Framework for Skew-Probit Links in Binary Regression

We review several asymmetrical links for binary regression models and present a unified approach for two skew-probit links proposed in the literature. Moreover, under skew-probit link, conditions for the existence of the ML estimators and the posterior distribution under improper priors are established. The framework proposed here considers two sets of latent variables which are helpful to implement the Bayesian MCMC approach. A simulation study to criteria for models comparison is conducted and two applications are made. Using different Bayesian criteria we show that, for these data sets, the skew-probit links are better than alternative links proposed in the literature.

Regression analysis of mean quality-adjusted survival time based on pseudo-observations

Regression models for the mean quality-adjusted survival time are specified from hazard functions of transitions between two states and the mean quality-adjusted survival time may be a complex function of covariates. We discuss a regression model for the mean quality-adjusted survival (QAS) time based on pseudo-observations, which has the advantage of directly modeling the effect of covariates in the QAS time. Both Monte Carlo Simulations and a real data set are studied. Copyright (C) 2009 John Wiley & Sons, Ltd.

A new class of survival regression models with heavy-tailed errors: robustness and diagnostics

Birnbaum-Saunders models have largely been applied in material fatigue studies and reliability analyses to relate the total time until failure with some type of cumulative damage. In many problems related to the medical field, such as chronic cardiac diseases and different types of cancer, a cumulative damage caused by several risk factors might cause some degradation that leads to a fatigue process. In these cases, BS models can be suitable for describing the propagation lifetime. However, since the cumulative damage is assumed to be normally distributed in the BS distribution, the parameter estimates from this model can be sensitive to outlying observations. In order to attenuate this influence, we present in this paper BS models, in which a Student-t distribution is assumed to explain the cumulative damage. In particular, we show that the maximum likelihood estimates of the Student-t log-BS models attribute smaller weights to outlying observations, which produce robust parameter estimates. Also, some inferential results are presented. In addition, based on local influence and deviance component and martingale-type residuals, a diagnostics analysis is derived. Finally, a motivating example from the medical field is analyzed using log-BS regression models. Since the parameter estimates appear to be very sensitive to outlying and influential observations, the Student-t log-BS regression model should attenuate such influences. The model checking methodologies developed in this paper are used to compare the fitted models.

Covariance matrix formula for Birnbaum-Saunders regression models

The Birnbaum-Saunders regression model is commonly used in reliability studies. We derive a simple matrix formula for second-order covariances of maximum-likelihood estimators in this class of models. The formula is quite suitable for computer implementation, since it involves only simple operations on matrices and vectors. Some simulation results show that the second-order covariances can be quite pronounced in small to moderate sample sizes. We also present empirical applications.

Some restriction tests in a new class of regression models for proportions

The main purpose of this work is to study the behaviour of Skovgaard`s [Skovgaard, I.M., 2001. Likelihood asymptotics. Scandinavian journal of Statistics 28, 3-32] adjusted likelihood ratio statistic in testing simple hypothesis in a new class of regression models proposed here. The proposed class of regression models considers Dirichlet distributed observations, and the parameters that index the Dirichlet distributions are related to covariates and unknown regression coefficients. This class is useful for modelling data consisting of multivariate positive observations summing to one and generalizes the beta regression model described in Vasconcellos and Cribari-Neto [Vasconcellos, K.L.P., Cribari-Neto, F., 2005. Improved maximum likelihood estimation in a new class of beta regression models. Brazilian journal of Probability and Statistics 19,13-31]. We show that, for our model, Skovgaard`s adjusted likelihood ratio statistics have a simple compact form that can be easily implemented in standard statistical software. The adjusted statistic is approximately chi-squared distributed with a high degree of accuracy. Some numerical simulations show that the modified test is more reliable in finite samples than the usual likelihood ratio procedure. An empirical application is also presented and discussed. (C) 2009 Elsevier B.V. All rights reserved.

Birnbaum-Saunders nonlinear regression models

We introduce, for the first time, a new class of Birnbaum-Saunders nonlinear regression models potentially useful in lifetime data analysis. The class generalizes the regression model described by Rieck and Nedelman [Rieck, J.R., Nedelman, J.R., 1991. A log-linear model for the Birnbaum-Saunders distribution. Technometrics 33, 51-60]. We discuss maximum-likelihood estimation for the parameters of the model, and derive closed-form expressions for the second-order biases of these estimates. Our formulae are easily computed as ordinary linear regressions and are then used to define bias corrected maximum-likelihood estimates. Some simulation results show that the bias correction scheme yields nearly unbiased estimates without increasing the mean squared errors. Two empirical applications are analysed and discussed. Crown Copyright (C) 2009 Published by Elsevier B.V. All rights reserved.

An Analysis of the Telecommunications Business in China by Linear Regression

In this paper, we study the influence of the National Telecom Business Volume by the data in 2008 that have been published in China Statistical Yearbook of Statistics. We illustrate the procedure of modeling “National Telecom Business Volume” on the following eight variables, GDP, Consumption Levels, Retail Sales of Social Consumer Goods Total Renovation Investment, the Local Telephone Exchange Capacity, Mobile Telephone Exchange Capacity, Mobile Phone End Users, and the Local Telephone End Users. The testing of heteroscedasticity and multicollinearity for model evaluation is included. We also consider AIC and BIC criterion to select independent variables, and conclude the result of the factors which are the optimal regression model for the amount of telecommunications business and the relation between independent variables and dependent variable. Based on the final results, we propose several recommendations about how to improve telecommunication services and promote the economic development.

Defining Relevant Product Markets for Pharmaceuticals

To identify the relevant product markets for Swedish pharmaceuticals, a spatial econometrics approach is employed. First, we calculate Moran’s Is for different market definitions and then we use a spatial Durbin model to determine the effect of price changes on quantity sold off own and competing products. As expected, the results show that competition is strongest between close substitutes; however, the relevant product markets for Swedish pharmaceuticals extend beyond close substitutes down to products included in the same class on the four-digit level of the Anatomic Therapeutic Chemical system as defined by the World Health Organization. The spatial regression model further indicates that increases in the price of a product significantly lower the quantity sold of that product and in the same time increase the quantity sold of competing products. For close substitutes (products belonging to the same class on the seven-digit level of the Anatomic Therapeutic Chemical system), as well as for products that, without being close substitutes, belong to the same therapeutic/pharmacological/chemical subgroup (the same class on the five-digit level of the Anatomic Therapeutic Chemical system), a significant change towards increased competition is also visible after 1 July 2009 when the latest policy changes with regards to pharmaceuticals have been implemented in Sweden.

Computerized identification of motor complications in Parkinson's disease

Objective: To investigate whether spirography-based objective measures are able to effectively characterize the severity of unwanted symptom states (Off and dyskinesia) and discriminate them from motor state of healthy elderly subjects. Background: Sixty-five patients with advanced Parkinson’s disease (PD) and 10 healthy elderly (HE) subjects performed repeated assessments of spirography, using a touch screen telemetry device in their home environments. On inclusion, the patients were either treated with levodopa-carbidopa intestinal gel or were candidates for switching to this treatment. On each test occasion, the subjects were asked trace a pre-drawn Archimedes spiral shown on the screen, using an ergonomic pen stylus. The test was repeated three times and was performed using dominant hand. A clinician used a web interface which animated the spiral drawings, allowing him to observe different kinematic features, like accelerations and spatial changes, during the drawing process and to rate different motor impairments. Initially, the motor impairments of drawing speed, irregularity and hesitation were rated on a 0 (normal) to 4 (extremely severe) scales followed by marking the momentary motor state of the patient into 2 categories that is Off and Dyskinesia. A sample of spirals drawn by HE subjects was randomly selected and used in subsequent analysis. Methods: The raw spiral data, consisting of stylus position and timestamp, were processed using time series analysis techniques like discrete wavelet transform, approximate entropy and dynamic time warping in order to extract 13 quantitative measures for representing meaningful motor impairment information. A principal component analysis (PCA) was used to reduce the dimensions of the quantitative measures into 4 principal components (PC). In order to classify the motor states into 3 categories that is Off, HE and dyskinesia, a logistic regression model was used as a classifier to map the 4 PCs to the corresponding clinically assigned motor state categories. A stratified 10-fold cross-validation (also known as rotation estimation) was applied to assess the generalization ability of the logistic regression classifier to future independent data sets. To investigate mean differences of the 4 PCs across the three categories, a one-way ANOVA test followed by Tukey multiple comparisons was used. Results: The agreements between computed and clinician ratings were very good with a weighted area under the receiver operating characteristic curve (AUC) coefficient of 0.91. The mean PC scores were different across the three motor state categories, only at different levels. The first 2 PCs were good at discriminating between the motor states whereas the PC3 was good at discriminating between HE subjects and PD patients. The mean scores of PC4 showed a trend across the three states but without significant differences. The Spearman’s rank correlations between the first 2 PCs and clinically assessed motor impairments were as follows: drawing speed (PC1, 0.34; PC2, 0.83), irregularity (PC1, 0.17; PC2, 0.17), and hesitation (PC1, 0.27; PC2, 0.77). Conclusions: These findings suggest that spirography-based objective measures are valid measures of spatial- and time-dependent deficits and can be used to distinguish drug-related motor dysfunctions between Off and dyskinesia in PD. These measures can be potentially useful during clinical evaluation of individualized drug-related complications such as over- and under-medications thus maximizing the amount of time the patients spend in the On state.

Indicadores de renda baseados em consumo de energia elétrica: abordagens domiciliar e regional na perspectiva da estatística espacial

Com o objetivo de avaliar o uso do consumo de energia elétrica como indicador socioeconômico, esta pesquisa analisa informações em dois níveis de agregação geográfica. No primeiro, sob perspectiva territorial, investiga indicadores de Renda e Consumo de Energia Elétrica agregados por áreas de ponderação (conjunto de setores censitários) do município de São Paulo e utiliza os microdados do Censo Demográfico 2000 em conjunto com a base de domicílios da AES Eletropaulo. Aplica modelos de Spatial Auto-Regression (SAR), Geographically Weighted Regression (GWR), e um modelo inédito combinado (GWR+SAR), desenvolvido neste estudo. Diversas matrizes de vizinhança foram utilizadas na avaliação da influência espacial (com padrão Centro-Periferia) das variáveis em estudo. As variáveis mostraram forte auto-correlação espacial (I de Moran superior a 58% para o Consumo de Energia Elétrica e superior a 75% para a Renda Domiciliar). As relações entre Renda e Consumo de Energia Elétrica mostraram-se muito fortes (os coeficientes de explicação da Renda atingiram valores de 0,93 a 0,98). No segundo nível, domiciliar, utiliza dados coletados na Pesquisa Anual de Satisfação do Cliente Residencial, coordenada pela Associação Brasileira dos Distribuidores de Energia Elétrica (ABRADEE), para os anos de 2004, 2006, 2007, 2008 e 2009. Foram aplicados os modelos Weighted Linear Model (WLM), GWR e SAR para os dados das pesquisas com as entrevistas alocadas no centróide e na sede dos distritos. Para o ano de 2009, foram obtidas as localizações reais dos domicílios entrevistados. Adicionalmente, foram desenvolvidos 6 algoritmos de distribuição de pontos no interior dos polígonos dos distritos. Os resultados dos modelos baseados em centróides e sedes obtiveram um coeficiente de determinação R2 em torno de 0,45 para a técnica GWR, enquanto os modelos baseados no espalhamento de pontos no interior dos polígonos dos distritos reduziram essa explicação para cerca de 0,40. Esses resultados sugerem que os algoritmos de alocação de pontos em polígonos permitem a observação de uma associação mais realística entre os construtos analisados. O uso combinado dos achados demonstra que as informações de faturamento das distribuidoras de energia elétrica têm grande potencial para apoiar decisões estratégicas. Por serem atuais, disponíveis e de atualização mensal, os indicadores socioeconômicos baseados em consumo de energia elétrica podem ser de grande utilidade como subsídio a processos de classificação, concentração e previsão da renda domiciliar.

Impacto dos investimentos em tecnologia de informação no desempenho financeiro das indústrias brasileiras

Os resultados obtidos possibilitam afirmar que as indústrias que mais investiram em Tecnologia de Informação (TI), no período de 2001 a 2011, obtiveram maior crescimento da sua receita operacional e resultados operacionais mais eficazes, comparadas com as indústrias que investiram menos no período. De acordo com o modelo proposto, para as empresas estudadas foi possível encontrar, no prazo de dois anos, um crescimento de 7% no resultado operacional para cada 1% a mais de investimentos em TI. Destaca-se o objetivo da pesquisa de identificar e analisar os impactos dos gastos e investimentos em tecnologia de informação no desempenho financeiro das indústrias brasileiras, para alcançá-lo, adotou-se um modelo de pesquisa que utilizou métricas contábeis-financeiras e indicadores de uso TI, bem como a combinação de técnicas estatísticas para as análises. O trabalho aprofunda e amplia as discussões existentes sobre a avaliação dos investimentos em TI e como aferir o impacto desta sobre o desempenho organizacional. O universo do estudo foi composto pelas companhias brasileiras, de capital aberto, do ramo industrial, com ações ativas na BOVESPA, totalizando 119 companhias. Por meio de uma survey obteve-se os dados complementares referentes aos gastos e investimentos em TI; os questionários semiestruturados foram encaminhados diretamente ao Gerente de TI (Chief Information Officer). Estes esforços na coleta de dados primários possibilitaram a obtenção de uma amostra bastante significativa, com 63 indústrias, ou seja, 53% da população estudada. Após coleta, a análise dos dados foi desenvolvida em três etapas: (1) Análise Fatorial (AF) para seleção de fatores de desempenho que resultou no final do processo em doze variáveis para o modelo da pesquisa; (2) Análise de Cluster (AC) que evidenciou três agrupamentos distintos de indústrias por suas características e desempenho e (3) Regressão Múltipla que adotou um modelo econométrico dinâmico, estimado pelo Método dos Momentos Generalizado (GMM), satisfazendo as condições do modelo de Arellano-Bond (1991). Salienta-se que o modelo proposto permitiu tratar de forma adequada metodologicamente as correlações espúrias, possibilitando identificar que os gastos e investimentos em TI, (IGTI t-2), de dois períodos anteriores impactaram no Resultado Operacional Atual, (ROPt), evidenciando o efeito tardio, ou lag effect. Além disso, foi constatado que outras variáveis de rentabilidade e liquidez impactam neste resultado, também adotando defasagem das variáveis. A principal variável de TI da pesquisa, o IGTI, é calculada pela soma de gastos e investimentos em TI anuais (OPEX/CAPEX), dividida pela Receita Operacional Líquida anual. Para pesquisas futuras, há a possibilidade de buscar medidas de avaliação por tipos (categorias) de investimento em TI, visando ao aprofundamento da análise destes impactos no desempenho setorizado (ligado a cada investimento) e da análise de clusters, adotando o modelo de análise da pesquisa.

Análise da precificação de imóveis na cidade do Rio de Janeiro utilizando Modelagem Hedônica e os efeitos da autocorrelação espacial

A escolha da cidade do Rio de Janeiro como sede de grandes eventos esportivos mundiais, a Copa do Mundo de Futebol de 2014 e os Jogos Olímpicos de 2016, colocou-a no centro de investimentos em infraestrutura, mobilidade urbana e segurança pública, com consequente impacto no mercado imobiliário, tanto de novos lançamentos de empreendimentos, quanto na revenda de imóveis usados. Acredita-se que o preço de um imóvel dependa de uma relação entre suas características estruturais como quantidade de quartos, suítes, vagas de garagem, presença de varanda, tal como sua localização, proximidade com centros de trabalho, entretenimento e áreas valorizadas ou degradadas. Uma das técnicas para avaliar a contribuição dessas características para a formação do preço do imóvel, conhecido na Econométrica como Modelagem Hedônica de Preços, é uma aplicação de regressão linear multivariada onde a variável dependente é o preço e as variáveis independentes, as respectivas características que deseja-se modelar. A utilização da regressão linear implica em observar premissas que devem ser atendidas para a confiabilidade dos resultados a serem analisados, tais como independência e homoscedasticidade dos resíduos e não colinearidade entre as variáveis independentes. O presente trabalho objetiva aplicar a modelagem hedônica de preços para imóveis localizados na cidade do Rio de Janeiro em um modelo de regressão linear multivariada, em conjunto com outras fontes de dados para a construção de variáveis de acessibilidade e socioambiental a fim de verificar a relação de importância entre elas para a formação do preço e, em particular, exploramos brevemente a tendência de preços em função da distância a favelas. Em atenção aos pré-requisitos observados para a aplicação de regressão linear, verificamos que a premissa de independência dos preços não pode ser atestada devido a constatação da autocorrelação espacial entre os imóveis, onde não apenas as características estruturais e de acessibilidade são levadas em consideração para a precificação do bem, mas principalmente a influência mútua que os imóveis vizinhos exercem um ao outro.

Estimation of genetic parameters for partial egg production periods by means of random regression models

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Mortalidade infantil e condições socioeconômicas nas microrregiões do Nordeste Brasileiro

The study aims to answer the following question: what are the different profiles of infant mortality, according to demographic, socioeconomic, infrastructure and health care, for the micro-regions at the Northeast of Brazil? Thus, the main objective is to analyze the profiles or typologies associated mortality levels sociodemographic conditions of the micro-regions, in the year 2010. To this end, the databases of birth and death certificates of SIM and SINASC (DATASUS/MS), were taken from the 2010 population Census microdata and from SIDRA/IBGE. As a methodology, a weighted multiple linear regression model was used in the analysis in order to find the most significant variables in the explanation child mortality for the year 2010. Also a cluster analysis was performed, seeking evidence, initially, of homogeneous groups of micro-regions, from of the significant variables. The logit of the infant mortality rate was used as dependent variable, while variables such as demographic, socioeconomic, infrastructure and health care in the micro-regions were taken as the independent variables of the model. The Bayesian estimation technique was applied to the database of births and deaths, due to the inconvenient fact of underreporting and random fluctuations of small quantities in small areas. The techniques of Spatial Statistics were used to determine the spatial behavior of the distribution of rates from thematic maps. In conclusion, we used the method GoM (Grade of Membership), to find typologies of mortality, associated with the selected variables by micro-regions, in order to respond the main question of the study. The results points out to the formation of three profiles: Profile 1, high infant mortality and unfavorable social conditions; Profile 2, low infant mortality, with a median social conditions of life; and Profile 3, median and high infant mortality social conditions. With this classification, it was found that, out of 188 micro-regions, 20 (10%) fits the extreme profile 1, 59 (31.4%) was characterized in the extreme profile 2, 34 (18.1%) was characterized in the extreme profile 3 and only 9 (4.8%) was classified as amorphous profile. The other micro-regions framed up in the profiles mixed. Such profiles suggest the need for different interventions in terms of public policies aimed to reducing child mortality in the region

Variance component estimates applying random regression models for test-day milk yield in Caracu heifers (Bos taurus Artiodactyla, Bovidae)

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)