Thesis (Ph. D.)--Indiana University, 1990. / Vita. Includes bibliographical references (leaves 189-204).

Dans cette thèse, nous donnons une introduction systématique à la condition dépendance faible, introduit par Doukhan and Louhichi (1999) , qui est plus générale que les cadres classiques de mélange ou de séquences associées. La notion est suffisamment large pour inclure des modèles standards tels que les modèles stables de Markov , les modèles bilinéaires , et plus généralement , les schémas de Bernoulli. Dans certains cas, aucunes des propriétés de mélangeant ne peut s'attendre sans hypothèse de régularité supplémentaire sur la distribution innovations pour lesquelles une condition de dépendance faible peut être facile- ment dérivée. Nous étudions la relation entre dépendance faible et mélangeant pour les processus de valeurs discrètes. Nous montrons que la dépendance faible implique des conditions de mélangeant sous des hypothèses naturelles. Les ré- sultats se spécialisent au cas des processus Markovian. Plusieurs exemples de processus à valeur entier sont examinés et leurs propriétés de dépendance faibles sont étudiés à l'aide d'une contraction principale.Dans la deuxième partie, nous établissons des vitesses de convergences en apprentissage statistique pour les prédictions d'une série chronologique. En util- isant l'approche PAC- bayésienne, les vitesses lentes de convergence d/n pour l'estimateur de Gibbs sous la perte absolue ont été donnés dans un travail précé- dent Alquier and Wintenberger (2012), où n est la taille de l'échantillon et d la dimension de l'ensemble des prédicteurs. Sous les mêmes conditions de dépendance faible, nous étendons ce résultat à une fonction de perte Lipschitz convexe. Nous identifions également une condition sur l'espace des paramètres qui assure des vitesses similaires pour la procédure classique de l'ERM pé- nalisé. Nous appliquons cette méthode pour la prédiction quantile du PIB français. Dans des conditions supplémentaires sur les fonctions de perte ( satis- faites par la fonction de perte quadratique ) et pour les processus uniformément mélangeant, nous montrons que l'estimateur de Gibbs atteint effectivement lesivvitesses rapides de convergence d/n. Nous discutons de l' optimalité de ces dif- férentes vitesses à abaisser les limites en soulignant des références quand elles sont disponibles. En particulier, ces résultats apportent une généralisation des résultats de Dalalyan and Tsybakov (2008) sur l'estimation en régression sparse à certains auto-régression. / This thesis aims at a systematic introduction to a weak dependence condition, provided by Doukhan and Louhichi (1999), which is more general than the clas- sical frameworks of mixing or associated sequences. The notion is broad enough to include some standard models such as stable Markov models, bilinear models, and more generally, Bernoulli shifts. In some cases no mixing properties can be expected without additional regularity assumption on the distribution of the innovations distribution for which a weak dependence condition can be easily de- rived. We investigate the relationship between weak dependence and mixing for discrete valued processes. We show that weak dependence implies mixing con- ditions under natural assumptions. The results specialize to the case of Markov processes. Several examples of integer valued processes are discussed and their weak dependence properties are investigated by means of a contraction principle.In the second part, we establish rates of convergences in statistical learning for time series forecasting. Using the PAC-Bayesian approach, slow rates of con- vergence d/n for the Gibbs estimator under the absolute loss were given in a previous work Alquier and Wintenberger (2012), where n is the sample size and d the dimension of the set of predictors. Under the same weak dependence conditions, we extend this result to any convex Lipschitz loss function. We also identify a condition on the parameter space that ensures similar rates for the clas- sical penalized ERM procedure. We apply this method for quantile forecasting of the French GDP. Under additional conditions on the loss functions (satisfied by the quadratic loss function) and for uniformly mixing processes, we prove that the Gibbs estimator actually achieves fast rates of convergence d/n. We discuss the optimality of these different rates pointing out references to lower bounds when they are available. In particular, these results bring a generalization of the results of Dalalyan and Tsybakov (2008) on sparse regression estimation to some autoregression.

Made available in DSpace on 2014-06-11T19:22:49Z (GMT). No. of bitstreams: 0 Previous issue date: 2011-12-14Bitstream added on 2014-06-13T20:47:32Z : No. of bitstreams: 1 xavier_rf_me_prud.pdf: 788260 bytes, checksum: 7ab87eb37bf3e7b481df9e653a6f0f74 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Introdução: A exposição ao cigarro promove alterações que prejudicam a eficácia do transporte mucociliar. Contudo, a influência da intensidade de exposição, assim como os efeitos da abstinência ao tabagismo sobre essas alterações foram pouco elucidados. Objetivos: Avaliar a influência de diferentes intensidades de exposição ao cigarro sobre o transporte mucociliar e o efeito da cessação do tabagismo sobre o transporte mucociliar nasal em fumantes avaliados durante um período de 180 dias. Casuística e Métodos: Participantes de um programa de cessação ao tabagismo, foram avaliados quanto ao histórico tabagístico, ao nível de dependência à nicotina, à avaliação da função pulmonar (espirometria), a concentração de monóxido de carbono no ar exalado (COex), ao nível de carboxihemoglobina (COHb) e ao transporte mucociliar (tempo de trânsito de sacarina – TTS). Para comparação foi avaliado um grupo... / Introduction: Exposure to cigarette smoke promotes changes that harm the effectiveness of the mucociliary clearance. However, the influence of the intensity of exposure, as well as the effects of abstinence from smoking on these changes is poorly understood. Objectives: To assess the influence of different intensities of exposure to cigarette smoke on mucociliary clearance and the effect of cessation of smoking on nasal mucociliary clearance in smokers evaluated over a period of 180 days. Methods: Participants from a smoking cessation programme, were evaluated about smoking behavior, level of nicotine dependence, lung function (spirometry), the carbon monoxide in exhaled air (exhaled CO), the carboxyhemoglobin (COHb) and mucociliary clearance (saccharin transit time - STT). Was evaluated for comparison... (Complete abstract click electronic access below)

Made available in DSpace on 2014-10-09T12:49:04Z (GMT). No. of bitstreams: 0 / Made available in DSpace on 2014-10-09T14:09:58Z (GMT). No. of bitstreams: 1 09677.pdf: 2435386 bytes, checksum: fad3b9442aa6c7409060487b5f245ba6 (MD5) / Dissertacao (Mestrado Profissionalizante em Lasers em Odontologia) / IPEN/D-MPLO / Instituto de Pesquisas Energeticas e Nucleares, IPEN/CNEN-SP; Faculdade de Odontologia, Universidade de Sao Paulo

Made available in DSpace on 2014-10-09T12:49:04Z (GMT). No. of bitstreams: 0 / Made available in DSpace on 2014-10-09T14:09:58Z (GMT). No. of bitstreams: 1 09677.pdf: 2435386 bytes, checksum: fad3b9442aa6c7409060487b5f245ba6 (MD5) / Dissertacao (Mestrado Profissionalizante em Lasers em Odontologia) / IPEN/D-MPLO / Instituto de Pesquisas Energeticas e Nucleares, IPEN/CNEN-SP; Faculdade de Odontologia, Universidade de Sao Paulo

The tail dependence coefficient (TDC) is a natural tool to describe extremal dependence. Estimation of the tail dependence coefficient can be performed via empirical process theory. In case of extremal independence, the limit degenerates and hence one cannot construct a test for extremal independence. In order to deal with this issue, we consider an analog of the covariance matrix, namely the extremogram matrix, whose entries depend only on extremal observations. We show that under the null hypothesis of extremal independence and for finite dimension d ≥ 2, the largest eigenvalue of the sample extremogram matrix converges to the maximum of d independent normal random variables. This allows us to conduct an hypothesis testing for extremal independence by means of the asymptotic distribution of the largest eigenvalue. Simulation studies are performed to further illustrate this approach.

Class of 2014 Abstract / Specific Aims: To show that Suboxone is more effective than no MAT (Medically Assisted Treatment) in opioid dependence. Additionally, that Suboxone is as effective as methadone in MAT. Methods: This study was a retrospective chart review of probationer’s case files at The Pima County Adult Probation Office. Treatment groups included: Suboxone (n=16), methadone (n=15), and no MAT control group (n=15). The total sample size was 46 probationers. The primary dependent variables were the number of negative events and time to a negative event (i.e. missed/positive urinalysis, violation of terms of probation). The secondary outcome variables were the number of positive events and time to a positive event (i.e. finding employment, documented social/family improvement). Data analysis utilized chi-square for categorical data while t-tests were used for continuous data. Main Results: 46 probationers of Pima County with violations related to possession or use of an opioid substance were analyzed. No significant differences were found between Suboxone and placebo (no MAT) for any of the four outcomes (number of negative events p=0.82; time to first negative event p=0.41; number of positive events p=0.93; time to first positive event p=0.45). No significant differences were found between Suboxone and methadone as well (number of negative events p=0.34; time to first negative event p=0.52; number of positive events p=0.93; time to first positive event p=0.56). Conclusion: This study found no statistically significant differences between no MAT and Suboxone nor Suboxone and methadone. Differences in baseline characteristics between groups were found that could characterize the Suboxone group as being more severely ill.

This article aims to contribute to the long-standing discussion about nonprofit organizations' (NPOs) dependence on public funding and its consequences on their advocacy role in modern societies. Drawing on resource dependence theory and data from a quantitative survey, the study investigates the impact of public funding and its extent on nonprofit engagement in advocacy. Traditionally, scholars have cautioned that NPOs reliant on public sources will hesitate to pursue political objectives and to engage in advocacy work. Yet, empirical findings are strikingly inconsistent. One of the reasons for these ambiguous findings may be the way advocacy is measured. To address this issue, we apply two different approaches to evaluate NPO engagement. Both sets of findings from our multivariate analyses of Austrian NPOs suggest that public funding does not have a negative impact on advocacy.

Class of 2005 Abstract / Objectives: The purpose of this study was to determine the demographics of co-morbid disorders and drug abuse characteristics of patients admitted to an inpatient facility for detoxification and treatment of chemical dependency to characterize the treatment programs including the psychiatric medication usage and prescribing patterns and to identify differences between men and women. Methods: Criteria inclusion for admittance included a diagnosis of chemical dependence at Sierra Tucson Behavioral Health Hospital during the time of January through June 2004. Patients were admitted to that were diagnosed with a chemical dependency, identified using a past hospital census. Charts of previously discharged patients were obtained from the medical records department of the institution. Specific variables from each chart were extracted for further analysis utilizing a data form. Results: 285 (170 women and 115) men chemically dependent patients that were admitted during the six-month study period. In this patient population there was a high incidence, 76.84%, of co-morbid psychiatric conditions. The most frequently abused drugs in men were alcohol, nicotine, and cocaine. The most frequently abused drugs in women were alcohol, nicotine, and opiates. Men and women were most frequently placed on a librium based alcohol detoxification program, and secondly a buprenorphine based opiate detoxification program. There was statistical significant improvement in the of Beck Depression Inventory scale (BDI), Beck Hopelessness scale (BHS), and Global Assessment Function (GAF) scores at admit and discharge and a downward trend in Clinical Institute Withdrawal Assessment (CIWA) and Clinical Opiate Withdrawal (COW) scores. Implications: There was a high incidence of co-morbid psychiatric conditions such as depression and anxiety that were present in both genders. In men, Attention Deficit and Hyperactivity Disorder/ Attention Deficit Disorder (ADHD/ADD) was an additional common condition observed, while in women eating disorders were observed. The treatments provided led to an overall improvement in GAF, BDI, BHS, CIWA and COW scores indicating effectiveness of the treatment program.

While the phenotypic effects of sexual selection have been well studied, the consequences for population mean fitness remain unclear. Additionally, there is a need to more fully characterize how various forms of inter- and intrasexual selection combine to affect the evolution of traits under sexual selection. Here, I address these issues as they relate to male territoriality in Drosophila serrata, a model system for the study of female preference for male pheromones. First, I demonstrate that territoriality occurs and is a likely component of male sexual fitness. Results from a phenotypic manipulation indicate that territorial success was also condition-dependent, and that sexual selection against low condition males tended to be stronger given a high opportunity for territory defense. Territorial success depended on body size but not on pheromones. How this and other components of male mating success interact to affect trait evolution and population mean fitness remains an important area for future study.