59-73;

Publication Stats

2k Citations
223.46 Total Impact Points

Institutions

  • 2001–2008
    • HEC Montréal - École des Hautes Études commerciales
      Montréal, Quebec, Canada
    • St. Mary's Hospital Center (Canada)
      Montréal, Quebec, Canada
    • Florida Atlantic University
      • Department of Mathematical Sciences
      Boca Raton, FL, United States
  • 2002–2004
    • University of Alberta
      • Department of Psychiatry
      Edmonton, Alberta, Canada
  • 1996–2002
    • Saint Mary's Hospital Center
      Montréal, Quebec, Canada
  • 2000
    • HEC Paris
      Lutetia Parisorum, Île-de-France, France
  • 1998–1999
    • University of Toronto
      • Department of Psychiatry
      Toronto, Ontario, Canada
  • 1997
    • Université de Montréal
      Montréal, Quebec, Canada