Papers by Basílio Pereira
Experience in combining subjective and quantitative forecasts of open market rates
Journal of Forecasting, 1989
This paper presents a method of combining subjective information from open‐market operators with ... more This paper presents a method of combining subjective information from open‐market operators with results from a time‐series forecasting model. Empirical results of forecasts for interest rates of bank reserves are presented.
Estat�stica em psiquiatria
Abp, 2001
Concessão Pela Ufrj Do Título De Doutor Honoris Causa Ao
Método Bayesiano de provisao de series temporais : aplicacao a una serie demanda de energia eléctrica / por Basilio de Braganca Pereira e Luiz Eduardo Pazito Memdés
ABSTRACT
Testes para discriminacao entre modelos / por Basilio de Braganca Pereira
ABSTRACT
Bayesian method of time series prediction: Application to demand of electrical energy
Empirical comparisons of some test of separate families of hypotheses / Basilio de Braganca Pereira
Structural inference for the generalized gamma distribution
Structural inference is used in the analysis of a three parameter model which consists of a repar... more Structural inference is used in the analysis of a three parameter model which consists of a reparametrization of the logarithm of a generalized gamma variate. Marginal likelihood and structural probabilities are presented. A regression generalization is given.
Tests for Discriminating Separate or Non-Nested Models
International Encyclopedia of Statistical Science, 2011
Separate Families of Hypotheses
Wiley StatsRef: Statistics Reference Online, 2014
In the last forty years since statistical procedures were first developed to test separate (nonne... more In the last forty years since statistical procedures were first developed to test separate (nonnested) families of hypotheses, a huge amount of literature has developed for testing a null model against one or more separate alternatives. In the first two decades, mainly statisticians were interested in this problem. During the eighties the econometricians took a great interest and in the nineties, Bayesian statisticians developed some new results on the subject. The purpose of this paper is to given an introductory overview of the subject and an updated bibliography. Keywords: Bayes factors: fractional; intrinsic; partial and posterior; hypothesis test; likelihood; model discrimination; nonnested models; separate families
Separate Families of Hypotheses
Encyclopedia of Biostatistics, 2005
In the last forty years since statistical procedures were first developed to test separate (nonne... more In the last forty years since statistical procedures were first developed to test separate (nonnested) families of hypotheses, a huge amount of literature has developed for testing a null model against one or more separate alternatives. In the first two decades, mainly statisticians were interested in this problem. During the eighties the econometricians took a great interest and in the nineties, Bayesian statisticians developed some new results on the subject. The purpose of this paper is to given an introductory overview of the subject and an updated bibliography. Keywords: Bayes factors: fractional, intrinsic, partial and posterior; hypothesis test; likelihood; model discrimination; nonnested models; separate families
Choice of a survival model for patients with a brain tumour
Metrika, 1981
ABSTRACT Tests of separate families of hypotheses are briefly described and applied to log-linear... more ABSTRACT Tests of separate families of hypotheses are briefly described and applied to log-linear regression models. The procedure is used for the choice of a survival model for patients with a brain tumour.
A Note on the Consistency and on the Finite Sample Comparisons of Some Tests of Separate Families of Hypotheses
Biometrika, 1977
The consistency of the tests developed by Cox (1961, 1962) and Atkinson (1970) in which null and ... more The consistency of the tests developed by Cox (1961, 1962) and Atkinson (1970) in which null and alternative hypotheses specify different parametric families is discussed. It is shown that Atkinson's procedure is not always consistent. An example is presented. Under the null hypothesis a discussion of the approach to asymptotic theory is provided through the examination of the terms which differentiate the two procedures and some insight into the behaviour of the tests in finite samples is then obtained.
Tests and efficiencies of separate regression models
Biometrika, 1978
SUMMARY The results of Cox (1961, 1962) on tests of separate families of hypotheses are used to d... more SUMMARY The results of Cox (1961, 1962) on tests of separate families of hypotheses are used to develop tests for some log linear regression models. The consequences of using one model when another is true are studied. The probability limits and asymptotic efficiencies of the estimators of the regression coefficients when using a false model in relation to the true model are investigated.
Empirical comparisons of some tests of separate families of hypotheses
Metrika, 1978
ABSTRACT Summary This paper is devoted to a comparison of the asymptotic tests of separate famili... more ABSTRACT Summary This paper is devoted to a comparison of the asymptotic tests of separate families of hypotheses proposed byCox [1961, 1962] and byAtkinson [1970]. The adequacy of the asymptotic results for finite samples is investigated and some conclusions reached. An examination of the terms which differentiate the two procedures is made. Empirical simulated results are discussed for cases involving the exponential, the lognormal and the Weibull distributions.
Corneal Collagen Cross-linking With Riboflavin and Ultraviolet-A Irradiation in Patients With Thin Corneas
American Journal of Ophthalmology, 2012
To report the outcomes after corneal collagen cross-linking (CXL) treatment with riboflavin and u... more To report the outcomes after corneal collagen cross-linking (CXL) treatment with riboflavin and ultraviolet-A (UVA) irradiation in patients with thin corneas (minimum corneal thickness less than 400 μm after epithelial removal and before riboflavin instillation). Prospective case series. Twelve patients (14 eyes, with minimum corneal thickness less than 400 μm after epithelial removal) were included in the study. All patients underwent riboflavin-UVA-induced CXL using the standard CXL (Dresden) protocol. Uncorrected distance visual acuity (UDVA) and corrected distance visual acuity (CDVA) (decimal scale), manifest refraction (diopters, D), and topography were evaluated at baseline and at 1, 3, 6, and 12 months follow-up. Images of the endothelium were acquired with a modified confocal scanning laser ophthalmoscope. No intraoperative or postoperative complications were observed in this patient series. Mean minimum preoperative corneal thickness at the apex of the cone after epithelial removal and before riboflavin instillation was 373.92 ± 22.92 μm (range 340-399 μm). UDVA and CDVA improved from 0.25 ± 0.15 and 0.40 ± 0.20 to 0.27 ± 0.17 and 0.49 ± 0.20 respectively at the last follow-up examination. There was a reduction of the mean keratometry readings from 51.99 ± 5.57 D to 49.33 ± 4.82 D at the last follow-up. A significant decrease of endothelial cell density was observed (preoperative: 2733 ± 180 cells/mm(2) [range 2467-3016], last follow-up visit: 2441 ± 400 cells/mm(2) [range 1448-2920], P < .01). CXL in thin corneas with minimum corneal thickness less than 400 μm after epithelial removal seems to result in a significant endothelial cell density decrease postoperatively. This finding was not related to other intraoperative or postoperative complications.
Journal of Data Science, 2021
The paper proposes the use of Kohonen's Self Organizing Map (SOM), and supervised neural networks... more The paper proposes the use of Kohonen's Self Organizing Map (SOM), and supervised neural networks to find clusters in samples of gammaray burst (GRB) using the measurements given in BATSE GRB. The extent of separation between clusters obtained by SOM was examined by cross validation procedure using supervised neural networks for classification. A method is proposed for variable selection to reduce the "curse of dimensionality". Six variables were chosen for cluster analysis. Additionally, principal components were computed using all the original variables and 6 components which accounted for a high percentage of variance was chosen for SOM analysis. All these methods indicate 4 or 5 clusters. Further analysis based on the average profiles of the GRB indicated a possible reduction in the number of clusters.
Communications in Statistics - Theory and Methods, 2017
An evaluation of FBST, Fully Bayesian Significance Test, restricted to survival models is the mai... more An evaluation of FBST, Fully Bayesian Significance Test, restricted to survival models is the main objective of the present paper. A Survival distribution should be chosen among the tree celebrated ones, lognormal, gamma, and Weibull. For this discrimination, a linear mixture of the three distributions, for which the mixture weights are defined by a Dirichlet distribution of order three, is an important tool: the FBST is used to test the hypotheses defined on the mixture weights space. Another feature of the paper is that all three distributions are reparametrized in that all the six parameters-two for each distribution-are written as functions of the mean and the variance of the population been studied. Note that the three distributions share the same two parameters in the mixture model. The mixture density has then four parameters, the same two for the three discriminating densities and two for the mixture weights. Some numerical results from simulations with some right-censored data are considered. The lognormal-gamma-Weibull model is also applied to a real study with dataset being composed by patients survival times of patients in the end-stage of chronic kidney failure subjected to hemodialysis procedures; data from Rio de Janeiro hospitals. The posterior density of the weights indicates an order of the mixture weights and the FBST is used for discriminating between the three survival distributions
Nature Precedings, 2008
In controlled clinical trials, each of several prognostic factors should be balanced across the t... more In controlled clinical trials, each of several prognostic factors should be balanced across the trial arms. Traditional restricted randomization may be proved inadequate especially with small sample sizes. In psychiatric disorders such as obsessive compulsive disorder (OCD), small trials prevail. Therefore, procedures to minimize the chance of imbalance between treatment arms are advisable. This paper describes a minimization procedure specifically designed for a clinical trial that evaluates treatment efficacy for OCD patients. Aitchison's compositional distance was used to calculate vectors for each possibility of allocation in a covariate adaptive method. Two different procedures were designed to allocate patients in small blocks or sequentially one-by-one. Partial results of this allocation procedure as well as simulated ones are shown. In the clinical trial for which this procedure was developed, the balancing between treatment arms was achieved successfully. Simulations of...
Revista da Sociedade Brasileira de Medicina Tropical
Nutritional status has been implicated in the modulation of the immune response, possibly augment... more Nutritional status has been implicated in the modulation of the immune response, possibly augmenting the pathogenesis of Chagas disease (Cd). We evaluated diet quality and nutritional status in adults and elderly patients with chronic Cd in a tertiary hospital. A case-control study of Cd patients was conducted, paired for gender, age, and co-morbidities with non-Cd patients. Anthropometric measurements and food frequency questionnaire was used, and diet quality was assessed by the Brazilian Healthy Eating Index-Revised (BHEI-R). The Estimated Average Requirement cut-off points were used to determine the dietary micronutrient adequacy. The Cd group was further grouped according to Los Andes classification. The study participants were 67 ± 10 years old, 73.6% elderly and 63% female. The prevalence of overweight/obesity and abdominal fat was high in both groups; however, Cd group showed a lower prevalence of obesity and increased risk of disease according to waist circumference classif...
Uploads
Papers by Basílio Pereira