In the recent years, the internet has been developed rapidly. By this convenient medium, the information can be spread easily all over the world. Using the convenience and variety of internet, e-learning has become a burgeoning and efficient way for learning. The main idea of e-learning is applying the concept of Asynchronous Course Delivery, and establishing a learning environment on the internet. With the connection between computer and the internet, user can learn more in a convenient environment. In order to apply the concept of e-learning to the course of statistics, we use the Java programming language to establish an on-line interactive environment. In addition to learn some fundamental concepts of statistics, learner can also strengthen the abilities of researching and surfing by themselves. In this paper we developed six interactive examples. Not only interpreting and illustrating, we also introduce the motive, goal, relative concepts and applications in detail for each example. Finally, we hope that user can easily learn more knowledge of statistics by this learning environment, then our e-learning to statistical education, can be achieved.

In time series models, autoregressive processes are one of the most popular stochastic processes, which are stationary under certain conditions. In this study we consider nonstationary autoregressive models of order one, which have iid random errors. One of the important nonstationary time series models is the unit root process in AR (1), which simply implies that a shock to the system has permanent effect through time. Therefore, testing unit root is a very important problem. However, under nonstationarity, any estimator of the autoregressive coefficient does not have a known exact distribution and the usual t &ndash / statistic is not accurate even if the sample size is very large. Hence,Wiener process is invoked to obtain the asymptotic distribution of the LSE under normality. The first four moments of under normality have been worked out for large n. In 1998, Tiku and Wong proposed the new test statistics and whose type I error and power values are calculated by using three &ndash / moment chi &ndash / square or four &ndash / moment F approximations. The test statistics are based on the modified maximum likelihood estimators and the least square estimators, respectively. They evaluated the type I errors and the power of these tests for a family of symmetric distributions (scaled Student&rsquo / s t). In this thesis, we have extended this work to skewed distributions, namely, gamma and generalized logistic.

Made available in DSpace on 2016-06-02T20:06:05Z (GMT). No. of bitstreams: 1 4180.pdf: 1039417 bytes, checksum: d09a61a4895fb47d1c2456468800fc2f (MD5) Previous issue date: 2012-02-29 / Financiadora de Estudos e Projetos / In this work we consider a new estimator proposed by Ferrari & Yang (2010), called the maximum Lq-likelihood estimator (MLqE), to estimate the parameters of the measurement error models, in particular, the structural model. The new estimator extends the classical maximum likelihood estimator (MLE) and its based on the minimization, by means of the Kullback-Leibler (KL) divergence, of the discrepancy between a distribuiton in a family and one that modifies the true distribution by the degree of distortion q. Depending on the choice of q, the transformed distribution can diminish or emphasize the role of extreme observations, unlike the ML method that equally weights each observation. For small and moderate sample sizes, the MLqE can trade bias for precision, causing a reduction of the mean square error (MSE). The structural model has the characteristic of non-identifiability. For this reason, we must make assumptions on the parameters to overcome the non-identifiability. We perform a analytical study and a simulation study to compare MLqE and MLE. To gauge performance of the estimators, we compute measures of overall performance, bias, standard deviation, standard error, MSE, probability of coverage and length of confidence intervals. / Neste trabalho utilizaremos um novo estimador proposto por Ferrari & Yang (2010), denominado de estimador de máxima Lq-verossimilhança (EMLqV), na estimação dos parâmetros de modelos com erros de medição estruturais normais. O novo estimador é uma generalização do estimador de máxima verossimilhança (EMV) usual e sua construção baseia-se na comparação, utilizando divergência de Kullback-Leibler (KL), entre duas distribuições, a distribuição inalterada e a distribuição modificada pelo grau de distorção da função de verossimilhança (q). Conforme a escolha para q, a distribuição modificada poderá atenuar ou exaltar o papel das observações extremas, diferentemente do EMV usual que atribui os mesmos pesos a todas as observações. Na comparação entre as duas distribuições pela divergência de KL é inserida certa quantidade de viés no estimador resultante, que é controlada pelo parâmetro q. O aumento do viés do estimador MLqV pode ser compensado com a redução de sua variância, pela escolha apropriada de q. O modelo estrutural possui a característica de ser inidentificável. Para torná-lo identificável faremos suposições sobre os parâmetros do modelo, analisando cinco casos de identificabilidade do modelo. A comparação entre os métodos MLqV e MV na estimação dos parâmetros do modelo será baseada em resultados analíticos e em simulações, sendo calculadas medidas de desempenho global, viés, desvio padrão (DP), erro padrão estimado (EP), erro quadrático médio (EQM), probabilidade de cobertura e amplitude dos intervalos de confiança.

Cognitive radio (CR) is often described as a context-intelligent radio, capable of changing the transmit parameters dynamically based on the interaction with the environment it operates. The work in this thesis explores the problem of using received signal strength (RSS) measurements taken by a network of CR nodes to generate an interference map of a given geographical area and estimate the locations of multiple primary transmitters that operate simultaneously in the area. A probabilistic model of the problem is developed, and algorithms to address location estimation challenges are proposed. Three approaches are proposed to solve the localization problem. The first approach is based on estimating the locations from the generated interference map when no information about the propagation model or any of its parameters is present. The second approach is based on approximating the maximum likelihood (ML) estimate of the transmitter locations with the grid search method when the model is known and its parameters are available. The third approach also requires the knowledge of model parameters but it is actually based on generating samples from the joint posterior of the unknown location parameter with Markov chain Monte Carlo (MCMC) methods, as an alternative for the highly computationally complex grid search approach. For RF cartography generation problem, we study global and local interpolation techniques, specifically the Delaunay triangulation based techniques as the use of existing triangulation provides a computationally attractive solution. We present a comparative performance evaluation of these interpolation techniques in terms of RF field strength estimation and emitter localization. Even though the estimates obtained from the generated interference maps are less accurate compared to the ML estimator, the rough estimates are utilized to initialize a more accurate algorithm such as the MCMC technique to reduce the complexity of the algorithm. The complexity issues of ML estimators based on full grid search are also addressed by various types of iterative grid search methods. One challenge to apply the ML estimation algorithm to multiple emitter localization problem is that, it requires a pdf approximation to summands of log-normal random variables for likelihood calculations at each grid location. This inspires our investigations on sum of log-normal approximations studied in literature for selecting the appropriate approximation to our model assumptions. As a final extension of this work, we propose our own approximation based on distribution fitting to a set of simulated data and compare our approach with Fenton-Wilkinson's well-known approximation which is a simple and computational efficient approach that fits a log-normal distribution to sum of log-normals by matching the first and second central moments of random variables. We demonstrate that the location estimation accuracy of the grid search technique obtained with our proposed approximation is higher than the one obtained with Fenton-Wilkinson's in many different case scenarios.

Dans le contexte de l'estimation paramétrique, les performances d'un estimateur peuvent être caractérisées, entre autre, par son erreur quadratique moyenne (EQM) et sa résolution limite. La première quantifie la précision des valeurs estimées et la seconde définit la capacité de l'estimateur à séparer plusieurs paramètres. Cette thèse s'intéresse d'abord à la prédiction de l'EQM "optimale" à l'aide des bornes inférieures pour des problèmes d'estimation simultanée de paramètres aléatoires et non-aléatoires (estimation hybride), puis à l'extension des bornes de Cramér-Rao pour des modèles d'observation moins standards. Enfin, la caractérisation des estimateurs en termes de résolution limite est également étudiée. Ce manuscrit est donc divisé en trois parties :Premièrement, nous complétons les résultats de littérature sur les bornes hybrides en utilisant deux bornes bayésiennes : la borne de Weiss-Weinstein et une forme particulière de la famille de bornes de Ziv-Zakaï. Nous montrons que ces bornes "étendues" sont plus précises pour la prédiction de l'EQM optimale par rapport à celles existantes dans la littérature.Deuxièmement, nous proposons des bornes de type Cramér-Rao pour des contextes d'estimation moins usuels, c'est-à-dire : (i) Lorsque les paramètres non-aléatoires sont soumis à des contraintes d'égalité linéaires ou non-linéaires (estimation sous contraintes). (ii) Pour des problèmes de filtrage à temps discret où l'évolution des états (paramètres) est régit par une chaîne de Markov. (iii) Lorsque la loi des observations est différente de la distribution réelle des données.Enfin, nous étudions la résolution et la précision des estimateurs en proposant un critère basé directement sur la distribution des estimées. Cette approche est une extension des travaux de Oh et Kashyap et de Clark pour des problèmes d'estimation de paramètres multidimensionnels. / In the parametric estimation context, estimators performances can be characterized, inter alia, by the mean square error and the resolution limit. The first quantities the accuracy of estimated values and the second defines the ability of the estimator to allow a correct resolvability. This thesis deals first with the prediction the "optimal" MSE by using lower bounds in the hybrid estimation context (i.e. when the parameter vector contains both random and non-random parameters), second with the extension of Cramér-Rao bounds for non-standard estimation problems and finally to the characterization of estimators resolution. This manuscript is then divided into three parts :First, we fill some lacks of hybrid lower bound on the MSE by using two existing Bayesian lower bounds: the Weiss-Weinstein bound and a particular form of Ziv-Zakai family lower bounds. We show that these extended lower bounds are tighter than the existing hybrid lower bounds in order to predict the optimal MSE.Second, we extend Cramer-Rao lower bounds for uncommon estimation contexts. Precisely: (i) Where the non-random parameters are subject to equality constraints (linear or nonlinear). (ii) For discrete-time filtering problems when the evolution of states are defined by a Markov chain. (iii) When the observation model differs to the real data distribution.Finally, we study the resolution of the estimators when their probability distributions are known. This approach is an extension of the work of Oh and Kashyap and the work of Clark to multi-dimensional parameters estimation problems.

Ce travail de thèse porte sur l'estimation paramétrique du maximum de vraisemblance pour des données de survie tronquées à droite, lorsque les délais de troncature sont considérés déterministes. Il a été motivé par le problème de la modélisation des délais de survenue des effets indésirables médicamenteux à partir des bases de données de pharmacovigilance, constituées des cas notifiés. Les distributions exponentielle, de Weibull et log-logistique ont été explorées.Parfois le caractère tronqué à droite des données est ignoré et un estimateur naïf est utilisé à la place de l'estimateur pertinent. Une première étude de simulations a montré que, bien que ces deux estimateurs - naïf et basé sur la troncature à droite - puissent être positivement biaisés, le biais de l'estimateur basé sur la troncature est bien moindre que celui de l'estimateur naïf et il en va de même pour l'erreur quadratique moyenne. De plus, le biais et l'erreur quadratique moyenne de l'estimateur basé sur la troncature à droite diminuent nettement avec l'augmentation de la taille d'échantillon, ce qui n'est pas le cas de l'estimateur naïf. Les propriétés asymptotiques de l'estimateur paramétrique du maximum de vraisemblance ont été étudiées. Sous certaines conditions, suffisantes, cet estimateur est consistant et asymptotiquement normal. La matrice de covariance asymptotique a été détaillée. Quand le délai de survenue est modélisé par la loi exponentielle, une condition d'existence de l'estimation du maximum de vraisemblance, assurant ces conditions suffisantes, a été obtenue. Pour les deux autres lois, une condition d'existence de l'estimation du maximum de vraisemblance a été conjecturée.A partir des propriétés asymptotiques de cet estimateur paramétrique, les intervalles de confiance de type Wald et de la vraisemblance profilée ont été calculés. Une seconde étude de simulations a montré que la couverture des intervalles de confiance de type Wald pouvait être bien moindre que le niveau attendu en raison du biais de l'estimateur du paramètre de la distribution, d'un écart à la normalité et d'un biais de l'estimateur de la variance asymptotique. Dans ces cas-là, la couverture des intervalles de la vraisemblance profilée est meilleure.Quelques procédures d'adéquation adaptées aux données tronquées à droite ont été présentées. On distingue des procédures graphiques et des tests d'adéquation. Ces procédures permettent de vérifier l'adéquation des données aux différents modèles envisagés.Enfin, un jeu de données réelles constitué de 64 cas de lymphomes consécutifs à un traitement anti TNF-α issus de la base de pharmacovigilance française a été analysé, illustrant ainsi l'intérêt des méthodes développées. Bien que ces travaux aient été menés dans le cadre de la pharmacovigilance, les développements théoriques et les résultats des simulations peuvent être utilisés pour toute analyse rétrospective réalisée à partir d'un registre de cas, où les données sur un délai de survenue sont aussi tronquées à droite. / This work investigates the parametric maximum likelihood estimation for right-truncated survival data when the truncation times are considered deterministic. It was motivated by the modeling problem of the adverse drug reactions time-to-onset from spontaneous reporting databases. The families of the exponential, Weibull and log-logistic distributions were explored.Sometimes, right-truncation features of spontaneous reports are not taken into account and a naive estimator is used instead of the truncation-based estimator. Even if the naive and truncation-based estimators may be positively biased, a first simulation study showed that the bias of the truncation-based estimator is always smaller than the naive one and this is also true for the mean squared error. Furthermore, when the sample size increases, the bias and the mean squared error are almost constant for the naive estimator while they decrease clearly for the truncation-based estimator.Asymptotic properties of the truncation-based estimator were studied. Under sufficient conditions, this parametric truncation-based estimator is consistent and asymptotically normally distributed. The covariance matrix was detailed. When the time-to-onset is exponentially distributed, these sufficient conditions are checked as soon as a condition for the maximum likelihood estimation existence is satisfied. When the time-to-onset is Weibull or log-logistic distributed, a condition for the maximum likelihood estimation existence was conjectured.The asymptotic distribution of the maximum likelihood estimator makes it possible to derive Wald-type and profile likelihood confidence intervals for the distribution parameters. A second simulation study showed that the estimated coverage probability of the Wald-type confidence intervals could be far from the expected level because of a bias of the parametric maximum likelihood estimator, a gap from the gaussian distribution and a bias of the asymptotic variance estimator. In these cases, the profile likelihood confidence intervals perform better.Some goodness-of-fit procedures adapted to right-truncated data are presented. Graphical procedures and goodness-of-fit tests may be distinguished. These procedures make it possible to check the fit of different parametric families to the data.Illustrating the developed methods, a real dataset of 64 cases of lymphoma, that occurred after anti TNF-α treatment and that were reported to the French pharmacovigilance, was finally analyzed. Whilst an application to pharmacovigilance was led, the theoretical developments and the results of the simulation study may be used for any retrospective analysis from case registries where data are right-truncated.

Dans cette thèse, nous étudions des modèles de moyennes conditionnelles de séries temporelles à valeurs entières. Tout d’abord, nous proposons l’estimateur de quasi maximum de vraisemblance de Poisson (EQMVP) pour les paramètres de la moyenne conditionnelle. Nous montrons que, sous des conditions générales de régularité, cet estimateur est consistant et asymptotiquement normal pour une grande classe de modèles. Étant donné que les paramètres de la moyenne conditionnelle de certains modèles sont positivement contraints, comme par exemple dans les modèles INAR (INteger-valued AutoRegressive) et les modèles INGARCH (INteger-valued Generalized AutoRegressive Conditional Heteroscedastic), nous étudions la distribution asymptotique de l’EQMVP lorsque le paramètre est sur le bord de l’espace des paramètres. En tenant compte de cette dernière situation, nous déduisons deux versions modifiées du test de Wald pour la significativité des paramètres et pour la moyenne conditionnelle constante. Par la suite, nous accordons une attention particulière au problème de validation des modèles des séries temporelles à valeurs entières en proposant un test portmanteau pour l’adéquation de l’ajustement. Nous dérivons la distribution jointe de l’EQMVP et des autocovariances résiduelles empiriques. Puis, nous déduisons la distribution asymptotique des autocovariances résiduelles estimées, et aussi la statistique du test. Enfin, nous proposons l’EQMVP pour estimer équation-par-équation (EpE) les paramètres de la moyenne conditionnelle des séries temporelles multivariées à valeurs entières. Nous présentons les hypothèses de régularité sous lesquelles l’EQMVP-EpE est consistant et asymptotiquement normal, et appliquons les résultats obtenus à plusieurs modèles des séries temporelles multivariées à valeurs entières. / The framework of this PhD dissertation is the conditional mean count time seriesmodels. We propose the Poisson quasi-maximum likelihood estimator (PQMLE) for the conditional mean parameters. We show that, under quite general regularityconditions, this estimator is consistent and asymptotically normal for a wide classeof count time series models. Since the conditional mean parameters of some modelsare positively constrained, as, for example, in the integer-valued autoregressive (INAR) and in the integer-valued generalized autoregressive conditional heteroscedasticity (INGARCH), we study the asymptotic distribution of this estimator when the parameter lies at the boundary of the parameter space. We deduce a Waldtype test for the significance of the parameters and another Wald-type test for the constance of the conditional mean. Subsequently, we propose a robust and general goodness-of-fit test for the count time series models. We derive the joint distribution of the PQMLE and of the empirical residual autocovariances. Then, we deduce the asymptotic distribution of the estimated residual autocovariances and also of a portmanteau test. Finally, we propose the PQMLE for estimating, equation-by-equation (EbE), the conditional mean parameters of a multivariate time series of counts. By using slightly different assumptions from those given for PQMLE, we show the consistency and the asymptotic normality of this estimator for a considerable variety of multivariate count time series models.

Made available in DSpace on 2016-06-02T20:06:06Z (GMT). No. of bitstreams: 1 4331.pdf: 1908865 bytes, checksum: d564b46a6111fdca6f7cc9f4d5596637 (MD5) Previous issue date: 2009-03-18 / Universidade Federal de Minas Gerais / The Weibull distribuition is a common initial choice for modeling data with monotone hazard rates. However, such distribution fails to provide a reasonable parametric _t when the hazard function is unimodal or bathtub-shaped. In this context, Cooray (2006) proposed a generalization of the Weibull family by considering the distributions of the odds of Weibull and inverse Weibull families, referred as the odd Weibull family which is not just useful for modeling unimodal and bathtub-shaped hazards, but it is also convenient for testing goodness-of-_t of Weibull and inverse Weibull as submodels. In this project we have systematically studied the odd Weibull family along with its properties, showing motivations for its utilization, inserting covariates in the model, pointing out some troubles associated with the maximum likelihood estimation and proposing interval estimation and hypothesis test construction methodologies for the model parameters. We have also compared resampling results with asymptotic ones. Coverage probability from proposed con_dence intervals and size and power of considered hypothesis tests were both analyzed as well via Monte Carlo simulation. Furthermore, we have proposed a Bayesian estimation methodology for the model parameters based in Monte Carlo Markov Chain (MCMC) simulation techniques. / A distribuição Weibull é uma escolha inicial freqüente para modelagem de dados com taxas de risco monótonas. Entretanto, esta distribuição não fornece um ajuste paramétrico razoável quando as funções de risco assumem um formato unimodal ou em forma de banheira. Neste contexto, Cooray (2006) propôs uma generalização da família Weibull considerando a distribuição da razão de chances das famílias Weibull e Weibull inversa, referida como família Weibull de razão de chances. Esta família não é apenas conveniente para modelar taxas de risco unimodal e banheira, mas também é adequada para testar a adequabilidade do ajuste das famílias Weibull e Weibull inversa como submodelos. Neste trabalho, estudamos sistematicamente a família Weibull de razão de chances e suas propriedades, apontando as motivações para o seu uso, inserindo covariáveis no modelo, veri_cando as di_culdades referentes ao problema da estimação de máxima verossimilhança dos parâmetros do modelo e propondo metodologia de estimação intervalar e construção de testes de hipóteses para os parâmetros do modelo. Comparamos os resultados obtidos por meio dos métodos de reamostragem com os resultados obtidos via teoria assintótica. Tanto a probabilidade de cobertura dos intervalos de con_ança propostos quanto o tamanho e poder dos testes de hipóteses considerados foram estudados via simulação de Monte Carlo. Além disso, propusemos uma metodologia Bayesiana de estimação para os parâmetros do modelo baseados em técnicas de simulação de Monte Carlo via Cadeias de Markov.

Dans la première partie de cette thèse, nous considérons plusieurs problèmes d'estimation de paramètre de dimension finie pour les séquences de Markov dans l'asymptotique des grands échantillons. Le comportement asymptotique des estimateurs bayésiens et les estimateurs obtenus par la méthode des moments sont décrits. Nous montrons que sous les conditions de régularité ces estimateurs sont consistants et asymptotiquement normaux et que l'estimateur bayésien est asymptotiquement efficace. Les estimateur-processus du maximum de vraisemblance un-pas et deux-pas sont étudiés. Ces estimateurs nous permettent de construire des estimateurs asymptotiquement efficaces sur la base de certainsestimateurs préliminaires, par exemple, les estimateurs obtenus par la méthode des moments ou l'estimateur deBayes et la structure de l'estimateur du maximum de vraisemblance un-pas. Nous proposons notamment des processus autorégressifs non linéaires comme exemple et nous illustrons les propriétés de ces estimateurs à l'aide de simulations numériques. Dans la deuxième partie, nous donnons les applications de processus de Markov en économie de la santé. Nous comparons les modèles de Markov homogènes et non-homogènes pour l'analyse coût-efficacité de l'utilisation depansements transparents contenant un gel de gluconate de chlorhexidine par rapport aux pansements transparents standard. Le pansement antimicrobien protège les accès vasculaire centrale et réduit le risque de bactériémies liées aux cathéters. L'impact de l'approche de modélisation sur la décision d'adopter des pansements antimicrobiens pour les patients gravement malades est discuté. / In the first part of this dissertation we consider several problems of finite-dimensional parameter estimation for Markov sequences in the asymptotics of large samples. The asymptotic behavior of the Bayesian estimators and the estimators of the method of moments are described. It is shown that under regularity conditions these estimators are consistent and asymptotically normal. We show that the Bayesian estimator is asymptotically efficient. The one-step and two-step maximum likelihood estimator-processes are studied. These estimators allow us to construct the asymptotically efficient estimators based on some preliminary estimators, say, the estimators of the method of moments or Bayes estimator and the one-step maximum likelihood estimator structure. We propose particular non-linear autoregressive processes as examples and we illustrate the properties of these estimators with the help of numerical simulations. In the second part we give theapplications of Markov processes in health economics. We compare homogeneous and non-homogeneous Markov models for cost-effectiveness analysis of routine use of transparent dressings containing a chlorhexidine gluconate gel pad versus standard transparent dressings. The antimicrobial dressing protects central vascular accesses reducing the risk of catheter-related bloodstream infections. The impact of the modeling approach on the decision of adopting antimicrobialdressings for critically-ill patients is discussed.

[pt] O objetivo desta dissertação é comparar através de um estudo de simulação diferentes estimadores de modelos não-lineares. Nós consideramos neste trabalho o estimador não-linear de mínimos quadrados em dois estágios (NL2SLS), o estimador não-linear de máxima verossimilhança de informação limitada (LIML) e o estimador com função controle (CF). Os resultados mostram que os estimadores CF e LIML possuem em geral uma performance superior ao do NL2SLS para os modelos selecionados. O trabalho considera uma aplicação de uma Curva de Phillips não-linear para a Economia Brasileira. / [en] The aim of this dissertation is to compare, in a simulation study, different nonlinear estimators for selected models. We consider the two-stage nonlinear least-squares (NL2SLS), the nonlinear limited information maximum likelihood (LIML), and the control function (CF) estimator. Our results show that usually either CF or LIML estimators perform better than the NL2SLS estimator for the selected models. In an application with real data, we consider the estimation a nonlinear Phillips Curve for Brazilian economy.