Bernardo Borba de Andrade

ORCID: 0000-0003-4688-9733
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Statistical Methods and Bayesian Inference
  • Efficiency Analysis Using DEA
  • Mathematical and Theoretical Analysis
  • Statistical Methods and Inference
  • Statistical Distribution Estimation and Applications
  • Advanced Statistical Methods and Models
  • Computability, Logic, AI Algorithms
  • Hydrology and Watershed Management Studies
  • Rural Development and Agriculture
  • Lattice Boltzmann Simulation Studies
  • Hydrology and Drought Analysis
  • Water resources management and optimization
  • Software System Performance and Reliability
  • Bayesian Methods and Mixture Models
  • Agricultural Innovations and Practices
  • Aquaculture Nutrition and Growth
  • COVID-19 epidemiological studies
  • Financial Risk and Volatility Modeling
  • Cloud Computing and Resource Management
  • Probability and Statistical Research
  • SARS-CoV-2 and COVID-19 Research
  • Data Stream Mining Techniques
  • Economics of Agriculture and Food Markets
  • Posttraumatic Stress Disorder Research
  • Advanced Statistical Process Monitoring

Universidade de Brasília
2015-2024

Instituto de Engenharia de Sistemas e Computadores Investigação e Desenvolvimento
2021-2023

Instituto Superior Técnico
2023

Polytechnic Institute of Bragança
2019

Federal Center for Technological Education of Minas Gerais
2019

Universidade Federal do Rio Grande do Norte
2011-2015

Centro Universitário do Rio Grande do Norte
2014

University of Oklahoma Health Sciences Center
2011

University of Oklahoma
2011

Objective. Employees of long-term care facilities (LTCFs) who have contact with residents should be vaccinated against influenza annually to reduce incidence among residents. This investigation estimated the magnitude benefit this recommendation. Methods. The New Mexico Department Health implemented active surveillance in all its 75 LTCFs during seasons 2006-2007 and 2007-2008. Information about number laboratory-confirmed cases proportion both direct-care employees each facility was...

10.1086/661916 article EN Infection Control and Hospital Epidemiology 2011-09-19

Goodness–of–fit tests for the distribution of composed error term in a Stochastic Frontier Model (SFM) are suggested. The focus is on case normal/gamma SFM and heavy–tailed stable/gamma SFM. In first moment generating function used as tool while latter characteristic employed. both cases our test statistics formulated weighted integrals properly standardized data. new consistent, shown to have an intrinsic relation moment–based tests. finite–sample behavior resampling versions investigated...

10.1016/j.ecosta.2024.08.002 article EN cc-by-nc-nd Econometrics and Statistics 2024-08-01

This article discusses two asymmetrization methods, Azzalini's representation and beta generation, to generate asymmetric bimodal models including novel beta-generated models. The practical utility of these is assessed with nine data sets from different fields applied sciences. Besides this tutorial assessment, some methodological contributions are made: a random number generator for the Rathie–Swamee model developed (generators other already known briefly described) new likelihood ratio...

10.1080/00949655.2016.1157180 article EN Journal of Statistical Computation and Simulation 2016-03-10

One of the most challenging problems in migration a monolith to microservices architecture is identification boundaries. Several approaches have been recently proposed for automatic microservices, which, even though following same basic steps, diverge on how data system collected and analysed. In this paper, we compare decompositions generated two systems into set candidate when static dynamic analysis collection techniques are used. The using combination similarity measures evaluated...

10.48550/arxiv.2204.11844 preprint EN cc-by arXiv (Cornell University) 2022-01-01

Maximum likelihood (ML) estimation of relative risks via log-binomial regression requires a restricted parameter space. Computation non linear programming is simple to implement and has high convergence rate. We show that the optimization problem well posed (convex domain convex objective) provide variance formula along with methodology for obtaining standard errors prediction intervals which account estimates on boundary performed simulations under several scenarios already used in...

10.1080/03610926.2017.1402045 article EN Communication in Statistics- Theory and Methods 2017-12-06

Using data collected by the Brazilian National Household Sample Survey - COVID-19 (PNAD-COVID19) and semi-Bayesian modelling developed Wu et al., we have estimated effect of underreporting cases in Brazil as December 2020. The total number infected individuals is about 3 to 8 times reported, depending on state. Confirmed are at 3.1% population our estimate almost 15% approximately 212 million Brazilians method adopted from with slight modifications prior specifications, applies bias...

10.1590/0102-311x00290120 article EN cc-by Cadernos de Saúde Pública 2021-01-01

The Expectation-Maximization (EM) algorithm is developed for the stochastic frontier models most used in practice with cross-section data. resulting algorithms can be easily programmed into a computer and are shown to worthy alternatives general-purpose optimization routines currently used. half normal exponential have closed-form expressions whereas those truncated gamma will require numerical solution of nonlinear equation. Implementations EM either as stand-alone routine or accelerated...

10.1590/0101-7438.2019.039.03.0361 article EN Pesquisa Operacional 2019-12-01

Abstract This paper provides a general treatment of statistical inference for the reliability in copula‐based stress‐strength models. Most current literature is either focused on specific models that yield clean formulas or restricted to estimation and engineering aspects without addressing inference. We present two frameworks, one parametric, nonparametric, reliability. The parametric methodology presented under framework estimating equations, mostly as combination existing methodologies...

10.1002/qre.2694 article EN Quality and Reliability Engineering International 2020-06-29

Recently, Bolfarine et al. [Bimodal symmetric-asymmetric power-normal families. Commun Statist Theory Methods. Forthcoming. doi:10.1080/03610926.2013.765475] introduced a bimodal asymmetric model having the normal and skew as special cases. Here, we prove stochastic representation for their use it to generate random numbers from that model. It is shown how resulting algorithm can be seen an improvement over rejection method. We also discuss practical numerical aspects regarding estimation of...

10.1080/00949655.2015.1016434 article EN Journal of Statistical Computation and Simulation 2015-02-25

Abstract The most common control chart used to monitor count data is based on Poisson distribution, which presents a strong restriction: mean equal the variance. To deal with under‐ or overdispersion, charts considering other distributions as Negative Binomial (NB) hyper‐Poisson, generalized distribution (GPD), Conway–Maxwell–Poisson (COM‐Poisson), Poisson–Lindley, new Poisson–Lindley (NGPL) have been developed and can be found in literature. In this paper we also present Shewhart Touchard...

10.1002/qre.2833 article EN Quality and Reliability Engineering International 2021-01-13

10.1016/j.physa.2015.01.066 article EN Physica A Statistical Mechanics and its Applications 2015-02-14

We prove a nonstandard central limit theorem for strongly mixing stationary sequences using the "radically elementary" probability theory developed by Nelson (1987) and use this result to obtain Markov chain theorem. An analogue of Gaussian autoregressive process is used illustrate how rate convergence. A functional also proved under conditions similar square integrability underlying martingale.

10.1142/s021848851100699x article EN International Journal of Uncertainty Fuzziness and Knowledge-Based Systems 2011-04-01

Modern portfolio theory indicates that optimization can be carried out based on the mean-variance model, where returns and risk are represented as average variance of historical data stock’s returns, respectively. Several studies have been to find better proxies, was not accurate. On other hand, fewer papers devoted model/characterize returns. In present paper, we explore use reliability measure P(Y<X) choose between portfolios with given by distributions X Y. Thus, instead comparing...

10.3390/stats4040059 article EN cc-by Stats 2021-12-09

We present a novel model, which is two-parameter extension of the Poisson distribution. Its normalizing constant related to Touchard polynomials, hence name this model. It flexible distribution that can account for both under- or overdispersion and concentration zeros are frequently found in non-Poisson count data. In contrast some other generalizations, Hessian matrix maximum likelihood estimation parameters has simple form. exemplify with three data sets, showing our suggested model...

10.1080/03610926.2018.1444177 article EN Communication in Statistics- Theory and Methods 2018-03-08

Drying food involves complex physical atmospheric mechanisms with non-linear relations from the air-food interactions. Moreover, those are strongly dependent on moisture contents and actual type of food. Such dependence makes it to design suitable machines dedicated a single drying process. To speed-up streamline machine design, heat pump dryer optimization algorithm was developed. The proposed inputs air proprieties, volume container technical specifications heat-pump off-the shelf...

10.20944/preprints201907.0281.v1 preprint EN 2019-07-25

Aims: This study demonstrates that auxiliary and exclusion criteria variables increase the effectiveness of missing imputation in correcting underestimation physiologic reactivity relation to post‐traumatic stress disorder (PTSD) caused by deleting cases with data. Methods: used data from survivors 1995 Oklahoma City bombing imputed heart rate using variables. Logistic regression was examine current PTSD. Results: Of 113 who participated study's 7‐year follow‐up interview, 42 (37%) had on...

10.1111/j.1440-1819.2011.02233.x article EN Psychiatry and Clinical Neurosciences 2011-08-01

Stochastic production frontier models are widely used in microeconometrics and, the last decades, have been proven to be versatile their range of applications. However, there few studies concerning endogeneity stochastic models. Here we present two with endogenous variables based on main distributions for technical inefficiency. We also derive analytic gradient vectors obtain best performance at a reasonable computational time cost. The methodology presented here is one and two-step maximum...

10.1590/0101-7438.2022.042.00243504 article EN Pesquisa Operacional 2022-01-01

This article proves a nonstandard Central Limit Theorem (CLT) in the sense of Nelson’s Radically Elementary Probability Theory. The CLT proved here is obtained by establishing near equivalence standardized averages from L2 IID random variables to average resulting binomial CLT. A model for on metric spaces replaces conventional results weak convergence. Statements and proofs remain radically elementary without applying full Internal Set notion normality discussed.

10.4115/jla.2015.7.3 article EN cc-by Journal of Logic and Analysis 2015-01-01

The aim of this study is to get further into the two-state Markov chain model for synthetic generation daily streamflows. proposed in Aksoy and Bayazit (2000) (2003) based on a two chains determining state stream. ascension curve hydrograph modeled by two-parameter Gamma probability distribution function assumed that recession follows an exponentially function. In work, instead assuming pre-defined order involved modelling streamflows, BIC test performed establish best fit data. methodology...

10.5540/tema.2018.019.03.0449 article EN DOAJ (DOAJ: Directory of Open Access Journals) 2018-12-01
Coming Soon ...