Simulation-Based Finite and Large Sample Tests in Multivariate Regressions.

In the context of multivariate linear regression (MLR) models, it is well known that commonly employed asymptotic test criteria are seriously biased towards overrejection. In this paper, we propose a general method for constructing exact tests of possibly nonlinear hypotheses on the coefficients of MLR systems. For the case of uniform linear hypotheses, we present exact distributional invariance results concerning several standard test criteria. These include Wilks' likelihood ratio (LR) criterion as well as trace and maximum root criteria. The normality assumption is not necessary for most of the results to hold. Implications for inference are two-fold. First, invariance to nuisance parameters entails that the technique of Monte Carlo tests can be applied on all these statistics to obtain exact tests of uniform linear hypotheses. Second, the invariance property of the latter statistic is exploited to derive general nuisance-parameter-free bounds on the distribution of the LR statistic for arbitrary hypotheses. Even though it may be difficult to compute these bounds analytically, they can easily be simulated, hence yielding exact bounds Monte Carlo tests. Illustrative simulation experiments show that the bounds are sufficiently tight to provide conclusive results with a high probability. Our findings illustrate the value of the bounds as a tool to be used in conjunction with more traditional simulation-based test methods (e.g., the parametric bootstrap) which may be applied when the bounds are not conclusive.

Actuarial applications of multivariate phase-type distributions : model calibration and credibility

Thèse numérisée par la Division de la gestion de documents et des archives de l'Université de Montréal

Inférence robuste à la présence des valeurs aberrantes dans les enquêtes

Cette thèse comporte trois articles dont un est publié et deux en préparation. Le sujet central de la thèse porte sur le traitement des valeurs aberrantes représentatives dans deux aspects importants des enquêtes que sont : l’estimation des petits domaines et l’imputation en présence de non-réponse partielle. En ce qui concerne les petits domaines, les estimateurs robustes dans le cadre des modèles au niveau des unités ont été étudiés. Sinha & Rao (2009) proposent une version robuste du meilleur prédicteur linéaire sans biais empirique pour la moyenne des petits domaines. Leur estimateur robuste est de type «plugin», et à la lumière des travaux de Chambers (1986), cet estimateur peut être biaisé dans certaines situations. Chambers et al. (2014) proposent un estimateur corrigé du biais. En outre, un estimateur de l’erreur quadratique moyenne a été associé à ces estimateurs ponctuels. Sinha & Rao (2009) proposent une procédure bootstrap paramétrique pour estimer l’erreur quadratique moyenne. Des méthodes analytiques sont proposées dans Chambers et al. (2014). Cependant, leur validité théorique n’a pas été établie et leurs performances empiriques ne sont pas pleinement satisfaisantes. Ici, nous examinons deux nouvelles approches pour obtenir une version robuste du meilleur prédicteur linéaire sans biais empirique : la première est fondée sur les travaux de Chambers (1986), et la deuxième est basée sur le concept de biais conditionnel comme mesure de l’influence d’une unité de la population. Ces deux classes d’estimateurs robustes des petits domaines incluent également un terme de correction pour le biais. Cependant, ils utilisent tous les deux l’information disponible dans tous les domaines contrairement à celui de Chambers et al. (2014) qui utilise uniquement l’information disponible dans le domaine d’intérêt. Dans certaines situations, un biais non négligeable est possible pour l’estimateur de Sinha & Rao (2009), alors que les estimateurs proposés exhibent un faible biais pour un choix approprié de la fonction d’influence et de la constante de robustesse. Les simulations Monte Carlo sont effectuées, et les comparaisons sont faites entre les estimateurs proposés et ceux de Sinha & Rao (2009) et de Chambers et al. (2014). Les résultats montrent que les estimateurs de Sinha & Rao (2009) et de Chambers et al. (2014) peuvent avoir un biais important, alors que les estimateurs proposés ont une meilleure performance en termes de biais et d’erreur quadratique moyenne. En outre, nous proposons une nouvelle procédure bootstrap pour l’estimation de l’erreur quadratique moyenne des estimateurs robustes des petits domaines. Contrairement aux procédures existantes, nous montrons formellement la validité asymptotique de la méthode bootstrap proposée. Par ailleurs, la méthode proposée est semi-paramétrique, c’est-à-dire, elle n’est pas assujettie à une hypothèse sur les distributions des erreurs ou des effets aléatoires. Ainsi, elle est particulièrement attrayante et plus largement applicable. Nous examinons les performances de notre procédure bootstrap avec les simulations Monte Carlo. Les résultats montrent que notre procédure performe bien et surtout performe mieux que tous les compétiteurs étudiés. Une application de la méthode proposée est illustrée en analysant les données réelles contenant des valeurs aberrantes de Battese, Harter & Fuller (1988). S’agissant de l’imputation en présence de non-réponse partielle, certaines formes d’imputation simple ont été étudiées. L’imputation par la régression déterministe entre les classes, qui inclut l’imputation par le ratio et l’imputation par la moyenne sont souvent utilisées dans les enquêtes. Ces méthodes d’imputation peuvent conduire à des estimateurs imputés biaisés si le modèle d’imputation ou le modèle de non-réponse n’est pas correctement spécifié. Des estimateurs doublement robustes ont été développés dans les années récentes. Ces estimateurs sont sans biais si l’un au moins des modèles d’imputation ou de non-réponse est bien spécifié. Cependant, en présence des valeurs aberrantes, les estimateurs imputés doublement robustes peuvent être très instables. En utilisant le concept de biais conditionnel, nous proposons une version robuste aux valeurs aberrantes de l’estimateur doublement robuste. Les résultats des études par simulations montrent que l’estimateur proposé performe bien pour un choix approprié de la constante de robustesse.

Precision of distances and ordering of microsatellite markers in consensus linkage maps of chromosomes 1, 3 and 4 from two reciprocal chicken populations using bootstrap sampling

Some factors complicate comparisons between linkage maps from different studies. This problem can be resolved if measures of precision, such as confidence intervals and frequency distributions, are associated with markers. We examined the precision of distances and ordering of microsatellite markers in the consensus linkage maps of chromosomes 1, 3 and 4 from two F 2 reciprocal Brazilian chicken populations, using bootstrap sampling. Single and consensus maps were constructed. The consensus map was compared with the International Consensus Linkage Map and with the whole genome sequence. Some loci showed segregation distortion and missing data, but this did not affect the analyses negatively. Several inversions and position shifts were detected, based on 95% confidence intervals and frequency distributions of loci. Some discrepancies in distances between loci and in ordering were due to chance, whereas others could be attributed to other effects, including reciprocal crosses, sampling error of the founder animals from the two populations, F(2) population structure, number of and distance between microsatellite markers, number of informative meioses, loci segregation patterns, and sex. In the Brazilian consensus GGA1, locus LEI1038 was in a position closer to the true genome sequence than in the International Consensus Map, whereas for GGA3 and GGA4, no such differences were found. Extending these analyses to the remaining chromosomes should facilitate comparisons and the integration of several available genetic maps, allowing meta-analyses for map construction and quantitative trait loci (QTL) mapping. The precision of the estimates of QTL positions and their effects would be increased with such information.

Método de Bootstrap e teoria da credibilidade na estimativa das provisões para sinistros

Dissertação para obtenção do Grau de Mestre em Matemática e Aplicações, no ramo Actuariado, Estatística e Investigação Operacional

Dealing with frame imperfections in a business survey: an empirical study using without replacement bootstrap

This paper approaches issues related to frame problems and nonresponse in surveys. These nonsampling errors affect the accuracy of the estimates whereas the estimators became biased and less precise. We analyse some estimation methods that deal with those problems and give an especial focus to post-stratification procedures.

Bootstrap performance profiles in stochastic algorithms assessment

Optimization with stochastic algorithms has become a relevant research field. Due to its stochastic nature, its assessment is not straightforward and involves integrating accuracy and precision. Performance profiles for the mean do not show the trade-off between accuracy and precision, and parametric stochastic profiles require strong distributional assumptions and are limited to the mean performance for a large number of runs. In this work, bootstrap performance profiles are used to compare stochastic algorithms for different statistics. This technique allows the estimation of the sampling distribution of almost any statistic even with small samples. Multiple comparison profiles are presented for more than two algorithms. The advantages and drawbacks of each assessment methodology are discussed.

Forecasting time series combining Holt-Winters and bootstrap approaches

Publicado em "AIP Conference Proceedings", Vol. 1648

A metodologia Bootstrap associada ao método de Holt-Winters na previsão de séries temporais

Os métodos de alisamento exponencial são muito utilizados na modelação e previsão de séries temporais, devido à sua versatilidade e opção de modelos que integram. Na estatística computacional, a metodologia Bootstrap é muito aplicada em inferência estatística no âmbito de séries temporais. Este estudo teve como principal objectivo analisar o desempenho do método de Holt-Winters associado à metodologia Bootstrap, como um processo alternativo na modelação e previsão de séries temporais.

A Bootstrap Neural Network Based Heterogeneous Panel Unit Root Test: Application to Exchange Rates

This paper proposes a bootstrap artificial neural network based panel unit root test in a dynamic heterogeneous panel context. An application to a panel of bilateral real exchange rate series with the US Dollar from the 20 major OECD countries is provided to investigate the Purchase Power Parity (PPP). The combination of neural network and bootstrapping significantly changes the findings of the economic study in favour of PPP.

A Consistent Nonparametric Bootstrap Test of Exogeneity

This paper proposes a novel way of testing exogeneity of an explanatory variable without any parametric assumptions in the presence of a "conditional" instrumental variable. A testable implication is derived that if an explanatory variable is endogenous, the conditional distribution of the outcome given the endogenous variable is not independent of its instrumental variable(s). The test rejects the null hypothesis with probability one if the explanatory variable is endogenous and it detects alternatives converging to the null at a rate n..1=2:We propose a consistent nonparametric bootstrap test to implement this testable implication. We show that the proposed bootstrap test can be asymptotically justi.ed in the sense that it produces asymptotically correct size under the null of exogeneity, and it has unit power asymptotically. Our nonparametric test can be applied to the cases in which the outcome is generated by an additively non-separable structural relation or in which the outcome is discrete, which has not been studied in the literature.

Método convencional e "bootstrap" para estimar o número de observações na determinação dos parâmetros da função K(Θ)

A variabilidade natural do solo dificulta a obtenção de valores que representem adequadamente as propriedades do solo em determinada área. O conhecimento do número mínimo de observações, que devem ser realizadas para representar, com um erro aceitável, uma propriedade ou característica do solo, é fundamental para que os resultados experimentais possam ser aplicados com segurança. No presente trabalho, comparou-se o método convencional (teste-t) com o método "bootstrap", com vistas em estimar o número de observações necessárias para calcular os parâmetros que caracterizam a relação entre a condutividade hidráulica e o teor de água do solo, determinada pelo método do perfil instantâneo. Realizou-se um experimento de drenagem num Latossolo Vermelho-Amarelo em Piracicaba (SP), numa parcela experimental com 45 pontos de observação distanciados de 1 m entre si. Observaram-se a umidade (com TDR) e o potencial mátrico (com tensiômetros) durante três semanas de redistribuição da água. Após processamento dos dados, o conjunto de valores mostrou uma distribuição não-normal, fazendo-se necessária a eliminação de "outliers" para a aplicação do método convencional, normalizando a distribuição. Assim, o uso do método tradicional só é recomendado após a confirmação da pertinência da eliminação dos "outliers". Ambos os métodos de análise requerem grande número de repetições, reafirmando que determinações da função condutividade hidráulica com poucas repetições não podem ser extrapoladas para áreas maiores.

Applications of the bootstrap to survival analysis

En este trabajo se revisan algunas de las aplicaciones clásicas del bootstrap al análisis de la supervivencia. Se consideran en primer lugar el estimador bootstrap de la varianza y el estimador de la mediana corregido para el sesgo del estimador de Kaplan-Meier de la función de supervivencia. A continuación se consideran algunos aspectos mas recientes, tales como métodos para construir bandas de confianza para el estimador de la funcidn de supervivencia y contrastes aproximados para la comparación de funciones de supervivencia. En ambas situaciones el bootstrap resulta de gran utilidad para la aproximación de 10s valores críticos necesarios.

Intervalo de confiança "bootstrap" como ferramenta para classificar raças do nematóide de cisto da soja

Estimativas "bootstrap" da média aritmética dos genótipos de soja 'Pickett', 'Peking', PI88788 e PI90763 e os intervalos de confiança obtidos pela teoria normal e através da distribuição "bootstrap" deste estimador, como o percentil "bootstrap" e o BCa, correção para o viés e aceleração, do parâmetro de diferenciação da cultivar padrão de suscetibilidade Lee são utilizados para classificar raças do nematóide de cisto da soja. Os intervalos de confiança obtidos a partir da distribuição "bootstrap" apresentaram menor amplitude e foram muito similares, dessa forma, o limite inferior do intervalo de confiança percentil "bootstrap" foi tomado como nível de referência nas distribuições "bootstrap" do estimador da média aritmética dos genótipos diferenciadores, permitindo estimar a probabilidade empírica de uma reação positiva ou negativa, e, conseqüentemente, identificar a raça mais provável sob determinado teste.