Mylène Bédard, Ph.D.

                                                                           Bureau:  4223, pavillon André-Aisenstadt 

                                                                          Adresse:  Département de mathématiques et de statistique
                                                                                          Université de Montréal
                                                                                         CP 6128, succ. Centre-ville
                                                                                         Montréal, Québec, Canada
                                                                                         H3C 3J7

                                                                          Téléphone:  (514) 343-6111 poste 2727
                                                                          Télécopieur: (514) 343-5700

                                                                          Courriel:  mylene.bedard@umontreal.ca

            Professeure adjointe

English version

Curriculum vitae (en anglais)

Enseignement

• STT 6115 - Théorie de la décision bayésienne

• STT 1995 - Analyses statistiques

Recherche

    Articles publiés/acceptés

• Bédard, M. (2007). Weak Convergence of Metropolis Algorithms for Non-iid Target Distributions. Ann. Appl. Probab. 17, 1222-44.    pdf / ps

• Bédard, M., Fraser, D.A.S., Wong, A. (2007). Higher Accuracy for Bayesian and Frequentist Inference: Large Sample Theory for Small Sample Likelihood. Statist. Sci. 22, 301-21.    pdf / ps

• Bédard, M. (2008). Efficient Sampling using Metropolis Algorithms: Applications of Optimal Scaling Results. J. Comput. Graph. Statist. 17, 312-32.    pdf / ps

• Bédard, M. (2006). Optimal Acceptance Rates for Metropolis Algorithms: Moving Beyond 0.234. To appear in Stochastic Process. Appl.     pdf / ps

• Bédard, M. and Rosenthal, J.S. (2007). Optimal Scaling of Metropolis Algorithms: Is 0.234 as Robust as is Believed? Invited paper, to appear in Canad. J. Statist.     pdf / ps 

• Bédard, M. and Fraser, D.A.S. (2008). On a Directionally Adjusted Metropolis-Hastings Algorithm. To appear in a special volume of IJSS, in honour of E. Saleh.     pdf / ps 

• Bédard, M. (2006). On the Robustness of Optimal Scaling for Random Walk Metropolis Algorithms. Ph.D. Thesis. Department of Statistics, University of Toronto.    pdf / ps 

    Articles en préparation

• Bédard, M. On the Optimal Scaling Problem for Hierarchical Models.

• Bédard, M., Fort, G., and Moulines, E. Optimal Scaling for the Multiple Try Metropolis Algorithm.

• Bédard, M. and Kendall, W.S. Weak Convergence of RWM Algorithms using Dirichlet Forms.

Supervision

• Matei Mireuta (M.Sc. temps partiel, depuis février 2008)

• Audrey Béliveau (projet CRSNG, avril 2008 - octobre 2008)     rapport_final.pdf

Dernière modification: 11-11-2008