Página 1 dos resultados de 348 itens digitais encontrados em 0.025 segundos

Procedimento para determinação experimental de carregamentos externos para o projeto estrutural de uma plataforma semi-submersível.; Procedure for experimental determination of external loads for structural design of a Semi-Submersible platform.

Garcia, Edgard Enrique Mulford
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 21/10/2014 Português
Relevância na Pesquisa
67.375273%
Um dos aspectos fundamentais do projeto estrutural de plataformas flutuantes para produção de petróleo no mar é a determinação dos carregamentos externos globais provenientes da ação das ondas sobre a estrutura da plataforma. A presente dissertação de mestrado apresenta uma proposta de procedimento destinado à determinação experimental, em tanque de provas, dos carregamentos estruturais globais atuantes em uma plataforma de exploração e produção de petróleo do tipo semi-submersível. O procedimento proposto envolve as seguintes etapas: especificação do tipo de esforço que se pretende medir; definição das condições de ensaio; definição da escala dos modelos; escolha do processo construtivo dos modelos; especificação do processo de medida dos esforços; definição dos equipamentos e instrumentos de medida experimental; especificação da matriz de ensaios; definição dos procedimentos de análise de resultados. Como exemplo de aplicação, o procedimento proposto foi empregado na avaliação dos esforços de Momento Fletor no Convés e Força de Separação nos Flutuadores de uma Plataforma Semi-submersível padrão, empregada para validação de resultados em tanques de prova. Os resultados obtidos foram comparados com os da literatura...

Analise de testes em ambiente Windows

Fernando Antonio de Alemão Cisneiros
Fonte: Biblioteca Digital da Unicamp Publicador: Biblioteca Digital da Unicamp
Tipo: Dissertação de Mestrado Formato: application/pdf
Publicado em 16/12/1992 Português
Relevância na Pesquisa
57.216934%
Na última década ocorreram grandes avanços na técnica de interpretação de testes de pressão em poços e ao mesmo tempo uma expansão vertiginosa das facilidades de acesso a recursos computacionais através do advento dos microcomputadores. Nos últimos anos a popularização das interfaces gráficas para microcomputadores com o advento do Macintosh, do Windows e do OS/2, estão modificando fortemente a interação homem-máquina e abrindo novos horizontes para as tecnologias acentuadamente dependentes de recursos gráficos. A interpretação de testes de pressão em poços é sem dúvida uma tecnologia que se enquadra nesse perfil e a partir desta constatação, este trabalho propõe-se a definir e desenvolver um sistema profissional básico para análise de testes em ambiente gráfico. São definidos o modelo de dados e a especificação do sistema. As metodologias para análise em poços surgentes e não surgentes (DST) são implementadas incluindo métodos de análise especializada, análise por curva típica e análise automatizada. O desenvolvimento do sistema é feito utilizando um compilador C e o ambiente gráfico Windows; A considerable progress has occurred in well test interpretations techniques in the last decade. At the same time...

Geração automática de testes a partir de descrições de linguagens

Antunes, Cleverton Hentz
Fonte: Universidade Federal do Rio Grande do Norte; BR; UFRN; Programa de Pós-Graduação em Sistemas e Computação; Ciência da Computação Publicador: Universidade Federal do Rio Grande do Norte; BR; UFRN; Programa de Pós-Graduação em Sistemas e Computação; Ciência da Computação
Tipo: Dissertação Formato: application/pdf
Português
Relevância na Pesquisa
57.376973%
Some programs may have their entry data specified by formalized context-free grammars. This formalization facilitates the use of tools in the systematization and the rise of the quality of their test process. This category of programs, compilers have been the first to use this kind of tool for the automation of their tests. In this work we present an approach for definition of tests from the formal description of the entries of the program. The generation of the sentences is performed by taking into account syntactic aspects defined by the specification of the entries, the grammar. For optimization, their coverage criteria are used to limit the quantity of tests without diminishing their quality. Our approach uses these criteria to drive generation to produce sentences that satisfy a specific coverage criterion. The approach presented is based on the use of Lua language, relying heavily on its resources of coroutines and dynamic construction of functions. With these resources, we propose a simple and compact implementation that can be optimized and controlled in different ways, in order to seek satisfaction the different implemented coverage criteria. To make the use of our tool simpler, the EBNF notation for the specification of the entries was adopted. Its parser was specified in the tool Meta-Environment for rapid prototyping; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Alguns programas podem ter sua entrada formalizada através de gramáticas livres de contexto. Esta formalização facilita a utilização de ferramentas na sistematização e na elevação da qualidade do seu processo de teste. Dentro desta categoria de programas os compiladores foram os primeiros a utilizar este tipo de ferramenta para a automação de seus testes. Neste trabalho apresentamos uma abordagem para a definição de testes a partir da descrição formal das entradas do programa. A geração das sentenças é realizada levando em consideração aspectos sintáticos definidos pela especificação da entrada...

Geração de casos de teste a partir de especificações B

Souza, Fernanda Monteiro de
Fonte: Universidade Federal do Rio Grande do Norte; BR; UFRN; Programa de Pós-Graduação em Sistemas e Computação; Ciência da Computação Publicador: Universidade Federal do Rio Grande do Norte; BR; UFRN; Programa de Pós-Graduação em Sistemas e Computação; Ciência da Computação
Tipo: Dissertação Formato: application/pdf
Português
Relevância na Pesquisa
68.01515%
With the increasing complexity of software systems, there is also an increased concern about its faults. These faults can cause financial losses and even loss of life. Therefore, we propose in this paper the minimization of faults in software by using formally specified tests. The combination of testing and formal specifications is gaining strength in searches mainly through the MBT (Model-Based Testing). The development of software from formal specifications, when the whole process of refinement is done rigorously, ensures that what is specified in the application will be implemented. Thus, the implementation generated from these specifications would accurately depict what was specified. But not always the specification is refined to the level of implementation and code generation, and in these cases the tests generated from the specification tend to find fault. Additionally, the generation of so-called "invalid tests", ie tests that exercise the application scenarios that were not addressed in the specification, complements more significantly the formal development process. Therefore, this paper proposes a method for generating tests from B formal specifications. This method was structured in pseudo-code. The method is based on the systematization of the techniques of black box testing of boundary value analysis...

Joker: um realizador de desenhos animados para linguagens formais

Souza, Diego Henrique Oliveira de
Fonte: Universidade Federal do Rio Grande do Norte; BR; UFRN; Programa de Pós-Graduação em Sistemas e Computação; Ciência da Computação Publicador: Universidade Federal do Rio Grande do Norte; BR; UFRN; Programa de Pós-Graduação em Sistemas e Computação; Ciência da Computação
Tipo: Dissertação Formato: application/pdf
Português
Relevância na Pesquisa
57.361577%
Using formal methods, the developer can increase software s trustiness and correctness. Furthermore, the developer can concentrate in the functional requirements of the software. However, there are many resistance in adopting this software development approach. The main reason is the scarcity of adequate, easy to use, and useful tools. Developers typically write code and test it. These tests usually consist of executing the program and checking its output against its requirements. This, however, is not always an exhaustive discipline. On the other side, using formal methods one might be able to investigate the system s properties further. Unfortunately, specification languages do not always have tools like animators or simulators, and sometimes there are no friendly Graphical User Interfaces. On the other hand, specification languages usually have a compiler which normally generates a Labeled Transition System (LTS). This work proposes an application that provides graphical animation for formal specifications using the LTS as input. The application initially supports the languages B, CSP, and Z. However, using a LTS in a specified XML format, it is possible to animate further languages. Additionally, the tool provides traces visualization...

Beta: uma ferramenta para geração de testes de unidade a partir de especificações B

Matos, Ernesto Cid Brasil de
Fonte: Universidade Federal do Rio Grande do Norte; BR; UFRN; Programa de Pós-Graduação em Sistemas e Computação; Ciência da Computação Publicador: Universidade Federal do Rio Grande do Norte; BR; UFRN; Programa de Pós-Graduação em Sistemas e Computação; Ciência da Computação
Tipo: Dissertação Formato: application/pdf
Português
Relevância na Pesquisa
67.58918%
Formal methods and software testing are tools to obtain and control software quality. When used together, they provide mechanisms for software specification, verification and error detection. Even though formal methods allow software to be mathematically verified, they are not enough to assure that a system is free of faults, thus, software testing techniques are necessary to complement the process of verification and validation of a system. Model Based Testing techniques allow tests to be generated from other software artifacts such as specifications and abstract models. Using formal specifications as basis for test creation, we can generate better quality tests, because these specifications are usually precise and free of ambiguity. Fernanda Souza (2009) proposed a method to define test cases from B Method specifications. This method used information from the machine s invariant and the operation s precondition to define positive and negative test cases for an operation, using equivalent class partitioning and boundary value analysis based techniques. However, the method proposed in 2009 was not automated and had conceptual deficiencies like, for instance, it did not fit in a well defined coverage criteria classification. We started our work with a case study that applied the method in an example of B specification from the industry. Based in this case study we ve obtained subsidies to improve it. In our work we evolved the proposed method...

Uma estratégia para a avaliação e evolução de teste funcional de software; A Strategy for the evaluation and evolution of functional software testing

Arantes, Gilmar Ferreira
Fonte: Universidade Federal de Goiás; Brasil; UFG; Programa de Pós-graduação em Ciência da Computação (INF); Escola de Engenharia Elétrica, Mecânica e de Computação (EMC) - RG Publicador: Universidade Federal de Goiás; Brasil; UFG; Programa de Pós-graduação em Ciência da Computação (INF); Escola de Engenharia Elétrica, Mecânica e de Computação (EMC) - RG
Tipo: Dissertação Formato: application/pdf
Português
Relevância na Pesquisa
57.230737%
Software Testing is part of software quality assurance activities. It aims to uncover the presence of defects, that can be inserted in various stages of software develop- ment. Several techniques are used in the testing activity, highlighting the functional ones, which derive test requirements from the software specification. The research faces the problem of how to evolve the functional testing strategies with low costs, relative to the amount of test cases needed, without compromising the number of uncovered defects. A systematic review was planned and executed, based on formu- lated questions so as to answer the research problem. Such review supported the definition of a new criterion for functional testing, the Systematic Functional Test with Decision Table Application (TFS-DT), which is an extension of Systematic Software Testing (TFS) and provides joint application of criteria: Partitioning Equi- valence Classes, Boundary Value Analysis and Decision Table. The TFS-DT defines a strategy based on a set of requirements and has a process in order to apply the strategy in a systematic manner. Three empirical studies were applied with promi- sing results compared to TFS: all of them reduces at least half the adequated set without impact on the number of uncovered defects.; Fundação de Amparo à Pesquisa do Estado de Goiás - FAPEG; Teste de Software faz parte das atividades de garantia da qualidade do software. Destina-se a revelar a presen ̧ca de defeitos...

Contribuciones al análisis estocástico de la eficiencia técnica mediante métodos no paramétricos

Murillo Melchor, Carmen
Fonte: Universidad de Cantabria Publicador: Universidad de Cantabria
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
57.2312%
RESUMEN: La exposición de las contribuciones al análisis estocástico de la eficiencia técnica de este trabajo de investigación, requiere que: en el primer capítulo se definan los conceptos básicos para la comprensión de los capítulos dos y tres. Además y para la formulación de los problemas que han dado origen a este trabajo, se presenta también en este capítulo una breve revisión de las técnicas de estimación de la eficiencia técnica y de la productividad. Dentro de estas técnicas y debido a la gran flexibilidad funcional que proporciona, nos hemos centrado en la estimación no paramétrica y más en concreto en mejorar la inferencia estadística de sus estimaciones. Es por ello que el segundo de los aspectos que se trata es la inferencia estadística que se debería de efectuar en el análisis de la envolvente de datos, habitualmente denominado con el acrónimo DEA. El análisis estadístico es sistemáticamente "olvidado" en casi todos los trabajos que aplican esta técnica, y tal y como mostramos en este apartado, según se incorpore o no inferencia estadística al DEA la interpretación de los resultados es diferente. En el tercer apartado y continuando en la línea de mejorar las herramientas de inferencia estadística en el ámbito no paramétrico...

A new class of distribution-free tests for time series models specification

Delgado, Miguel A.; Velasco, Carlos
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: info:eu-repo/semantics/workingPaper; info:eu-repo/semantics/workingPaper Formato: text/plain; application/pdf; application/octet-stream; application/octet-stream; application/octet-stream
Publicado em /11/2007 Português
Relevância na Pesquisa
57.46652%
The construction of asymptotically distribution free time series model specification tests using as statistics the estimated residual autocorrelations is considered from a general view point. We focus our attention on Box-Pierce type tests based on the sum of squares of a few estimated residual autocorrelations. This type of tests belongs to the class defined by quadratic forms of weighted residual autocorrelations, where weights are suitably transformed resulting in asymptotically distribution free tests. The weights can be optimally chosen to maximize the power function when testing in the direction of local alternatives. The optimal test in this class against MA, AR or Bloomfield alternatives is a Box-Pierce type test based on the sum of squares of a few transformed residual autocorrelations. Such transformations are, in fact, the recursive residuals in the projection of the residual autocorrelations on a certain score function.

A new class of distribution-free tests for time series models specification

Delgado, Miguel A.; Velasco, Carlos
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: Trabalho em Andamento Formato: application/pdf
Publicado em /02/2009 Português
Relevância na Pesquisa
57.46652%
The construction of asymptotically distribution free time series model specification tests using as statistics the estimated residual autocorrelations is considered from a general view point. We focus our attention on Box-Pierce type tests based on the sum of squares of a few estimated residual autocorrelations. This type of tests belong to the class defined by quadratic forms of weighted residual autocorrelations, where weights are suitably transformed resulting in asymptotically distribution free tests. The weights can be optimally chosen to maximize the power function when testing in the direction of local alternatives. The optimal test in this class against MA, AR or Bloomfield alternatives is a Box-Pierce type test based on the sum of squares of a few transformed residual autocorrelations. Such transformations are, in fact, the recursive residuals in the projection of the residual autocorrelations on a certain score function.

Consistent specification testing of quantile regression models

Delgado, Miguel A.; Domínguez, Manuel A.
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: Trabalho em Andamento Formato: application/pdf
Publicado em /05/1997 Português
Relevância na Pesquisa
57.38311%
This paper introduces a specification testing procedure for quantile regression functions consistent in the direction of nonparametric alternatives. We consider test statistics based on a marked empirical process which does not require to estimate nonparametrically the true model. In general, the tests are not distribution free, but critical values can be consistentIy approximated using a residual based bootstrap. A small Monte Cario experiment shows that the test works fairly well in practice.

Specification, design and kinematic analysis of an electric toothbrush using CATIA® V5R19

Zurdo Martín, Lorena
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: info:eu-repo/semantics/bachelorThesis; info:eu-repo/semantics/masterThesis Formato: application/pdf; application/pdf
Português
Relevância na Pesquisa
67.020166%
Throughout of the present document, an electric toothbrush development will be explained. In the first place, the theoretical introductions about the system designed and its history are narrated along the Chapters 2and 3: Historical Development of Toothbrush and Explanation about basic mechanism. Besides, in the Chapter 4 is explained the basic concepts of the modules of CATIA® used Immediately, in the following pages (Chapter 5 and 6) are dedicated to describe the model, each and every one of its components and its characteristics. Moreover, it will explain the kinematic features for the model works correctly. When the Toothbrush is finished, start the stage of optimization and analysis. During this step, diverse studies have been made. On the one hand, the main objective is the optimization of Upper Brush rotational angle, because for a better brushing, this angle should be the maximum as possible. On the other hand, the model has been subjected to other studies: test of clashes, calculation of sweep volume of the mobile parts. Furthermore, it is necessary to analyze the behaviour of the gear along the movement transmission, and check the relation between the kinematic parts and the gears movement. In conclusion, the general objectives of this project are to know the operational mode of several modules from CATIA® V5 R19. In addition...

Three essays on specification testing

Xuexin, Wang
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: Tese de Doutorado Formato: application/pdf
Português
Relevância na Pesquisa
58.233423%
En el primer capítulo, “A General Approach to Conditional Moment Specification Testing with Projections”, se desarrolla un enfoque general para el análisis de especificación del modelo dentro del marco de pruebas de especificación de los momentos condicionales. A diferencia del paradigma de cálculos aproximados y pruebas desarrollado por Newey (1985a, b) y Tauchen (1985), la nueva metodología de estimación, teniendo como objetivo explorar la naturaleza de prueba de especificación de los momentos condicionales, elimina el efecto de estimación no despreciable a través de una transformación del estadístico de prueba basada en la proyección. Es decir, las restricciones de los momentos condicionales no sólo implican las limitaciones de los momentos no-condicionales que estamos examinando, sino también muchas otras más. Nuestro procedimiento incluye como un caso especial el estadístico modificado de Wooldridge (1990). Este enfoque es robusto a las desviaciones de las hipótesis de distribución que no hemos llegado a examinar, por otra parte sólo se necesita un preliminar estimador √T -consistente, y la transformación es asintóticamente libre d distribución. Además, el estadístico transformado alcanza la eficiencia asintótica en términos de la estimación GMM. Ponemos como un ejemplo...

Consideraciones a modo de guía a partir de estándares IEEE para calidad y buenas prácticas en desarrollo de software

Martínez de Morentín Góngora, Maria del Pilar
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: info:eu-repo/semantics/bachelorThesis; info:eu-repo/semantics/masterThesis Formato: application/pdf
Português
Relevância na Pesquisa
67.18833%
Mediante este proyecto a través de la selección de estándares (IEEE) tomados los más vigentes en las distintas fases de desarrollo del software como son: plan de aseguramiento de la calidad del software, especificación de requisitos, descripción de diseño del software, fundamentos de pruebas, se han unificado en una guía para que empresas u organizaciones puedan elevar el nivel de calidad, disminuir costes y aumentar la productividad, formando parte de la política y de los objetivos estratégicos de toda organización o empresa que tenga visión de futuro, dado que con ello se satisface al cliente, se generan beneficios. Esta guía proporciona a empresas u organizaciones que desean desarrollar productos o servicios de calidad una estructura adecuada, desde que el cliente piensa en lo que desea es calidad, hasta la entrega del producto o servicio es calidad. Por ello, su previsión fundamental debe ser la de proveer productos o servicios o realizar actividades, que satisfagan las necesidades expresadas e implícitas de los clientes todo ello al menor coste posible. El despliegue de la función de la calidad es un proceso estructurado y riguroso capaz de identificar y transmitir la voz del cliente para transformarla en requisitos del producto o servicio...

Specification and casualty of distribution models

Troster, Víctor Emilio
Fonte: Universidade Carlos III de Madrid Publicador: Universidade Carlos III de Madrid
Tipo: Tese de Doutorado
Português
Relevância na Pesquisa
58.010107%
Many important economic and finance hypotheses are investigated through testing the specification of restrictions on the conditional distribution of a time series, such as conditional goodness-of- t (Box and Pierce (1970)), conditional quantiles (Koenker and Machado (1999)), and distributional Granger non-causality (Taamouti, Bouezmarni, and El Ghouch, 2014). This PhD Thesis contributes to the study of specification and causality tests that provide a more flexible and detailed approach to evaluate economic relationships, which are useful in many relevant empirical applications. In the first chapter, we propose a practical and consistent specification test of conditional distribution models for dependent data in a very general setting. Our approach covers conditional distribution models possibly indexed by function-valued parameters, which allows for a wide range of important empirical applications, such as the linear quantile auto-regressive, the CAViaR, and the distributional regression models. Our test statistic is based on a comparison between the estimated parametric and the empirical distribution functions. The new specification test (i) is valid for general linear and nonlinear dynamic models under parameter estimation error...

Testing Mean-Variance Efficiency in CAPM with Possibly Non-Gaussian Errors : An Exact Simulation-Based Approach

BEAULIEU, Marie-Claude; DUFOUR, Jean-Marie; KHALAF, Lynda
Fonte: Université de Montréal Publicador: Université de Montréal
Tipo: Artigo de Revista Científica Formato: 400691 bytes; application/pdf
Português
Relevância na Pesquisa
57.65593%
In this paper we propose exact likelihood-based mean-variance efficiency tests of the market portfolio in the context of Capital Asset Pricing Model (CAPM), allowing for a wide class of error distributions which include normality as a special case. These tests are developed in the frame-work of multivariate linear regressions (MLR). It is well known however that despite their simple statistical structure, standard asymptotically justified MLR-based tests are unreliable. In financial econometrics, exact tests have been proposed for a few specific hypotheses [Jobson and Korkie (Journal of Financial Economics, 1982), MacKinlay (Journal of Financial Economics, 1987), Gib-bons, Ross and Shanken (Econometrica, 1989), Zhou (Journal of Finance 1993)], most of which depend on normality. For the gaussian model, our tests correspond to Gibbons, Ross and Shanken’s mean-variance efficiency tests. In non-gaussian contexts, we reconsider mean-variance efficiency tests allowing for multivariate Student-t and gaussian mixture errors. Our framework allows to cast more evidence on whether the normality assumption is too restrictive when testing the CAPM. We also propose exact multivariate diagnostic checks (including tests for multivariate GARCH and mul-tivariate generalization of the well known variance ratio tests) and goodness of fit tests as well as a set estimate for the intervening nuisance parameters. Our results [over five-year subperiods] show the following: (i) multivariate normality is rejected in most subperiods...

Finite-Sample Diagnostics for Multivariate Regressions with Applications to Linear Asset Pricing Models

DUFOUR, Jean-Marie; KHALAF, Lynda; BEAULIEU, Marie-Claude
Fonte: Université de Montréal Publicador: Université de Montréal
Tipo: Artigo de Revista Científica Formato: 219916 bytes; application/pdf
Português
Relevância na Pesquisa
68.12541%
In this paper, we propose several finite-sample specification tests for multivariate linear regressions (MLR) with applications to asset pricing models. We focus on departures from the assumption of i.i.d. errors assumption, at univariate and multivariate levels, with Gaussian and non-Gaussian (including Student t) errors. The univariate tests studied extend existing exact procedures by allowing for unspecified parameters in the error distributions (e.g., the degrees of freedom in the case of the Student t distribution). The multivariate tests are based on properly standardized multivariate residuals to ensure invariance to MLR coefficients and error covariances. We consider tests for serial correlation, tests for multivariate GARCH and sign-type tests against general dependencies and asymmetries. The procedures proposed provide exact versions of those applied in Shanken (1990) which consist in combining univariate specification tests. Specifically, we combine tests across equations using the MC test procedure to avoid Bonferroni-type bounds. Since non-Gaussian based tests are not pivotal, we apply the “maximized MC” (MMC) test method [Dufour (2002)], where the MC p-value for the tested hypothesis (which depends on nuisance parameters) is maximized (with respect to these nuisance parameters) to control the test’s significance level. The tests proposed are applied to an asset pricing model with observable risk-free rates...

Exact Skewness-Kurtosis Tests for Multivariate Normality and Goodness-of-fit in Multivariate Regressions with Application to Asset Pricing Models

DUFOUR, Jean-Marie; KHALAF, Lynda; BEAULIEU, Marie-Claude
Fonte: Université de Montréal Publicador: Université de Montréal
Tipo: Artigo de Revista Científica Formato: 225374 bytes; application/pdf
Português
Relevância na Pesquisa
57.681943%
We study the problem of testing the error distribution in a multivariate linear regression (MLR) model. The tests are functions of appropriately standardized multivariate least squares residuals whose distribution is invariant to the unknown cross-equation error covariance matrix. Empirical multivariate skewness and kurtosis criteria are then compared to simulation-based estimate of their expected value under the hypothesized distribution. Special cases considered include testing multivariate normal, Student t; normal mixtures and stable error models. In the Gaussian case, finite-sample versions of the standard multivariate skewness and kurtosis tests are derived. To do this, we exploit simple, double and multi-stage Monte Carlo test methods. For non-Gaussian distribution families involving nuisance parameters, confidence sets are derived for the the nuisance parameters and the error distribution. The procedures considered are evaluated in a small simulation experi-ment. Finally, the tests are applied to an asset pricing model with observable risk-free rates, using monthly returns on New York Stock Exchange (NYSE) portfolios over five-year subperiods from 1926-1995.; Dans cet article, nous proposons des tests sur la forme de la distribution des erreurs dans un modèle de régression linéaire multivarié (RLM). Les tests que nous développons sont fonction des résidus obtenus par moindres carrés multivariés...

Exact Tests for Contemporaneous Correlation of Disturbances in Seemingly Unrelated Regressions.

DUFOUR, Jean-Marie; KHALAF, Lynda
Fonte: Université de Montréal Publicador: Université de Montréal
Tipo: Artigo de Revista Científica Formato: 425709 bytes; application/pdf
Português
Relevância na Pesquisa
58.02588%
This paper proposes finite-sample procedures for testing the SURE specification in multi-equation regression models, i.e. whether the disturbances in different equations are contemporaneously uncorrelated or not. We apply the technique of Monte Carlo (MC) tests [Dwass (1957), Barnard (1963)] to obtain exact tests based on standard LR and LM zero correlation tests. We also suggest a MC quasi-LR (QLR) test based on feasible generalized least squares (FGLS). We show that the latter statistics are pivotal under the null, which provides the justification for applying MC tests. Furthermore, we extend the exact independence test proposed by Harvey and Phillips (1982) to the multi-equation framework. Specifically, we introduce several induced tests based on a set of simultaneous Harvey/Phillips-type tests and suggest a simulation-based solution to the associated combination problem. The properties of the proposed tests are studied in a Monte Carlo experiment which shows that standard asymptotic tests exhibit important size distortions, while MC tests achieve complete size control and display good power. Moreover, MC-QLR tests performed best in terms of power, a result of interest from the point of view of simulation-based tests. The power of the MC induced tests improves appreciably in comparison to standard Bonferroni tests and...

Simulation-Based Finite-Sample Tests for Heteroskedasticity and ARCH Effects.

DUFOUR, Jean-Marie; KHALAF, Lynda; BERNARD, Jean-Thomas; GENEST, Ian
Fonte: Université de Montréal Publicador: Université de Montréal
Tipo: Artigo de Revista Científica Formato: 342447 bytes; application/pdf
Português
Relevância na Pesquisa
57.70767%
A wide range of tests for heteroskedasticity have been proposed in the econometric and statistics literature. Although a few exact homoskedasticity tests are available, the commonly employed procedures are quite generally based on asymptotic approximations which may not provide good size control in finite samples. There has been a number of recent studies that seek to improve the reliability of common heteroskedasticity tests using Edgeworth, Bartlett, jackknife and bootstrap methods. Yet the latter remain approximate. In this paper, we describe a solution to the problem of controlling the size of homoskedasticity tests in linear regression contexts. We study procedures based on the standard test statistics [e.g., the Goldfeld-Quandt, Glejser, Bartlett, Cochran, Hartley, Breusch-Pagan-Godfrey, White and Szroeter criteria] as well as tests for autoregressive conditional heteroskedasticity (ARCH-type models). We also suggest several extensions of the existing procedures (sup-type of combined test statistics) to allow for unknown breakpoints in the error variance. We exploit the technique of Monte Carlo tests to obtain provably exact p-values, for both the standard and the new tests suggested. We show that the MC test procedure conveniently solves the intractable null distribution problem...