Improving mutual fund market timing measures: a markov switching approach

Market timing performance of mutual funds is usually evaluated with linear models with dummy variables which allow for the beta coefficient of CAPM to vary across two regimes: bullish and bearish market excess returns. Managers, however, use their predictions of the state of nature to deÞne whether to carry low or high beta portfolios instead of the observed ones. Our approach here is to take this into account and model market timing as a switching regime in a way similar to Hamilton s Markov-switching GNP model. We then build a measure of market timing success and apply it to simulated and real world data.

Aspectos do mercado eleitoral brasileiro: análise econométrica do impacto dos gastos de campanha nas eleições para a Câmara e o Senado de 2002

Esta dissertação de mestrado em economia foi motivada por uma questão complexa bastante estudada na literatura de economia política nos dias de hoje: as formas como campanhas políticas afetam votação em uma eleição. estudo procura modelar mercado eleitoral brasileiro para deputados federais senadores. Através de um modelo linear, conclui-se que os gastos em campanha eleitoral são fatores decisivos para eleição de um candidato deputado federal. Após reconhecer que variável que mede os gastos em campanha possui erro de medida (devido ao famoso "caixa dois", por exemplo), além de ser endógena uma vez que candidatos com maiores possibilidades de conseguir votos conseguem mais fontes de financiamento -, modelo foi estimado por variáveis instrumentais. Para senadores, utilizando modelos lineares modelos com variável resposta binaria, verifica-se também importância, ainda que em menor escala, da campanha eleitoral, sendo que um fator mais importante para corrida ao senado parece ser uma percepção priori da qualidade do candidato.

Risco de abandono de relacionamento

This paper presents a study carried out with customers with credit card of a large retailer to measure the risk of abandonment of a relationship, when this has already purchase history. Two activities are the most important in this study: the theoretical and methodological procedures. The first step was to the understanding of the problem, the importance of theme and the definition of search methods. The study brings a bibliographic survey comprising several authors and shows that the loyalty of customers is the basis that gives sustainability and profitability for organizations of various market segments, examines the satisfaction as the key to success for achievement and specially for the loyalty of customers. To perform this study were adjusted logistic-linear models and through the test Kolmogorov - Smirnov (KS) and the curve Receiver Operating Characteristic (ROC) selected the best model. Had been used cadastral and transactional data of 100,000 customers of credit card issuer, the software used was SPSS which is a modern system of data manipulation, statistical analysis and presentation graphics. In research, we identify the risk of each customer leave the product through a score.

Os efeitos da concentração regional no desempenho das empresas: uma abordagem multinível

O presente trabalho tem por objetivo avaliar o impacto das concentrações regionais no desempenho organizacional das empresas brasileiras com ênfase no setor serviços. Com o intuito de atingir este objetivo realizou-se uma comparação entre o desempenho organizacional das firmas localizadas em áreas de concentração geográficas e aquelas situadas fora destas áreas. Além disso, procurou-se contrastar o efeito da concentração regional sobre o desempenho das empresas de serviços com as empresas do setor industrial. A revisão literária evidenciou a existência de vantagens para empresas concentradas regionalmente, o que levou à principal hipótese deste trabalho, de que tais vantagens ocasionariam melhor desempenho das firmas. Desta forma, buscou-se averiguar a existência de uma relação entre o desempenho organizacional e a localização geográfica das empresas de serviços regionalmente concentradas. O trabalho de identificação das concentrações regionais foi realizado adaptando-se os critérios utilizados no setor industrial para o setor serviços, a partir dos dados de número de estabelecimentos e de funcionários, obtidos através da base dados da Relação Anual de Informações Sociais (RAIS). O desempenho organizacional foi mensurado por dois indicadores: lucratividade e o crescimento de vendas. A fonte de dados de desempenho utilizada foi a base de microdados das seguintes pesquisas do Instituto Brasileiro de Geografia e Estatística (IBGE): Pesquisa Industrial Anual (PIA) e Pesquisa Anual de Serviços (PAS). A amostra utilizada incluiu 78.789 observações de prestadoras de serviços e 22.460 observações de empresas do setor industrial, entre 2001 e 2005. Os resultados foram produzidos por meio da aplicação dos modelos hierárquicos ou modelos multiníveis. Os resultados revelaram um efeito positivo sobre o crescimento das empresas situadas em áreas de concentração regional (tanto do setor serviços quanto da indústria), porém não foram encontradas evidências de maior lucratividade das mesmas. As conclusões deste trabalho contribuem para a tomada de decisão dos gestores, ao avaliar se deverão ou não situar seu empreendimento em uma área de concentração regional. Além de apresentar implicações para as políticas públicas, pois a constatação de um efeito positivo sobre o crescimento das firmas em determinadas concentrações pode direcionar políticas de incentivo, com o objetivo de estimular a formação de tais concentrações em determinadas localidades para desenvolvimento regional.

Falta de qualidade da educação brasileira: qual a magnitude do problema?

In this paper we investigate how several national educational policies and practices influence both students' average reading achievement and the social distributioll of achievement within schools and countries. Data come fJ:om the 2000/2001 administration of PISA (programme for International Student Assessment) by the Organization for Economic Cooperation and Developrnent (OECD). They include observations from 212,880 lS-year-old students attending 8,038 secondary schools, which are located in 39 countries. We analyze these data with three-level Hierarchical Linear Models (HLM), with students nested in schools, which are nested within countries. Results focus on the role played by three country-level educational policies: (1) retention/repetition; (2) the mix of students in schools based on socioeconomic status (school social mix); and vocational education. We explore how these policies influence the social distribution of achievemer.t between schools within countries. Implications of these findings are discussed.

Modelos dinâmicos e simulação estocástica

This paper presents new methodology for making Bayesian inference about dy~ o!s for exponential famiIy observations. The approach is simulation-based _~t> use of ~vlarkov chain Monte Carlo techniques. A yletropolis-Hastings i:U~UnLlllll 1::; combined with the Gibbs sampler in repeated use of an adjusted version of normal dynamic linear models. Different alternative schemes are derived and compared. The approach is fully Bayesian in obtaining posterior samples for state parameters and unknown hyperparameters. Illustrations to real data sets with sparse counts and missing values are presented. Extensions to accommodate for general distributions for observations and disturbances. intervention. non-linear models and rnultivariate time series are outlined.

A relação entre aglomeração produtiva e crescimento: a aplicação de um modelo multinível ao setor industrial paulista

Este estudo identificou a relação da aglomeração de firmas de uma mesma atividade econômica na taxa de crescimento do emprego local. Dados das firmas industriais do Estado de São Paulo constantes da Relação Anual de Informações Sociais [RAIS] nos anos de 1996 a 2005 foram coletados. Foram analisadas 263.020 observações de nível de emprego de 26.231 combinações de município-CNAE e 296 diferentes atividades. Os critérios de Puga (2003) e Suzigan, Furtado, Garcia, Sampaio (2003) foram usados para identificar as aglomerações. Uma análise de curva de crescimento, usando-se um modelo multinível, foi desenvolvida no software Hierarchical Linear Models [HLM]. Os resultados evidenciam que existe uma relação positiva entre aglomeração de firmas de uma mesma atividade econômica e o crescimento de emprego. Considerando as externalidades previstas pelo fato de as empresas estarem localizadas em uma mesma região, pode-se sugerir que, em termos comparativos, firmas de uma mesma atividade econômica, localizadas em aglomeração, podem, perceber crescimento maior que suas concorrentes localizadas fora de um aglomerado. Este resultado é relevante, tanto para a empresa individual, como para o estabelecimento de políticas públicas que apóiam o desenvolvimento regional, no nível do município. As evidências confirmam estudos anteriores de caso, permitindo dar mais robustez à teoria

Endogamia em um rebanho da raça Guzerá

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Old beagle dogs have lower faecal concentrations of some fermentation products and lower peripheral lymphocyte counts than young adult beagles

The effects of age on microbiota composition, gut fermentation end-product formation and peripheral lymphocyte numbers were compared between old and young adult Beagle dogs fed four kibble diets differing in yeast cell wall contents. The experiment had a double 4 x 4 Latin square design, one with four mature dogs (4 years old) and the other with four old dogs (10 years old), with four replicates (diets) per dog. In each period a 15d adaptation period preceded a 5d total collection of faeces for the digestibility trial. on day 21, fresh faecal samples were collected for the determination of bacterial enumeration, pH, biogenic amine and short-chain fatty acid. Flow cytometry was used for immunophenotypic evaluation. Dogs were fed four kibble diets with similar composition with 0, 0.15, 0.30 and 0.45% of yeast cell wall (as-fed), respectively. Data were evaluated using general linear models of Statistical Analysis Systems statistical software (P<0.05). No evidence of a difference in faecal bacteria counts between ages was found (total aerobes, total anaerobes, Bifidobacterium, Lactobacillus, Clostridium and Escherichia coli: P. 0.15). Faecal concentrations of butyrate, histamine, agmatine and spermine were lower (P <= 0.05) and faecal pH was higher (P=0.03) in older dogs than in mature adult dogs, suggesting an alteration in bacterial metabolic activity, or in the rate of intestinal absorption of these compounds. Concentrations of T-lymphocytes, T-cytotoxic lymphocytes and B-lymphocytes were also lower (P <= 0.01) in older dogs than in mature adult dogs. The study confirmed alterations in peripheral lymphocytes and revealed a reduced concentration of some fermentation end products in the colon of old dogs.

A simple and non-destructive model for individual leaf area estimation in citrus

Introduction. Leaf area is often related to plant growth, development, physiology and yield. Many non-destructive models have been proposed for leaf area estimation of several plant genotypes, demonstrating that leaf length, leaf width and leaf area are closely correlated. Thus, the objective of our study was to develop a reliable model for leaf area estimation from linear measurements of leaf dimensions for citrus genotypes. Materials and methods. Leaves of citrus genotypes were harvested, and their dimensions (length, width and area) were measured. Values of leaf area were regressed against length, width, the square of length, the square of width and the product (length x width). The most accurate equations, either linear or second-order polynomial, were regressed again with a new data set; then the most reliable equation was defined. Results and discussion. The first analysis showed that the variables length, width and the square of length gave better results in second-order polynomial equations, while the linear equations were more suitable and accurate when the width and the product (length x width) were used. When these equations were regressed with the new data set, the coefficient of determination (R(2)) and the agreement index 'd' were higher for the one that used the variable product (length x width), while the Mean Absolute Percentage Error was lower. Conclusion. The product of the simple leaf dimensions (length x width) can provide a reliable and simple non-destructive model for leaf area estimation across citrus genotypes.

Aplicação superficial de calcário em pomar de laranjeira pêra em produção

A citricultura paulista é a maior do mundo, sendo de extrema importância manejos que visem a aumentar e melhorar a produção de frutos. Com vistas a isso, foi instalado na EECB (Bebedouro-SP), em um Latossolo Vermelho distrófico típico, um experimento com a aplicação de cinco doses de calcário calcinado, em julho/99. Os efeitos no solo foram avaliados através de amostragens nas camadas de 0-10; 10-20; 20-40 e 40-60 cm, aos 6; 12; 18; 24; 30 e 36 meses. Através da utilização de modelos lineares, constatou-se que os efeitos da aplicação superficial de calcário no solo podem atingir até a camada de 20-40 cm, sendo a saturação por bases uma ótima característica indicadora da ação do corretivo. A máxima reação do calcário ocorreu entre 12 e 18 meses após a aplicação. O estado nutricional das plantas e a produção foram alterados, significativamente em função da aplicação superficial de calcário, sendo que melhores respostas da planta foram obtidas com saturação por bases de aproximadamente 50%.

Growth curve in Santa Ines sheep

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Identificação fuzzy-multimodelos para sistemas não lineares

This paper presents a new multi-model technique of dentification in ANFIS for nonlinear systems. In this technique, the structure used is of the fuzzy Takagi-Sugeno of which the consequences are local linear models that represent the system of different points of operation and the precursors are membership functions whose adjustments are realized by the learning phase of the neuro-fuzzy ANFIS technique. The models that represent the system at different points of the operation can be found with linearization techniques like, for example, the Least Squares method that is robust against sounds and of simple application. The fuzzy system is responsible for informing the proportion of each model that should be utilized, using the membership functions. The membership functions can be adjusted by ANFIS with the use of neural network algorithms, like the back propagation error type, in such a way that the models found for each area are correctly interpolated and define an action of each model for possible entries into the system. In multi-models, the definition of action of models is known as metrics and, since this paper is based on ANFIS, it shall be denominated in ANFIS metrics. This way, ANFIS metrics is utilized to interpolate various models, composing a system to be identified. Differing from the traditional ANFIS, the created technique necessarily represents the system in various well defined regions by unaltered models whose pondered activation as per the membership functions. The selection of regions for the application of the Least Squares method is realized manually from the graphic analysis of the system behavior or from the physical characteristics of the plant. This selection serves as a base to initiate the linear model defining technique and generating the initial configuration of the membership functions. The experiments are conducted in a teaching tank, with multiple sections, designed and created to show the characteristics of the technique. The results from this tank illustrate the performance reached by the technique in task of identifying, utilizing configurations of ANFIS, comparing the developed technique with various models of simple metrics and comparing with the NNARX technique, also adapted to identification

Estrutura ANFIS modificada para identificação e controle de plantas com ampla faixa de operação e não linearidade acentuada

In this work a modification on ANFIS (Adaptive Network Based Fuzzy Inference System) structure is proposed to find a systematic method for nonlinear plants, with large operational range, identification and control, using linear local systems: models and controllers. This method is based on multiple model approach. This way, linear local models are obtained and then those models are combined by the proposed neurofuzzy structure. A metric that allows a satisfactory combination of those models is obtained after the structure training. It results on plant s global identification. A controller is projected for each local model. The global control is obtained by mixing local controllers signals. This is done by the modified ANFIS. The modification on ANFIS architecture allows the two neurofuzzy structures knowledge sharing. So the same metric obtained to combine models can be used to combine controllers. Two cases study are used to validate the new ANFIS structure. The knowledge sharing is evaluated in the second case study. It shows that just one modified ANFIS structure is necessary to combine linear models to identify, a nonlinear plant, and combine linear controllers to control this plant. The proposed method allows the usage of any identification and control techniques for local models and local controllers obtaining. It also reduces the complexity of ANFIS usage for identification and control. This work has prioritized simpler techniques for the identification and control systems to simplify the use of the method

Identificação em tempo real de modelo dinâmico de robô móvel com acionamento diferencial e zona morta

Several mobile robots show non-linear behavior, mainly due friction phenomena between the mechanical parts of the robot or between the robot and the ground. Linear models are efficient in some cases, but it is necessary take the robot non-linearity in consideration when precise displacement and positioning are desired. In this work a parametric model identification procedure for a mobile robot with differential drive that considers the dead-zone in the robot actuators is proposed. The method consists in dividing the system into Hammerstein systems and then uses the key-term separation principle to present the input-output relations which shows the parameters from both linear and non-linear blocks. The parameters are then simultaneously estimated through a recursive least squares algorithm. The results shows that is possible to identify the dead-zone thresholds together with the linear parameters