Context tree selection: A unifying view

Context tree models have been introduced by Rissanen in [25] as a parsimonious generalization of Markov models. Since then, they have been widely used in applied probability and statistics. The present paper investigates non-asymptotic properties of two popular procedures of context tree estimation: Rissanen's algorithm Context and penalized maximum likelihood. First showing how they are related, we prove finite horizon bounds for the probability of over- and under-estimation. Concerning overestimation, no boundedness or loss-of-memory conditions are required: the proof relies on new deviation inequalities for empirical probabilities of independent interest. The under-estimation properties rely on classical hypotheses for processes of infinite memory. These results improve on and generalize the bounds obtained in Duarte et al. (2006) [12], Galves et al. (2008) [18], Galves and Leonardi (2008) [17], Leonardi (2010) [22], refining asymptotic results of Buhlmann and Wyner (1999) [4] and Csiszar and Talata (2006) [9]. (C) 2011 Elsevier B.V. All rights reserved.

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.

The structure of worker compensation in Brazil, with a comparison to France and the United States

We employ comprehensive linked employer-employee data for Brazil to analyze wage determinants and compare results to Abowd et al. (2001) for French and U.S. manufacturing. While returns to human capita in Brazilian manufacturing exceed those of the other countries, occupation and gender differentials are similar. The worker-characteristics component accounts for much of the greater wage inequality in Brazil, but the establishment-fixed component has scant explanatory power. Thus, firm-or industry-level factors offer little scope for explaining the differences in wage inequality. Brazil`s wage structure resembles that of France, a country with some similarity in labor market institutions.

ICT AND PRODUCTIVITY IN DEVELOPING COUNTRIES: NEW FIRM-LEVEL EVIDENCE FROM BRAZIL AND INDIA

This paper uses a unique new data set on manufacturing firms in Brazil and India to estimate production functions, augmented by information and communications technology (ICT). We find a strong positive association between ICT capital and productivity in both countries that is robust to several different specification tests. The paper also breaks new ground when using the Indian data to investigate the effect of the institutional and policy environment on ICT capital investment and productivity. We find that poorer infrastructure quality and labor market policy are associated with lower levels of ICT adoption, while poorer infrastructure is also associated with lower returns to investment.

Patterns of food acquisition in Brazilian households and associated factors: a population-based survey

Objective: To identify food acquisition patterns in Brazil and relate them to the sociodemographic characteristics of the household. Design: A cross-sectional national Household Budget Survey (HBS). Principal component factor analysis was used to derive food patterns (factors) on the basis of the acquisition of food classified into thirty-two food groups. Setting: The source of data originates from the 2002-2003 HBS carried out by the Brazilian Institute of Geography and Statistics between June 2002 and July 2003 using a representative sample of all Brazilian households. Subject: A total of 48 470 households allocated into 443 strata of households that were geographically and socio-economically homogeneous as a study unit. Results: We identified two patterns of food acquisition. The first, named `dual`, was characterized by dairy, fruit, fruit juice, vegetables, processed meat, soft drinks, sweets, bread and margarine, and by inverse correlations with Brazilian staple foods. In contrast, the second pattern, named `traditional`, was characterized by rice, beans, manioc, flour, milk and sugar. The `dual` pattern was associated with higher household educational level, income and the average age of adults on the strata, whereas the `traditional` presented higher loadings in less-educated households and in the rural setting. Conclusions: Dietary patterns described here suggest that policies and programmes to promote healthy eating need to consider that healthy and non-healthy foods may be integral in the same pattern.

Random walks systems with killing on Z

We study random walks systems on Z whose general description follows. At time zero, there is a number N >= 1 of particles at each vertex of N, all being inactive, except for those placed at the vertex one. Each active particle performs a simple random walk on Z and, up to the time it dies, it activates all inactive particles that it meets along its way. An active particle dies at the instant it reaches a certain fixed total of jumps (L >= 1) without activating any particle, so that its lifetime depends strongly on the past of the process. We investigate how the probability of survival of the process depends on L and on the jumping probabilities of the active particles.

Evolução temporal da dengue no município de Ribeirão Preto, São Paulo, 1994 a 2003

Este estudo caracteriza-se epidemiológico-descritivo com objetivo de descrever a evolução temporal dos casos de dengue em Ribeirão Preto, São Paulo, no período de 1994 a 2003, segundo mês de ocorrência e sexo. Os dados foram obtidos junto às fichas de notificação compulsória fornecidas pela Vigilância Epidemiológica da Secretaria Municipal de Saúde do município. Foram obtidos os coeficientes de incidência por 100.000 habitantes, segundo estimativas populacionais do Instituto Brasileiro de Geografia e Estatística. O município viveu uma epidemia de dengue no ano de 2001, quando o coeficiente de incidência chegou a 619,65 casos/100.000 habitantes, sendo que dentre os 5.553 casos encontrados no período estudado, 0,07% ocorreram no ano de 1994, 3,68% em 1995, 4,52% em 1996, 2,40% em 1997, 1,82% em 1998, 5,73% em 1999, 3,75% em 2000, 57,37% em 2001, 6,25% em 2002 e, 14,39% em 2003 . Os meses do ano de maior ocorrência da doença foram de janeiro a maio. Em relação à variável sexo, a proporção entre o número de casos foi de aproximadamente 1:1, mostrando pequenas flutuações de casos de dengue entre homens e mulheres, para todo período estudado. Os resultados apontam a necessidade do desenvolvimento de estudos sobre a temática e reforçam o papel das instituições de ensino na questão da dengue no nosso país.

Inbreeding levels in Northeast Brazil: strategies for the prospecting of new genetic disorders

A new autosomal recessive genetic condition, the SPOAN syndrome (an acronym for spastic paraplegia, optic atrophy and neuropathy syndrome), was recently discovered in an isolated region of the State of Rio Grande do Norte in Northeast Brazil, in a population that was identified by the IBGE (Brazilian Institute of Geography and Statistics) as belonging to the Brazilian communities with the highest rates of "deficiencies" (Neri, 2003), a term used to describe diseases, malformations, and handicaps in general. This prompted us to conduct a study of consanguinity levels in five of its municipal districts by directly interviewing their inhabitants. Information on 7,639 couples (corresponding to about 40% of the whole population of the studied districts) was obtained. The research disclosed the existence of very high frequencies of consanguineous marriages, which varied from about 9% to 32%, suggesting the presence of a direct association between genetic diseases such as the SPOAN syndrome, genetic drift and inbreeding levels. This fact calls for the introduction of educational programs for the local populations, as well as for further studies aiming to identify and characterize other genetic conditions. Epidemiological strategies developed to collect inbreeding data, with the collaboration of health systems available in the region, might be very successful in the prospecting of genetic disorders.

Aquisição de açúcar e perfil de macronutrientes na cesta de alimentos adquirida pelas famílias brasileiras (2002-2003)

Avaliou-se a influência exercida pela aquisição de calorias de açúcar sobre a participação calórica dos demais macronutrientes da dieta. As estimativas deste estudo são baseadas em dados da Pesquisa de Orçamentos Familiares realizada no Brasil pelo Instituto Brasileiro de Geografia e Estatística entre julho de 2002 e junho de 2003. Modelos de regressão linear múltiplos foram utilizados para estudar a influência das calorias de açúcar sobre a participação calórica de cada um dos macronutrientes na aquisição domiciliar de alimentos com o controle do valor calórico total da aquisição de alimentos e variáveis sócio-demográficas. Cada caloria adquirida de açúcar eleva em 0,3 caloria a participação de gorduras na aquisição domiciliar de alimentos e diminui em 0,07 a participação de proteínas. Cada caloria de açúcar procedente de alimentos processados aumenta em 1,6 caloria a participação de gorduras e em 0,4 caloria de ácidos graxos saturados e diminui em 0,8 caloria a participação de outros carboidratos que não o açúcar. Os resultados encontrados trazem novas evidências sobre o papel prejudicial do açúcar à saúde humana.

Eqüidade e provisão de serviços públicos odontológicos no estado do Paraná

OBJETIVO: Analisar a associação entre indicadores socioeconômicos, de provisão de serviços públicos odontológicos e de alocação de recursos financeiros em saúde, e identificar se o sentido das associações ocorre em favor da eqüidade vertical. MÉTODOS: Foi realizado um estudo transversal de abordagem ecológica, com dados do Ministério da Saúde referentes a 399 municípios do estado do Paraná, no período de 1998 a 2005. A condição socioeconômica foi aferida por meio do Índice de Desenvolvimento Humano dos municípios, além de indicadores de renda, educação e saneamento básico, os quais foram obtidos nas bases de dados do Instituto Brasileiro de Geografia e Estatística. Os dados foram submetidos a testes estatísticos não-paramétricos: coeficiente de correlação de Spearman, Friedman e Mann-Whitney. RESULTADOS: Houve tendência redistributiva dos recursos federais transferidos aos municípios para o custeio da atenção básica, intensificada a partir do lançamento da Estratégia Saúde da Família. Observou-se expansão das ações de saúde bucal no período analisado, bem como tendência pró-eqüidade na oferta e utilização dos serviços odontológicos em atenção básica. CONCLUSÕES: Houve tendência redistributiva, ou pró-eqüidade, na provisão de serviços odontológicos no estado do Paraná, com maior provisão per capita de recursos ou serviços para municípios com piores indicadores socioeconômicos. Esta tendência se mostrou compatível com as diretrizes programáticas recentes do Ministério da Saúde.

Influência da renda sobre as despesas com alimentação fora do domicílio, no Brasil, 2002-2003

Objetivou-se descrever e avaliar a influência da renda sobre a participação da alimentação fora do domicílio no Brasil. Utilizaram-se dados coletados pela Pesquisa de Orçamentos Familiares realizada em 2002/2003 (POF 2002/2003), pelo Instituto Brasileiro de Geografia e Estatística. Analisaram-se os registros dos gastos com aquisições de alimentos e bebidas consumidos fora do domicílio. A associação entre a participação da alimentação fora do domicílio e a renda, ajustada para atributos sócio-demográficos, foi estudada por meio de modelos de regressão utilizados para estimação de coeficientes de elasticidade-renda. A alimentação fora do domicílio representou 21% do total dos gastos com alimentação; destaque-se que o incremento de 10% na renda aumentaria em 3% a participação da alimentação fora do domicílio. O efeito da renda sobre a participação da alimentação fora, ainda que sempre positivo, diminui conforme elevação da renda, sendo alto nos domicílios com renda inferior a R$68,70 per capita/mês. Há influência da renda nos gastos com alimentação fora do domicílio, assim a evolução favorável da renda resultará em aumento dessa forma de se alimentar.

The production of school numbers (1871-1931): contributions to a critical approach to statistical sources in History of Education

This article intends to contribute to the reflection on the Educational Statistics as being source for the researches on History of Education. The main concern was to reveal the way Educational Statistics related to the period from 1871 to 1931 were produced, in central government. Official reports - from the General Statistics Directory - and Statistics yearbooks released by that department were analyzed and, on this analysis, recommendations and definitions to perform the works were sought. By rending problematic to the documental issues on Educational Statistics and their usual interpretations, the intention was to reduce the ignorance about the origin of the school numbers, which are occasionally used in current researches without the convenient critical exam.

Fuzzy risk index for power transformer failures due to external short-circuits

A novel methodology to assess the risk of power transformer failures caused by external faults, such as short-circuit, taking the paper insulation condition into account, is presented. The risk index is obtained by contrasting the insulation paper condition with the probability that the transformer withstands the short-circuit current flowing along the winding during an external fault. In order to assess the risk, this probability and the value of the degree of polymerization of the insulating paper are regarded as inputs of a type-2 fuzzy logic system (T2-FLS), which computes the fuzzy risk level. A Monte Carlo simulation has been used to find the survival function of the currents flowing through the transformer winding during a single-phase or a three-phase short-circuit. The Roy Billinton Test System and a real power system have been used to test the results. (C) 2008 Elsevier B.V. All rights reserved.

The choice of the best among the shortest routes in transparent optical networks

This work introduces the problem of the best choice among M combinations of the shortest paths for dynamic provisioning of lightpaths in all-optical networks. To solve this problem in an optimized way (shortest path and load balance), a new fixed routing algorithm, named Best among the Shortest Routes (BSR), is proposed. The BSR`s performance is compared in terms of blocking probability and network utilization with Dijkstra`s shortest path algorithm and others algorithms proposed in the literature. The evaluated scenarios include several representative topologies for all-optical networking and different wavelength conversion architectures. For all studied scenarios, BSR achieved superior performance. (C) 2010 Elsevier B.V. All rights reserved.

Auditory results from cochlear implants in elderly people

According to data from the Brazilian Institute of Geography and Statistics, the elderly population grew 47.8% in the last decade in Brazil. A portion of this population has severe and/or profound hearing loss and do not benefit from conventional hearing aids. Thus, the use of cochlear implant is required. Aim: To analyze the benefits of cochlear implants in the elderly based on the comparison of primary auditory thresholds before and after the operation, discrimination of sentences in speech and in talking on the telephone. Methodology: Retrospective cohort study, analyzing medical records from patients aged over 60 years, users of cochlear implant for at least 1 year. Results: Fourteen medical records were analyzed. Mean age of patients was 63.07 years. The mean pure tone thresholds between 500Hz, 1kHz, 2kHz and 4kHz before the implantation was 113dBHL. None of the patients, before operation, could discriminate sentences in open sets and only 3 scored 17% in closed sets sentence recognition. After one year of implantation, the mean sound field thresholds reached 34dBHL, and open set sentences recognition of 93.57%, while 71% of the patients had become able to have a conversation on the telephone. Conclusion: The elderly users of cochlear implant showed important outcomes, with significant improvement in understanding in the open set and in using the telephone.