Substance use data such as alcohol drinking often contain a high proportion of zeros. In studies examining the alcohol consumption in college students, for instance, many students may not drink in the studied period, resulting in a number of zeros. Zero-inflated continuous data, also called semi continuous data, typically consist of a mixture of a degenerate distribution at the origin (zero) and a right-skewed, continuous distribution for the positive values. Ignoring the extreme non-normality in semi-continuous data may lead to substantially biased estimates and inference. Longitudinal or repeated measures of semi-continuous data present special challenges in statistical inference because of the correlation tangled in the repeated measures on the same subject. Linear mixed-eects models (LMM) with normality assumption that is routinely used to analyze correlated continuous outcomes are inapplicable for analyzing semi-continuous outcome. Data transformation such as log transformation is typically used to correct the non-normality in data. However, log-transformed data, after the addition of a small constant to handle zeros, may not successfully approximate the normal distribution due to the spike caused by the zeros in the original observations. In addition, the reasons that data transformation should be avoided include: (i) transforming usually provides reduced information on an underlying data generation mechanism; (ii) data transformation causes diculty in regard to interpretation of the transformed scale; and (iii) it may cause re-transformation bias. Two-part mixed-eects models with one component modeling the probability of being zero and one modeling the intensity of nonzero values have been developed over the last ten years to analyze the longitudinal semi-continuous data. However, log transformation is still needed for the right-skewed nonzero continuous values in the two-part modeling. In this research, we developed Bayesian hierarchical models in which the extreme non-normality in the longitudinal semi-continuous data caused by the spike at zero and right skewness was accommodated using skew-elliptical (SE) distribution and all of the inferences were carried out through Bayesian approach via Markov chain Monte Carlo (MCMC). The substance abuse/dependence data, including alcohol abuse/dependence symptoms (AADS) data and marijuana abuse/dependence symptoms (MADS) data from a longitudinal observational study, were used to illustrate the proposed models and methods. This dissertation explored three topics: First, we presented one-part LMM with skew-normal (SN) distribution under Bayesian framework and applied it to AADS data. The association between AADS and gene serotonin transporter polymorphism (5-HTTLPR) and baseline covariates was analyzed. The results from the proposed model were compared with those from LMMs with normal, Gamma and LN distributional assumptions. Simulation studies were conducted to evaluate the performance of the proposed models. We concluded that the LMM with SN distribution not only provides the best model t based on Deviance Information Criterion (DIC), but also offers more intuitive and convenient interpretation of results, because it models the original scale of response variable. Second, we proposed a flexible two-part mixed-effects model with skew distributions including skew-t (ST) and SN distributions for the right-skewed nonzero values in Part II of model under a Bayesian framework. The proposed model is illustrated with the longitudinal AADS data and the results from models with ST, SN and normal distributions were compared under different random-effects structures. Simulation studies are conducted to evaluate the performance of the proposed models. Third, multivariate (bivariate) correlated semi-continuous data are also commonly encountered in clinical research. For instance, the alcohol use and marijuana use may be observed in the same subject and there might be underlying common factors to cause the dependence of alcohol and marijuana uses. There is very limited literature on multivariate analysis of semi-continuous data. We proposed a Bayesian approach to analyze bivariate semi-continuous outcomes by jointly modeling a logistic mixed-effects model on zero-inflation in either response and a bivariate linear mixed-effects model (BLMM) on the positive values through a correlated random-effects structure. Multivariate skew distributions including ST and SN distributions were used to relax the normality assumption in BLMM. The proposed models were illustrated with an application to the longitudinal AADS and MADS data. A simulation study was conducted to evaluate the performance of the proposed models.

Objectifs : Ce mémoire propose de répertorier par une revue systématique les instruments de mesure clinique des conduites addictives établies et émergentes; de les comparer au moyen d’une grille d’analyse afin de de déterminer si ces conduites sont cohésives au plan conceptuel. Méthode : La stratégie analytique employée s’est déroulée en trois étapes : 1) Via les moteurs de recherche Pubmed, Psychinfo, HAPI et Embase, nous avons cherché, pour l’ensemble des conduites addictives, les questionnaires ayant fait l’objet d’une étude de validation interne au plan psychométrique. 2) Une grille d’analyse a été développée et validée, couvrant 21 paramètres tirés de 4 catégories conceptuelles : les critères diagnostiques de dépendance (DSM-IVTR), le tempérament (Cloninger et Zuckerman), le processus de production du handicap social (Fougeyrollas) et une grille d’analyse cognitivo-comportementale (Beck). 3) tous les instruments ont été analysés et comparés au moyen de cette grille qui a été développée est validée par un accord inter-juge élevé. Résultats : Nous avons répertorié 191 questionnaires répartis sur 21 conduites addictives. On constate que les conduites les plus prévalentes sont également celles pour lesquelles on retrouve le plus grand nombre de questionnaires. Les catégories que les questionnaires évaluent le plus sont celles des critères de la dépendance et l’analyse cognitivo-comportementale, les catégories beaucoup moins bien représentées étant celles du tempérament et du processus de production du handicap social. On note des tendances semblables pour les paramètres entre les questionnaires portant sur la toxicomanie et ceux portant sur les addictions sans drogues. Conclusion : Ce mémoire confirme une cohésion clinique dans la mesure des addictions, tel que déterminé par une grille validée appliquée sur un ensemble exhaustif de questionnaires répertoriés par une revue systématique. / Aims: To conduct a systematic review of instruments for the clinical measurement of established and emerging addictions; and to determine whether these addictive behaviours are similarly conceptualised in clinical research. Methods: The analytic strategy employed comprised three steps: 1) major search engines were used to do an inventory of available psychometrically validated clinical instruments for assessing addictions; 2) an analytical grid was developed and validated, covering 21-parameters related to four conceptual categories: dependence (DSM-IV-TR), temperament (Cloninger and Zuckerman), social handicap (Fougeyrollas), and cognitive behaviour analysis (Beck); 3) all instruments were analysed and compared through the grid. Results: The method yielded 191 questionnaires covering 21 addictive behaviours. The most prevalent behaviours were those best represented in terms of number of questionnaires. The criteria categories most evaluated by the questionnaires were dependence and cognitive behaviour; temperament and social handicap were much less often considered. Patterns were generally similar in terms of parameters, whether questionnaires concerned substance or non-substance addictions. Conclusions: The measurement of addictions appears clinically cohesive, as determined by a validated analysis grid applied to an exhaustive set of questionnaires identified via a systematic literature review.

No description available.