A Diagnostic Test for the Mixing Distribution in a Generalised Linear Mixed Model

We introduce a diagnostic test for the mixing distribution in a generalised linear mixed model. The test is based on the difference between the marginal maximum likelihood and conditional maximum likelihood estimates of a subset of the fixed effects in the model. We derive the asymptotic variance of this difference, and propose a test statistic that has a limiting chi-square distribution under the null hypothesis that the mixing distribution is correctly specified. For the important special case of the logistic regression model with random intercepts, we evaluate via simulation the power of the test in finite samples under several alternative distributional forms for the mixing distribution. We illustrate the method by applying it to data from a clinical trial investigating the effects of hormonal contraceptives in women.

UML approach to the generation of test sequences for Java-based concurrent systems

Starting with a UML specification that captures the underlying functionality of some given Java-based concurrent system, we describe a systematic way to construct, from this specification, test sequences for validating an implementation of the system. The approach is to first extend the specification to create UML state machines that directly address those aspects of the system we wish to test. To be specific, the extended UML state machines can capture state information about the number of waiting threads or the number of threads blocked on a given object. Using the SAL model checker we can generate from the extended UML state machines sequences that cover all the various possibilities of events and states. These sequences can then be directly transformed into test sequences suitable for input into a testing tool such as ConAn. As an illustration, the methodology is applied to generate sequences for testing a Java implementation of the producer-consumer system. © 2005 IEEE

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

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, in certain cases, outperforms the likelihood-based MC tests. The tests are applied to data used by Fischer (1993) to analyze the macroeconomic determinants of growth.

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

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, in particular those raised by the sup-type and combined test statistics as well as (when relevant) unidentified nuisance parameter problems under the null hypothesis. The method proposed works in exactly the same way with both Gaussian and non-Gaussian disturbance distributions [such as heavy-tailed or stable distributions]. The performance of the procedures is examined by simulation. The Monte Carlo experiments conducted focus on : (1) ARCH, GARCH, and ARCH-in-mean alternatives; (2) the case where the variance increases monotonically with : (i) one exogenous variable, and (ii) the mean of the dependent variable; (3) grouped heteroskedasticity; (4) breaks in variance at unknown points. We find that the proposed tests achieve perfect size control and have good power.

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

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, (ii) residual checks reveal no significant departures from the multivariate i.i.d. assumption, and (iii) mean-variance efficiency tests of the market portfolio is not rejected as frequently once it is allowed for the possibility of non-normal errors.

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

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, using monthly returns on New York Stock Exchange (NYSE) portfolios over five-year subperiods from 1926-1995. Our empirical results reveal the following. Whereas univariate exact tests indicate significant serial correlation, asymmetries and GARCH in some equations, such effects are much less prevalent once error cross-equation covariances are accounted for. In addition, significant departures from the i.i.d. hypothesis are less evident once we allow for non-Gaussian errors.

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

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.

Exact Multivariate Tests of Asset Pricing Models with Stable Asymmetric Distributions

In this paper, we propose exact inference procedures for asset pricing models that can be formulated in the framework of a multivariate linear regression (CAPM), allowing for stable error distributions. The normality assumption on the distribution of stock returns is usually rejected in empirical studies, due to excess kurtosis and asymmetry. To model such data, we propose a comprehensive statistical approach which allows for alternative - possibly asymmetric - heavy tailed distributions without the use of large-sample approximations. The methods suggested are based on Monte Carlo test techniques. Goodness-of-fit tests are formally incorporated to ensure that the error distributions considered are empirically sustainable, from which exact confidence sets for the unknown tail area and asymmetry parameters of the stable error distribution are derived. Tests for the efficiency of the market portfolio (zero intercepts) which explicitly allow for the presence of (unknown) nuisance parameter in the stable error distribution are derived. The methods proposed are applied to monthly returns on 12 portfolios of the New York Stock Exchange over the period 1926-1995 (5 year subperiods). We find that stable possibly skewed distributions provide statistically significant improvement in goodness-of-fit and lead to fewer rejections of the efficiency hypothesis.

Aplicação de modelos de defeitos na geração de conjuntos de teste completos a partir de Sistemas de Transição com Entrada/Saída

O Teste Baseado em Modelos (TBM) emergiu como uma estratégia promissora para minimizar problemas relacionados à falta de tempo e recursos em teste de software e visa verificar se a implementação sob teste está em conformidade com sua especificação. Casos de teste são gerados automaticamente a partir de modelos comportamentais produzidos durante o ciclo de desenvolvimento de software. Entre as técnicas de modelagem existentes, Sistemas de Transição com Entrada/Saída (do inglês, Input/Output Transition Systems - IOTSs), são modelos amplamente utilizados no TBM por serem mais expressivos do que Máquinas de Estado Finito (MEFs). Apesar dos métodos existentes para geração de testes a partir de IOTSs, o problema da seleção de casos de testes é um tópico difícil e importante. Os métodos existentes para IOTS são não-determinísticos, ao contrário da teoria existente para MEFs, que fornece garantia de cobertura completa com base em um modelo de defeitos. Esta tese investiga a aplicação de modelos de defeitos em métodos determinísticos de geração de testes a partir de IOTSs. Foi proposto um método para geração de conjuntos de teste com base no método W para MEFs. O método gera conjuntos de teste de forma determinística além de satisfazer condições de suficiência de cobertura da especificação e de todos os defeitos do domínio de defeitos definido. Estudos empíricos avaliaram a aplicabilidade e eficácia do método proposto: resultados experimentais para analisar o custo de geração de conjuntos de teste utilizando IOTSs gerados aleatoriamente e um estudo de caso com especificações da indústria mostram a efetividade dos conjuntos gerados em relação ao método tradicional de Tretmans.

Open Specification for BIM : Sydney Opera House Case Study

Executive Summary The objective of this report was to use the Sydney Opera House as a case study of the application of Building Information Modelling (BIM). The Sydney opera House is a complex, large building with very irregular building configuration, that makes it a challenging test. A number of key concerns are evident at SOH: • the building structure is complex, and building service systems - already the major cost of ongoing maintenance - are undergoing technology change, with new computer based services becoming increasingly important. • the current “documentation” of the facility is comprised of several independent systems, some overlapping and is inadequate to service current and future services required • the building has reached a milestone age in terms of the condition and maintainability of key public areas and service systems, functionality of spaces and longer term strategic management. • many business functions such as space or event management require up-to-date information of the facility that are currently inadequately delivered, expensive and time consuming to update and deliver to customers. • major building upgrades are being planned that will put considerable strain on existing Facilities Portfolio services, and their capacity to manage them effectively While some of these concerns are unique to the House, many will be common to larger commercial and institutional portfolios. The work described here supported a complementary task which sought to identify if a building information model – an integrated building database – could be created, that would support asset & facility management functions (see Sydney Opera House – FM Exemplar Project, Report Number: 2005-001-C-4 Building Information Modelling for FM at Sydney Opera House), a business strategy that has been well demonstrated. The development of the BIMSS - Open Specification for BIM has been surprisingly straightforward. The lack of technical difficulties in converting the House’s existing conventions and standards to the new model based environment can be related to three key factors: • SOH Facilities Portfolio – the internal group responsible for asset and facility management - have already well established building and documentation policies in place. The setting and adherence to well thought out operational standards has been based on the need to create an environment that is understood by all users and that addresses the major business needs of the House. • The second factor is the nature of the IFC Model Specification used to define the BIM protocol. The IFC standard is based on building practice and nomenclature, widely used in the construction industries across the globe. For example the nomenclature of building parts – eg ifcWall, corresponds to our normal terminology, but extends the traditional drawing environment currently used for design and documentation. This demonstrates that the international IFC model accurately represents local practice for building data representation and management. • a BIM environment sets up opportunities for innovative processes that can exploit the rich data in the model and improve services and functions for the House: for example several high-level processes have been identified that could benefit from standardized Building Information Models such as maintenance processes using engineering data, business processes using scheduling, venue access, security data and benchmarking processes using building performance data. The new technology matches business needs for current and new services. The adoption of IFC compliant applications opens the way forward for shared building model collaboration and new processes, a significant new focus of the BIM standards. In summary, SOH current building standards have been successfully drafted for a BIM environment and are confidently expected to be fully developed when BIM is adopted operationally by SOH. These BIM standards and their application to the Opera House are intended as a template for other organisations to adopt for the own procurement and facility management activities. Appendices provide an overview of the IFC Integrated Object Model and an understanding IFC Model Data.

Test and evaluation system for multi-protocol sampled value protection schemes

Proposed transmission smart grids will use a digital platform for the automation of substations operating at voltage levels of 110 kV and above. The IEC 61850 series of standards, released in parts over the last ten years, provide a specification for substation communications networks and systems. These standards, along with IEEE Std 1588-2008 Precision Time Protocol version 2 (PTPv2) for precision timing, are recommended by the both IEC Smart Grid Strategy Group and the NIST Framework and Roadmap for Smart Grid Interoperability Standards for substation automation. IEC 61850-8-1 and IEC 61850-9-2 provide an inter-operable solution to support multi-vendor digital process bus solutions, allowing for the removal of potentially lethal voltages and damaging currents from substation control rooms, a reduction in the amount of cabling required in substations, and facilitates the adoption of non-conventional instrument transformers (NCITs). IEC 61850, PTPv2 and Ethernet are three complementary protocol families that together define the future of sampled value digital process connections for smart substation automation. This paper describes a specific test and evaluation system that uses real time simulation, protection relays, PTPv2 time clocks and artificial network impairment that is being used to investigate technical impediments to the adoption of SV process bus systems by transmission utilities. Knowing the limits of a digital process bus, especially when sampled values and NCITs are included, will enable utilities to make informed decisions regarding the adoption of this technology.

Econometric Modelling with Time Series : Specification, Estimation and Testing

This book provides a general framework for specifying, estimating, and testing time series econometric models. Special emphasis is given to estimation by maximum likelihood, but other methods are also discussed, including quasi-maximum likelihood estimation, generalized method of moments estimation, nonparametric estimation, and estimation by simulation. An important advantage of adopting the principle of maximum likelihood as the unifying framework for the book is that many of the estimators and test statistics proposed in econometrics can be derived within a likelihood framework, thereby providing a coherent vehicle for understanding their properties and interrelationships. In contrast to many existing econometric textbooks, which deal mainly with the theoretical properties of estimators and test statistics through a theorem-proof presentation, this book squarely addresses implementation to provide direct conduits between the theory and applied work.

Computing complete test graphs for hierarchical systems

Conformance testing focuses on checking whether an implementation. under test (IUT) behaves according to its specification. Typically, testers are interested it? performing targeted tests that exercise certain features of the IUT This intention is formalized as a test purpose. The tester needs a "strategy" to reach the goal specified by the test purpose. Also, for a particular test case, the strategy should tell the tester whether the IUT has passed, failed. or deviated front the test purpose. In [8] Jeron and Morel show how to compute, for a given finite state machine specification and a test purpose automaton, a complete test graph (CTG) which represents all test strategies. In this paper; we consider the case when the specification is a hierarchical state machine and show how to compute a hierarchical CTG which preserves the hierarchical structure of the specification. We also propose an algorithm for an online test oracle which avoids a space overhead associated with the CTG.

Bootstrapping the Error Correction Model Cointegration Test

This paper is concerned with using the bootstrap to obtain improved critical values for the error correction model (ECM) cointegration test in dynamic models. In the paper we investigate the effects of dynamic specification on the size and power of the ECM cointegration test with bootstrap critical values. The results from a Monte Carlo study show that the size of the bootstrap ECM cointegration test is close to the nominal significance level. We find that overspecification of the lag length results in a loss of power. Underspecification of the lag length results in size distortion. The performance of the bootstrap ECM cointegration test deteriorates if the correct lag length is not used in the ECM. The bootstrap ECM cointegration test is therefore not robust to model misspecification.

Specification Based Regression Testing Using Explicit State Space Enumeration

This paper presents a method of partial automation of specification based regression testing, which we call ESSE (Explicit State Space Enumeration). The first step in ESSE method is the extraction of a finite state model of the system making use of an already tested version of the system under test (SUT). Thereafter, the finite state model thus obtained is used to compute good test sequences that can be used to regression test subsequent versions of the system. We present two new algorithms for test sequence computation - both based on our finite state model generated by the above method. We also provide the details and results of the experimental evaluation of ESSE method. Comparison with a practically used random-testing algorithm has shown substantial improvements.