CONFERENCIER(S) : Zhiqiang Tan (Rutgers University)

TITRE : Marginal and Nested Structural Models Using Instrumental Variables

LIEU : UQAM, Pav. Président-Kennedy, 201, av. Président-Kennedy, salle PK-5115

DATE : Le vendredi 2 octobre 2009

HEURE : 15 h 30

RESUME :
The objective of many scientific studies is to evaluate the effect of a treatment on an outcome of interest ceteris paribus. Instrumental variables (IVs) serve as an experimental handle, independent of potential outcomes and potential treatment status and affecting potential outcomes only through potential treatment status. We propose marginal and nested structural models using IVs, in the spirit of marginal and nested structural models under no unmeasured confounding. A marginal structural IV model parameterizes the expectations of two potential outcomes under an active treatment and the null treatment respectively, for those in a covariate-specific subpopulation who would take the active treatment if the instrument were externally set to each specific level. A nested structural IV model parameterizes the difference between the two expectations after transformed by a link function and hence the average treatment effect on the treated at each instrument level. We develop IV outcome regression, IV propensity score weighting, and doubly robust methods for estimation, in parallel to those for structural models under no unmeasured confounding. We apply our methods to study returns to education using data from the National Longitudinal Survey of Young Men.

Le jeudi 1er octobre 2009, à 13 h 30, à la salle 1240 du pavillon Alexandre-Vachon.

Wishart Mixtures Diffusion Tensor Imaging and the Statistics of Harish-Chandra
Peter Kim, Department of mathematics and statistics, University of Guelph.

To say the least, the work of Harish-Chandra has had profound consequences in the development of mathematics. To some degree, the work is also apparent in statistics. However, due to the fact that most of statistics take place in a commutative setting, the profound non-commutative results are somewhat hidden. In this talk, we will assume non-commutativity, and by doing so, we will demonstrate the contribution to statistics in the setting of Wishart mixture models on the space of positive definite symmetric matrices. This has practical relevance to Diffusion Tensor Imaging, which is a modern in vivo brain imaging technique that tracts the whole brain white matter fibers.

Chers membres de l’ASSQ,

J’ai le plaisir de vous annoncer la publication de l’édition estivale de Convergence. Vous retrouverez sa version pdf sur le site de l’ASSQ, ici.

Pour y accéder, vous devez entrer l’identifiant et le mot de passe qui vous a été envoyé par courriel.

Je vous souhaite une agréable lecture et un bel été !

Jean-François Quessy, Ph. D.
Rédacteur en chef de Convergence

Bonjour à tous les membres,

Vous êtes cordialement invités à participer à la 11e édition du tournoi de golf ASSQ. Ce tournoi aura lieu le samedi 5 septembre, au Club de golf Drummondville, lequel représente toute une «track» de golf. Voilà donc une occasion rêvée de vous inscrire pour une première fois à cette activité qui se déroule dans une ambiance de franche camaraderie. La formule habituelle sera maintenue afin de donner la chance aux golfeurs plus novices d’apprécier cette activité. Soyons donc des nôtres le samedi de la fin de semaine de la Fête du travail.

Veuillez manifester votre intérêt le plus rapidement possible à claude.ouimet”arobase”mtq.gouv.qc.ca en mentionnant si le golf et le souper vous intéressent. Seulement 24 places sont disponibles.

Votre paiement doit me parvenir avant la fin août.

Tous les détails de l’évènement sont inclus dans ce fichier.

Merci et au plaisir de vous y rencontrer

Claude Ouimet, stat ASSQ

Le 25e Symposium international de Statistique Canada sur les questions de méthodologie intitulé « Les enquêtes longitudinales: de la conception à l’analyse », se tiendra du 27 au 30 octobre 2009 au Palais des congrès à Gatineau (Qc).

Vous pouvez maintenant vous inscrire à l’événement.

Veuillez visiter le site web du symposium pour de plus amples renseignments.

http://www.statcan.gc.ca/conferences/symposium2009/reg-ins-fra.htm

Il est déjà temps de s’inscrire afin de ne pas manquer l’activité par excellence de votre association: l’Assemblée générale annuelle qui aura lieu le 12 juin 2009 au Manoir du Mont Saint-Castin. Cette année, nous retrouvons la formule habituelle qui inclut trois conférences, un coquetel et un souper gastronomique. La fiche d’inscription se trouve ici.

CONFERENCIER : Constantine Frangakis (Johns Hopkins University)

TITRE : The role of principal stratification in instrumental variables in case-control designs - an application to Mendelian randomization

DATE : 1 mai 2009

HEURE : 15:30

SALLE : Salle 1B36, McGill University, Burnside Hall, 805 Sherbrooke O.

RÉSUME :
We are motivated by studying the effect that the expression of inflammatory genes has on the risk of colorectal cancer. Gene expression, however, is likely confounded with other risk factors for cancer. But because meiosis within families is considered a random process, the genotypes can potentially be used as instruments for the actual inflammation levels. The problem we address here is that designs are typically based on case-control sampling for these settings. We show first that, in contrast to settings with no confounding, modeled with conditional logistic regression, instrumental variables causal effects are generally incorrectly estimated if the design effect is ignored, as they are not invariant under such designs. We show, second, how in general the framework of principal stratification is useful to validly estimate the causal effects under such designs. We demonstrate these results with the effect of inflammation on colorectal cancer.

Le dernier Convergence (Volume XIV, Numéro 1) est maintenant disponible ici. Comme c’est maintenant coutume, le mot de passe habituel est requis pour accéder au dernier numéro.

CONFERENCIER : Jinko Graham (Simon Fraser University)

TITRE : Graphical displays to uncover gene-environment interaction from data on case-parent trios

DATE : 24 avril 2009

HEURE : 15:30

SALLE : Salle PK-5115, UQÀM, Pavillon Président-Kennedy, 201, av. Président-Kennedy
RÉSUME :
In genetic association studies of complex diseases, case-parent-trio designs involve the collection of data from affected offspring and their parents. This design is well-suited to diseases of early onset, such as type 1 diabetes and childhood leukemia. Unlike the case-control design, the case-parent design is robust to bias from ethnic differences between cases and controls and it enables investigation of parent-of-origin effects for genetic risk factors. While the use of the case-parent design for finding genetic associations has been well studied, its use for uncovering gene-environment interactions is less well-understood. We review two existing ad-hoc approaches to explore gene-environment interaction from case-parent trios and illustrate their potential bias. We propose an alternate penalized likelihood approach that does not suffer from such bias and illustrate its use on simulated data. We conclude with some directions for future research. This is joint work with Ji-Hyung Shin and Brad McNeney.

CONFERENCIER : David Dunson (Duke university)

TITRE : Bayesian density regression with epidemiology applications

DATE : 17 avril 2009

HEURE : 15:30

SALLE : Salle 1B24, McGill University, Burnside Hall, 805 Sherbrooke O.

RÉSUME :
In assessing relationships between a response and multiple predictors, it is appealing to allow the conditional response distribution to vary flexibly, allowing non-linear and varying relationships with the different quantiles and predictors. Such flexibility is of critical importance in applications in which the tails of the distribution are of primary interest. For example, in epidemiology studies of continuous health responses, the tails of the distribution typically correspond to those individuals having the most adverse health conditions. We would like a method that can allow an environmental exposure, genetic factor or demographic covariate to flexibly impact risk of an adverse response, with adverse corresponding to values in the tails of the distribution. Values further in the tails vary in their severity, so it is important to avoid categorization or grouping. Motivated by studies of pregnancy outcomes and premature delivery, this talk proposes Bayesian nonparametric methods for density regression. I will also describe applications to molecular epidemiology studies. The talk is designed to be accessible to a general audience of biostatisticians and epidemiologists, so technical details will kept to a minimum.