RESUMO
This paper presents a novel approach for analyzing bivariate positive data, taking into account a covariate vector and left-censored observations, by introducing a hierarchical Bayesian analysis. The proposed method assumes marginal Weibull distributions and employs either a usual Weibull likelihood or Weibull-Tobit likelihood approaches. A latent variable or frailty is included in the model to capture the possible correlation between the bivariate responses for the same sampling unit. The posterior summaries of interest are obtained through Markov Chain Monte Carlo methods. To demonstrate the effectiveness of the proposed methodology, we apply it to a bivariate data set from stellar astronomy that includes left-censored observations and covariates. Our results indicate that the new bivariate model approach, which incorporates the latent factor to capture the potential dependence between the two responses of interest, produces accurate inference results. We also compare the two models using the different likelihood approaches (Weibull or Weibull-Tobit likelihoods) in the application. Overall, our findings suggest that the proposed hierarchical Bayesian analysis is a promising approach for analyzing bivariate positive data with left-censored observations and covariate information.
RESUMO
Cardiovascular diseases (CVD) are the leading cause of death in the world, and they are considered a serious public health problem in Colombia. The main goal of this study was to analyze CVD mortality spatially and temporarily in the Pacific region of Colombia during the 2002-2015 period, and its association with some municipal socio-economic indicators using spatial statistical analysis techniques. It involved a descriptive-ecological study in the 177 municipalities of the Pacific region that used CVD mortality data, under codes I00-I99 of the International Classification of Diseases (ICD-10), and seven municipal socio-economic indicators. The analysis included the calculation of crude and standardized mortality rates, according to sex, for CVD and its main causes, and modeling of CVD death counts using Bayesian hierarchical models. During the 2002-2015 period, standardized rates of CVD mortality showed a downward trend in men (129.0 to 119.3) and in women (129.0 to 110.0), the main causes of death being ischemic heart diseases, followed by cerebrovascular diseases. In general, the risk of CVD mortality was higher in the less economically and socially privileged municipalities.
Las enfermedades cardiovasculares (ECV) son la principal causa de muerte en el mundo y en Colombia siendo consideradas un serio problema de salud pública. El objetivo de este estudio fue analizar espacial y temporalmente la mortalidad por ECV en la región Pacifico de Colombia durante el periodo 2002-2015 y su asociación con algunos indicadores socioeconómicos municipales usando técnicas estadísticas de análisis espacial. Fue un estudio descriptivo-ecológico en los 177 municipios de la región Pacifico que usó datos de mortalidad por ECV, bajo los códigos I00-I99 de la Clasificación Internacional de Enfermedades (CIE-10), y siete indicadores socioeconómicos municipales. El análisis incluyó cálculo de tasas de mortalidad crudas y estandarizadas, según sexo, para las ECV y sus principales causas, y la modelación del conteo de defunciones usando modelos jerárquicos Bayesianos. Durante el periodo 2002-2015 las tasas estandarizadas de mortalidad por ECV mostraron una tendencia descendente en hombres (129,0 a 119,3) y en mujeres (129,0 a 110,0) siendo las principales causas de muerte las enfermedades isquémicas del corazón, seguidas de las cerebrovasculares. En general, el riesgo de mortalidad por ECV fue mayor en los municipios menos favorecidos económica y socialmente.
Assuntos
Doenças Cardiovasculares , Teorema de Bayes , Doenças Cardiovasculares/epidemiologia , Cidades , Colômbia/epidemiologia , Feminino , Humanos , Masculino , Mortalidade , Fatores SocioeconômicosRESUMO
Resumen Las enfermedades cardiovasculares (ECV) son la principal causa de muerte en el mundo y en Colombia siendo consideradas un serio problema de salud pública. El objetivo de este estudio fue analizar espacial y temporalmente la mortalidad por ECV en la región Pacifico de Colombia durante el periodo 2002-2015 y su asociación con algunos indicadores socioeconómicos municipales usando técnicas estadísticas de análisis espacial. Fue un estudio descriptivo-ecológico en los 177 municipios de la región Pacifico que usó datos de mortalidad por ECV, bajo los códigos I00-I99 de la Clasificación Internacional de Enfermedades (CIE-10), y siete indicadores socioeconómicos municipales. El análisis incluyó cálculo de tasas de mortalidad crudas y estandarizadas, según sexo, para las ECV y sus principales causas, y la modelación del conteo de defunciones usando modelos jerárquicos Bayesianos. Durante el periodo 2002-2015 las tasas estandarizadas de mortalidad por ECV mostraron una tendencia descendente en hombres (129,0 a 119,3) y en mujeres (129,0 a 110,0) siendo las principales causas de muerte las enfermedades isquémicas del corazón, seguidas de las cerebrovasculares. En general, el riesgo de mortalidad por ECV fue mayor en los municipios menos favorecidos económica y socialmente.
Abstract Cardiovascular diseases (CVD) are the leading cause of death in the world, and they are considered a serious public health problem in Colombia. The main goal of this study was to analyze CVD mortality spatially and temporarily in the Pacific region of Colombia during the 2002-2015 period, and its association with some municipal socio-economic indicators using spatial statistical analysis techniques. It involved a descriptive-ecological study in the 177 municipalities of the Pacific region that used CVD mortality data, under codes I00-I99 of the International Classification of Diseases (ICD-10), and seven municipal socio-economic indicators. The analysis included the calculation of crude and standardized mortality rates, according to sex, for CVD and its main causes, and modeling of CVD death counts using Bayesian hierarchical models. During the 2002-2015 period, standardized rates of CVD mortality showed a downward trend in men (129.0 to 119.3) and in women (129.0 to 110.0), the main causes of death being ischemic heart diseases, followed by cerebrovascular diseases. In general, the risk of CVD mortality was higher in the less economically and socially privileged municipalities.
Assuntos
Humanos , Masculino , Feminino , Doenças Cardiovasculares/epidemiologia , Fatores Socioeconômicos , Mortalidade , Teorema de Bayes , Cidades , Colômbia/epidemiologiaRESUMO
In this study, the components of extra-Poisson variability are estimated assuming random effect models under a Bayesian approach. A standard existing methodology to estimate extra-Poisson variability assumes a negative binomial distribution. The obtained results show that using the proposed random effect model it is possible to get more accurate estimates for the extra-Poisson variability components when compared to the use of a negative binomial distribution where it is possible to estimate only one component of extra-Poisson variability. Some illustrative examples are introduced considering real data sets.
RESUMO
Road or urban traffic accidents in Brazil have a large presence in external causes of mortality. The main goal of this study is to discover significant factors in the incidence of accidents on Brazilian highways based on a database with information on each person injured on federal highways in Brazil reported by the Federal Highway Police. Some factors are considered in the study as cause of the accident, type of accident, stage of the day, weather condition, highway type, highway facility, age of the victim, gender of the victim and type of vehicle. From the obtained results of chi-square tests and logistic regression models, it was observed statistical dependence (p < 0.05) of the occurrence of injured people with serious injuries and the factors cause of the accident, type of accident, day, highway type and vehicle type. Considering the dead victims, the covariates age, time of day, highway type, highway facility, gender and type of vehicle showed significance (p < 0.05). These results are of great interest for authorities to increase road enforcement, improve highway facilities and target the production of vehicles with better safety standards.
Assuntos
Acidentes de Trânsito , Tempo (Meteorologia) , Ferimentos e Lesões/fisiopatologia , Acidentes de Trânsito/mortalidade , Adolescente , Adulto , Brasil/epidemiologia , Criança , Pré-Escolar , Bases de Dados Factuais , Feminino , Humanos , Modelos Logísticos , Masculino , Pessoa de Meia-Idade , Índices de Gravidade do Trauma , Adulto JovemRESUMO
In time-to-event studies it is common the presence of a fraction of individuals not expecting to experience the event of interest; these individuals who are immune to the event or cured for the disease during the study are known as long-term survivors. In addition, in many studies it is observed two lifetimes associated to the same individual, and in some cases there exists a dependence structure between them. In these situations, the usual existing lifetime distributions are not appropriate to model data sets with long-term survivors and dependent bivariate lifetimes. In this study, it is proposed a bivariate model based on a Weibull standard distribution with a dependence structure based on fifteen different copula functions. We assumed the Weibull distribution due to its wide use in survival data analysis and its greater flexibility and simplicity, but the presented methods can be adapted to other continuous survival distributions. Three examples, considering real data sets are introduced to illustrate the proposed methodology. A Bayesian approach is assumed to get the inferences for the parameters of the model where the posterior summaries of interest are obtained using Markov Chain Monte Carlo simulation methods and the Openbugs software. For the data analysis considering different real data sets it was assumed fifteen different copula models from which is was possible to find models with satisfactory fit for the bivariate lifetimes in presence of long-term survivors.
RESUMO
Resumen Objetivo: Describir el perfil y la tendencia de la mortalidad general y específica, durante el periodo 2002-2014, de los departamentos de la región del Pacífico de Colombia: Cauca, Chocó, Nariño y Valle del Cauca. Metodología: Estudio descriptivo-ecológico que usa datos secundarios de mortalidad, nacimientos y proyecciones poblacionales provenientes del Departamento Administrativo Nacional de Estadística. Se calcularon tasas anuales de mortalidad general y específicas (por edad, sexo y para seis grandes grupos de causas de muerte), utilizando la lista corta de clasificación de las causas de mortalidad 6/67 de la Organización Panamericana de la Salud (enfermedades transmisibles, neoplasias/tumores, enfermedades del sistema circulatorio, afecciones originadas en el período perinatal, causas externas y demás causas). Las tendencias fueron evaluadas mediante un modelo de regresión de Poisson con efectos aleatorios. Resultados: Se encontró mayor mortalidad en el sexo masculino (razón hombre / mujer entre 1,26-1,61) y en la población mayor a 65 años. Se observó una tendencia descendente en la mortalidad general en los cuatro departamentos, siendo Valle del Cauca el que presentó las mayores tasas de mortalidad general y específica. La principal causa de muerte, y con tendencia ascendente, fueron las enfermedades del sistema circulatorio, seguida de demás causas, causas externas y neoplasias. Conclusiones: La mortalidad general mostró una tendencia descendente, con mayor magnitud en hombres, y riesgo diferencial según sexo a partir de 15-19 años, atribuido al grupo de causas externas. La principal causa de muerte fueron las enfermedades del sistema circulatorio, seguido de todas las demás causas y neoplasias. Las causas externas mostraron una marcada tendencia al descenso.
Abstract Objective: To describe the profile and trend of overall and cause-specific mortality, during the period 2002-2014, of the departments of the Pacific region of Colombia: Cauca, Chocó, Nariño and Valle del Cauca. Methodology: Descriptive-ecological study that uses secondary data on mortality, births and population projections from the Departamento Administrativo Nacional de Estadística (DANE). Annual overall and cause-specific mortality rates were calculated (by age, sex and for six large groups of causes of death), using the short list of causes of death 6/67 PAHO (communicable diseases, neoplasms/tumors, diseases of the circulatory system, conditions originating in the perinatal period, external causes and other causes). Trends were evaluated using a Poisson regression model with random effects. Results: Higher mortality was found in males (male/female ratio between 1.26-1.61) and in the population over 65 years of age. A downward trend was observed in overall mortality in the four departments, with Valle del Cauca having the highest overall and cause-specific mortality rates. The main cause of death, and with an upward trend, were diseases of the circulatory system, followed by other causes, external causes and neoplasms. Conclusions: Overall mortality showed a downward trend, of greater magnitude in men, and differential risk according to sex from 15-19 years attributed to the group of external causes. The main cause of death was diseases of the circulatory system, followed by all other causes and neoplasms. External causes showed a marked downward trend.
Resumo Objetivo: Descrever o perfil e a tendência da mortalidade geral e específica, durante o período 2002-2014, dos departamentos da região do Pacífico da Colômbia: Cauca, Chocó, Nariño e Valle del Cauca. Metodologia: Estudo descritivo-ecológico que utiliza dados secundários sobre mortalidade, nascimentos e projeções populacionais do Departamento Administrativo Nacional de Estatística (DANE). Calcularam-se taxas anuais de mortalidade geral e específica (por idade, sexo e para seis grandes grupos de causas de morte), usando a lista curta de classificação de causas de mortalidade 6/67 OPAS (doenças transmissíveis, neoplasias / tumores, doenças do sistema circulatório, condições originadas no período perinatal, causas externas e outras causas). As tendências foram avaliadas através de um modelo de regressão de Poisson com efeitos aleatórios. Resultados: Maior mortalidade foi encontrada no sexo masculino (razão homem / mulher entre 1,26-1,61) e na população acima de 65 anos. Uma tendência descendente na mortalidade geral foi observada nos quatro departamentos, sendo o Valle del Cauca aquele com as maiores taxas de mortalidade geral e específica. As principais causas de morte, e com tendência ascendente, foram as doenças do sistema circulatório, seguidas por outras causas, causas externas e neoplasias. Conclusões: A mortalidade geral apresentou tendência descendente, com maior magnitude nos homens, e risco diferencial segundo o sexo partindo de 15-19 anos, atribuído ao grupo de causas externas. As principais causas de morte foram as doenças do sistema circulatório, seguido por todas as outras causas e neoplasias. As causas externas mostraram uma tendência acentuada ao declínio.
RESUMO
Generic drugs have been commercialized in numerous countries. Most of these countries approve the commercialization of a generic drug when there is evidence of bioequivalence between the generic drug and the reference drug. Generally, the pharmaceutical industry is responsible for the bioequivalence test under the supervision of a regulatory agency. This procedure is concluded after a statistical data analysis. Several agencies adopt a standard statistical analysis based on procedures that were previously established. In practice, we face situations in which this standard model does not fit to some sets of bioequivalence data. In this study, we propose an evaluation of bioequivalence using univariate and bivariate models based on an extended generalized gamma distribution and a skew-t distribution, under a Bayesian perspective. We introduce a study of the empirical power of hypothesis tests for univariate models, showing advantages in the use of an extended generalized gamma distribution. Three sets of bioequivalence data were analyzed under these new procedures and compared with the standard model proposed by the majority of regulatory agencies. In order to verify that the asymmetrical distributions are usually better fitted for the data, when compared with the standard model, model discrimination methods were used, such as the Deviance Information Criterion (DIC) and quantile-quantile plots. The research concluded that, in general, the use of the extended generalized gamma distribution may be more appropriate to model bioequivalence data in the original scale. Copyright © 2016 John Wiley & Sons, Ltd.
Assuntos
Teorema de Bayes , Medicamentos Genéricos , Equivalência Terapêutica , Interpretação Estatística de Dados , Humanos , Distribuições EstatísticasRESUMO
OBJECTIVE: The aim of this study was to analyze social characteristics and stress as correlates of cigarette smoking in adolescence. The main intent was to identify elements that distinguish adolescents who had experimented with smoking and did not progress to regular smoking from those who became current smokers. METHODS: Students at 10 high schools in the city of Ribeirão Preto, Brazil, completed a questionnaire based on an instrument employed in a similar large-scale study. The students were classified as never-smokers or experimenters. The experimenters were subcategorized as having become current smokers or nonprogressors. Analyses were performed using adjusted logistic models. RESULTS: A total of 2,014 students (mean age, 16.2 ± 1.1 years; females, 53%) completed the questionnaire. We categorized 1,283 students (63.7%) as never-smokers, 244 (12.1%) as current smokers, and 487 (24.2%) as nonprogressors. We found that experimentation with smoking was associated with being held back a grade in school (OR = 1.80), alcohol intake (low/occasional, OR = 8.92; high/regular, OR = 2.64), illicit drug use (OR = 9.32), having a sibling or cousin who smokes (OR = 1.39), having a friend who smokes (OR = 2.08), and high levels of stress (in females only, OR = 1.32). Factors associated with an increased risk of transitioning from experimenter to current smoker were alcohol intake (low/occasional, OR = 3.28; high/regular, OR = 2.16), illicit drug use (OR = 3.61), and having a friend who smokes (OR = 7.20). CONCLUSIONS: Current smoking was associated with a profile of socioeconomic correlates different from that associated with experimentation only. Our data (showing that current smoking was associated with having a friend who smokes, ...
OBJETIVO: Analisar características sociais e estresse como correlatos de consumo de cigarros na adolescência. O principal objetivo foi identificar elementos que distingam adolescentes que experimentaram cigarros e não progrediram para o tabagismo regular daqueles que se tornaram fumantes correntes. MÉTODOS: Estudantes de 10 escolas do ensino médio de Ribeirão Preto responderam um questionário baseado em instrumento empregado em um estudo com escala semelhante. Os estudantes foram classificados em indivíduos que nunca fumaram (NF) e experimentadores de cigarros (E). O grupo E foi subcategorizado em fumantes atuais e indivíduos que não progrediram para tabagismo corrente. As análises foram realizadas usando modelos logísticos ajustados. RESULTADOS: Um total de 2.014 estudantes (16,2 ± 1,1 anos; mulheres, 53%) responderam o questionário. Categorizamos 1.283 alunos (63,7%) em nunca fumantes, 244 (12,1%) como fumantes atuais e 487 (24,2%) como não progressores. A experimentação de cigarros foi associada a repetição de anos na escola (OR = 1,80), consumo de álcool (baixo/ocasional, OR = 8,92; intenso/frequente, OR = 2,64), uso de drogas ilícitas (OR = 9,32), fumantes entre irmãos ou primos (OR = 1,39), fumantes entre amigos (OR = 2,08) e níveis elevados de estresse (apenas em mulheres, OR = 1,32). Fatores associados com um risco maior de passar de experimentador de cigarros para fumante atual foram consumo de álcool (baixo/ocasional, OR = 3,28; regular/elevado, OR = 2,16), uso de drogas ilícitas (OR = 3,61) e amigos fumantes (OR = 7,20). CONCLUSÕES: O tabagismo atual associou-se com um perfil de correlatos soc...
Assuntos
Adolescente , Feminino , Humanos , Masculino , Comportamento do Adolescente , Estresse Fisiológico , Fumar/epidemiologia , Tabagismo/epidemiologia , Brasil/epidemiologia , Estudos Transversais , Fatores de Risco , Fatores Sexuais , Inquéritos e Questionários , Fumar/psicologia , Estudantes/estatística & dados numéricos , Tabagismo/etiologia , Tabagismo/psicologiaRESUMO
2013 marked the 250th anniversary of the presentation of Bayes' theorem by the philosopher Richard Price. Thomas Bayes was a figure little known in his own time, but in the 20th century the theorem that bears his name became widely used in many fields of research. The Bayes theorem is the basis of the so-called Bayesian methods, an approach to statistical inference that allows studies to incorporate prior knowledge about relevant data characteristics into statistical analysis. Nowadays, Bayesian methods are widely used in many different areas such as astronomy, economics, marketing, genetics, bioinformatics and social sciences. This study observed that a number of authors discussed recent advances in techniques and the advantages of Bayesian methods for the analysis of epidemiological data. This article presents an overview of Bayesian methods, their application to epidemiological research and the main areas of epidemiology which should benefit from the use of Bayesian methods in coming years.
Assuntos
Teorema de Bayes , Estudos Epidemiológicos , Previsões , HumanosRESUMO
OBJECTIVE: The aim of this study was to analyze social characteristics and stress as correlates of cigarette smoking in adolescence. The main intent was to identify elements that distinguish adolescents who had experimented with smoking and did not progress to regular smoking from those who became current smokers. METHODS: Students at 10 high schools in the city of Ribeirão Preto, Brazil, completed a questionnaire based on an instrument employed in a similar large-scale study. The students were classified as never-smokers or experimenters. The experimenters were subcategorized as having become current smokers or nonprogressors. Analyses were performed using adjusted logistic models. RESULTS: A total of 2,014 students (mean age, 16.2 ± 1.1 years; females, 53%) completed the questionnaire. We categorized 1,283 students (63.7%) as never-smokers, 244 (12.1%) as current smokers, and 487 (24.2%) as nonprogressors. We found that experimentation with smoking was associated with being held back a grade in school (OR = 1.80), alcohol intake (low/occasional, OR = 8.92; high/regular, OR = 2.64), illicit drug use (OR = 9.32), having a sibling or cousin who smokes (OR = 1.39), having a friend who smokes (OR = 2.08), and high levels of stress (in females only, OR = 1.32). Factors associated with an increased risk of transitioning from experimenter to current smoker were alcohol intake (low/occasional, OR = 3.28; high/regular, OR = 2.16), illicit drug use (OR = 3.61), and having a friend who smokes (OR = 7.20). CONCLUSIONS: Current smoking was associated with a profile of socioeconomic correlates different from that associated with experimentation only. Our data (showing that current smoking was associated with having a friend who smokes, alcohol intake, and illicit drug use) suggest the need for comprehensive approaches to discourage substance use during adolescence.
OBJETIVO: Analisar características sociais e estresse como correlatos de consumo de cigarros na adolescência. O principal objetivo foi identificar elementos que distingam adolescentes que experimentaram cigarros e não progrediram para o tabagismo regular daqueles que se tornaram fumantes correntes. MÉTODOS: Estudantes de 10 escolas do ensino médio de Ribeirão Preto responderam um questionário baseado em instrumento empregado em um estudo com escala semelhante. Os estudantes foram classificados em indivíduos que nunca fumaram (NF) e experimentadores de cigarros (E). O grupo E foi subcategorizado em fumantes atuais e indivíduos que não progrediram para tabagismo corrente. As análises foram realizadas usando modelos logísticos ajustados. RESULTADOS: Um total de 2.014 estudantes (16,2 ± 1,1 anos; mulheres, 53%) responderam o questionário. Categorizamos 1.283 alunos (63,7%) em nunca fumantes, 244 (12,1%) como fumantes atuais e 487 (24,2%) como não progressores. A experimentação de cigarros foi associada a repetição de anos na escola (OR = 1,80), consumo de álcool (baixo/ocasional, OR = 8,92; intenso/frequente, OR = 2,64), uso de drogas ilícitas (OR = 9,32), fumantes entre irmãos ou primos (OR = 1,39), fumantes entre amigos (OR = 2,08) e níveis elevados de estresse (apenas em mulheres, OR = 1,32). Fatores associados com um risco maior de passar de experimentador de cigarros para fumante atual foram consumo de álcool (baixo/ocasional, OR = 3,28; regular/elevado, OR = 2,16), uso de drogas ilícitas (OR = 3,61) e amigos fumantes (OR = 7,20). CONCLUSÕES: O tabagismo atual associou-se com um perfil de correlatos socioeconômicos diferentes daqueles associados apenas à experimentação. Nossos achados (tabagismo atual associou-se a amigos fumantes, consumo de álcool e de drogas ilícitas) sugerem a necessidade de abordagens abrangentes para o desencorajamento do uso dessas substâncias na adolescência.
Assuntos
Comportamento do Adolescente , Fumar/epidemiologia , Estresse Fisiológico , Tabagismo/epidemiologia , Adolescente , Brasil/epidemiologia , Estudos Transversais , Feminino , Humanos , Masculino , Fatores de Risco , Fatores Sexuais , Fumar/psicologia , Estudantes/estatística & dados numéricos , Inquéritos e Questionários , Tabagismo/etiologia , Tabagismo/psicologiaRESUMO
OBJECTIVES: To characterize a motivational profile of reasons for smoking among teenagers. To investigate the influence of clinical and social elements on observed scores. METHODS: High school students who smoked in the past month (n = 226; age, 16.4 ± 10 years; 46.5% male) answered a questionnaire during school time. The instrument included the University of São Paulo Reasons for Smoking Scale (USP-RSS), the Fagerström Test for Nicotine Dependence, and clinical and social information. The USP-RSS scores from 307 healthy adult smokers (67.5% male; age, 37.9 ± 11.2 years) were also used for comparisons. RESULTS: Most of the adolescents (90.2%) exhibited low or very low levels of nicotine addiction (median Fagerström Test for Nicotine Dependence score 0, range 0 to 8). The mean scores of the USP-RSS subscales were as follows: Addiction, 1.9 ± 1.1; Pleasure From Smoking, 3.0 ± 1.3; Tension Reduction, 2.4 ± 1.3; Stimulation, 1.9 ± 0.9; Automatism, 1.3 ± 0.6; Handling, 2.3 ± 1.1; Social Smoking, 1.9 ± 1.0; Weight Control, 1.4 ± 1.0; and Affiliative Attachment, 1.6 ± 0.9. In comparison with adults, teenagers exhibited lower scores for Addiction, Pleasure From Smoking, Tension Reduction, Automatism, Weight Control, and Affiliative Attachment and higher scores for Social Smoking (P < 0.05). Older age, past school failure, illicit drugs use, alcohol abuse, high levels of perceived stress, and the death of at least one parent were associated with high scores for all subscales. CONCLUSIONS: The USP-RSS subscales Addiction, Pleasure From Smoking, and Social Smoking were important factors for adolescent smoking. Comparisons with adult smokers stressed the importance of the component of Social Smoking. The identification of distinctive factors that drive teenagers to smoke might help in making decisions dealing with interventions aimed at smoking cessation and control.
Assuntos
Alcoolismo , Motivação , Fumar , Estresse Psicológico/epidemiologia , Tabagismo/psicologia , Adolescente , Comportamento do Adolescente , Adulto , Fatores Etários , Alcoolismo/epidemiologia , Alcoolismo/psicologia , Brasil/epidemiologia , Comorbidade , Feminino , Humanos , Masculino , Fisiologia Comparada , Fatores de Risco , Fumar/epidemiologia , Fumar/psicologia , Comportamento Social , Estudantes/psicologia , Estudantes/estatística & dados numéricos , Inquéritos e QuestionáriosRESUMO
The study was designed to investigate the impact of air pollution on monthly inhalation/nebulization procedures in Ribeirão Preto, São Paulo State, Brazil, from 2004 to 2010. To assess the relationship between the procedures and particulate matter (PM(10)) a Bayesian Poisson regression model was used, including a random factor that captured extra-Poisson variability between counts. Particulate matter was associated with the monthly number of inhalation/nebulization procedures, but the inclusion of covariates (temperature, precipitation, and season of the year) suggests a possible confounding effect. Although other studies have linked particulate matter to an increasing number of visits due to respiratory morbidity, the results of this study suggest that such associations should be interpreted with caution.
Assuntos
Poluentes Atmosféricos/toxicidade , Poluição do Ar , Material Particulado/toxicidade , Doenças Respiratórias/induzido quimicamente , Administração por Inalação , Brasil , Incêndios , Humanos , Estações do Ano , População UrbanaRESUMO
The study was designed to investigate the impact of air pollution on monthly inhalation/nebulization procedures in Ribeirão Preto, São Paulo State, Brazil, from 2004 to 2010. To assess the relationship between the procedures and particulate matter (PM10) a Bayesian Poisson regression model was used, including a random factor that captured extra-Poisson variability between counts. Particulate matter was associated with the monthly number of inhalation/nebulization procedures, but the inclusion of covariates (temperature, precipitation, and season of the year) suggests a possible confounding effect. Although other studies have linked particulate matter to an increasing number of visits due to respiratory morbidity, the results of this study suggest that such associations should be interpreted with caution.
O objetivo foi investigar os possíveis efeitos da poluição atmosférica nas contagens mensais de procedimentos de inalação/nebulização no Município de Ribeirão Preto, São Paulo, Brasil, no período de 2004 a 2010. Para verificar a relação existente entre os procedimentos e o material particulado (MP10) foi assumido um modelo bayesiano de regressão de Poisson, na presença de um fator aleatório que captura a variabilidade extra Poisson entre as contagens. O material particulado mostrou-se associado ao número de inalações/nebulizações, mas a inserção de covariáveis (temperatura, precipitação e estação) sugere um possível efeito de confundimento. Embora outros estudos relacionem o material particulado com o aumento do número de atendimentos em decorrência de morbidades, os resultados do presente trabalho sugerem que estas associações devem ser interpretadas com cautela.
Assuntos
Humanos , Poluição do Ar , Poluentes Atmosféricos/toxicidade , Material Particulado/toxicidade , Doenças Respiratórias/induzido quimicamente , Administração por Inalação , Brasil , Incêndios , Estações do Ano , População UrbanaRESUMO
INTRODUCTION: Malaria is a serious problem in the Brazilian Amazon region, and the detection of possible risk factors could be of great interest for public health authorities. The objective of this article was to investigate the association between environmental variables and the yearly registers of malaria in the Amazon region using Bayesian spatiotemporal methods. METHODS: We used Poisson spatiotemporal regression models to analyze the Brazilian Amazon forest malaria count for the period from 1999 to 2008. In this study, we included some covariates that could be important in the yearly prediction of malaria, such as deforestation rate. We obtained the inferences using a Bayesian approach and Markov Chain Monte Carlo (MCMC) methods to simulate samples for the joint posterior distribution of interest. The discrimination of different models was also discussed. RESULTS: The model proposed here suggests that deforestation rate, the number of inhabitants per km², and the human development index (HDI) are important in the prediction of malaria cases. CONCLUSIONS: It is possible to conclude that human development, population growth, deforestation, and their associated ecological alterations are conducive to increasing malaria risk. We conclude that the use of Poisson regression models that capture the spatial and temporal effects under the Bayesian paradigm is a good strategy for modeling malaria counts.
INTRODUÇÃO: A malaria é uma doença endêmica na região da Amazônia Brasileira, e a detecção de possíveis fatores de risco pode ser de grande interesse às autoridades em saúde pública. O objetivo deste artigo é investigar a associação entre variáveis ambientais e os registros anuais de malária na região amazônica usando métodos bayesianos espaço-temporais. MÉTODOS: Utilizaram-se modelos de regressão espaço-temporais de Poisson para analisar os dados anuais de contagem de casos de malária entre os anos de 1999 a 2008, considerando a presença de alguns fatores como a taxa de desflorestamento. Em uma abordagem bayesiana, as inferências foram obtidas por métodos Monte Carlo em cadeias de Markov (MCMC) que simularam amostras para a distribuição conjunta a posteriori de interesse. A discriminação de diferentes modelos também foi discutida. RESULTADOS: O modelo aqui proposto sugeriu que a taxa de desflorestamento, o número de habitants por km² e o índice de desenvolvimento humano (IDH) são importantes para a predição de casos de malária. CONCLUSÕES: É possível concluir que o desenvolvimento humano, o crescimento populacional, o desflorestamento e as alterações ecológicas associadas a estes fatores estão associados ao aumento do risco de malária. Pode-se ainda concluir que o uso de modelos de regressão de Poisson que capturam o efeito temporal e espacial em um enfoque bayesiano é uma boa estratégia para modelar dados de contagem de malária.
Assuntos
Humanos , Conservação dos Recursos Naturais , Meio Ambiente , Malária/epidemiologia , Brasil , Distribuição de Poisson , Análise de Regressão , Fatores de Risco , ÁrvoresRESUMO
Teenage pregnancy is a common public health problem worldwide. The objective of this ecological study was to investigate the spatial association between teenage pregnancy rates and socioeconomic characteristics of municipalities in São Paulo State, Southeast Brazil. We used a Bayesian model with a spatial distribution following a conditional autoregressive (CAR) form based on Markov Chain Monte Carlo algorithm. We used data from the Live Birth Information System (SINASC) and the Brazilian Institute of Geography and Statistics (IBGE). Early pregnancy was more frequent in municipalities with lower per capital gross domestic product (GDP), higher poverty rate, smaller population, lower human development index (HDI), and a higher percentage of individuals with State social vulnerability index of 5 or 6 (more vulnerable). The study demonstrates a significant association between teenage pregnancy and socioeconomic indicators.
Assuntos
Gravidez na Adolescência/estatística & dados numéricos , Fatores Socioeconômicos , Adolescente , Teorema de Bayes , Brasil/epidemiologia , Escolaridade , Feminino , Humanos , Método de Monte Carlo , Gravidez , Taxa de GravidezRESUMO
A gravidez na adolescência é um problema de saúde pública comum em todo o mundo. O objetivo deste estudo ecológico é estudar o padrão espacial da associação entre os percentuais de gravidez na adolescência e características socioeconômicas dos municípios do Estado de São Paulo, Brasil. Para isso, foi utilizado um modelo bayesiano com uma distribuição espacial que segue uma estrutura condicional autorregressiva (CAR), baseado em algoritmos Monte Carlo em cadeias de Markov (MCMC). Foram usados dados do Sistema de Informações sobre Nascidos Vivos (SINASC) e do Instituto Brasileiro de Geografia e Estatística (IBGE). Verificou-se que a ocorrência de gravidezes precoces apresentou-se maior nos municípios de menor produto interno bruto (PIB) per capita, com maior incidência de pobreza, de menor tamanho populacional, menor índice de desenvolvimento humano (IDH) e maior percentual de indivíduos com índice paulista de vulnerabilidade social (IPVS) igual a 5 ou 6, ou seja, mais vulneráveis. O estudo demonstra uma estreita associação entre gravidez na adolescência e indicadores econômicos e sociais.
Teenage pregnancy is a common public health problem worldwide. The objective of this ecological study was to investigate the spatial association between teenage pregnancy rates and socioeconomic characteristics of municipalities in São Paulo State, Southeast Brazil. We used a Bayesian model with a spatial distribution following a conditional autoregressive (CAR) form based on Markov Chain Monte Carlo algorithm. We used data from the Live Birth Information System (SINASC) and the Brazilian Institute of Geography and Statistics (IBGE). Early pregnancy was more frequent in municipalities with lower per capital gross domestic product (GDP), higher poverty rate, smaller population, lower human development index (HDI), and a higher percentage of individuals with State social vulnerability index of 5 or 6 (more vulnerable). The study demonstrates a significant association between teenage pregnancy and socioeconomic indicators.
Assuntos
Adolescente , Feminino , Humanos , Gravidez , Gravidez na Adolescência/estatística & dados numéricos , Fatores Socioeconômicos , Teorema de Bayes , Brasil , Escolaridade , Método de Monte Carlo , Taxa de GravidezRESUMO
INTRODUCTION: Malaria is a serious problem in the Brazilian Amazon region, and the detection of possible risk factors could be of great interest for public health authorities. The objective of this article was to investigate the association between environmental variables and the yearly registers of malaria in the Amazon region using bayesian spatiotemporal methods. METHODS: We used Poisson spatiotemporal regression models to analyze the Brazilian Amazon forest malaria count for the period from 1999 to 2008. In this study, we included some covariates that could be important in the yearly prediction of malaria, such as deforestation rate. We obtained the inferences using a bayesian approach and Markov Chain Monte Carlo (MCMC) methods to simulate samples for the joint posterior distribution of interest. The discrimination of different models was also discussed. RESULTS: The model proposed here suggests that deforestation rate, the number of inhabitants per km², and the human development index (HDI) are important in the prediction of malaria cases. CONCLUSIONS: It is possible to conclude that human development, population growth, deforestation, and their associated ecological alterations are conducive to increasing malaria risk. We conclude that the use of Poisson regression models that capture the spatial and temporal effects under the bayesian paradigm is a good strategy for modeling malaria counts.
Assuntos
Conservação dos Recursos Naturais , Meio Ambiente , Malária/epidemiologia , Brasil , Humanos , Distribuição de Poisson , Análise de Regressão , Fatores de Risco , ÁrvoresRESUMO
Na área das finanças, modelos como o ARCH (autoregressive conditional heteroscedaticity), GARCH (general autoregressive conditional heteroscedasticity) e o modelo de volatilidade estocástica (MVE) são amplamente utilizados na análise de séries de tempo. Por outro lado, essas ferramentas são pouco difundidas na área da saúde. No presente estudo, buscamos transportar os conceitos do MVE para a análise dos registros de doações de sangue do Hemocentro de Ribeirão Preto, São Paulo, realizadas no período de julho de 1996 a junho de 2005. Para isso, utilizamos uma modelagem bayesiana baseada em métodos Monte Carlo em cadeia de Markov. Esse modelo é capaz de apontar os períodos de maior alteração do fluxo de doadores de sangue captados na rotina mensal do Hemocentro ao longo dos anos, e os seus resultados são de grande utilidade para o planejamento de campanhas de doação e captação de doadores, quando identificados os períodos mais críticos para os estoques de bolsas de sangue. O MVE evidencia que, nos anos que compõem o período estudado, o número de doações é caracterizado por uma grande diminuição no número de doações em dezembro, um aumento posterior no mês de janeiro e novamente uma queda em fevereiro.
In studies from the financial literature, models as ARCH (autoregressive conditional heteroscedaticity), GARCH (general autoregressive conditional heteroscedasticity) and the volatility stochastic model are extensively used in the analysis of time series. However, the application of these tools in the health is inexpressive. In the present study, we aimed to adapt the concepts from the volatility stochastic model to the analysis of the records of blood donors who attend Ribeirão Preto Blood Center, São Paulo, Brazil, between July 1996 and June 2005. For this purpose, we used a Bayesian approach based in Markov chain Monte Carlo (MCMC) methods. This model can identify the periods of time when the flux of blood donations collected in the mensal routine of the Blood Center is subject to the largest variation over the years, and its results are very useful for the planning of donation campaigns and search for blood donors, when the most critical periods of blood supply are identified. The volatility stochastic model shows that in the studied period, there is a large decrease in the number of blood donations in December, a subsequent increase in January, and a new decrease in February.
RESUMO
Sensitivity and specificity are measures that allow us to evaluate the performance of a diagnostic test. In practice, it is common to have situations where a proportion of selected individuals cannot have the real state of the disease verified, since the verification could be an invasive procedure, as occurs with biopsy. This happens, as a special case, in the diagnosis of prostate cancer, or in any other situation related to risks, that is, not practicable, nor ethical, or in situations with high cost. For this case, it is common to use diagnostic tests based only on the information of verified individuals. This procedure can lead to biased results or workup bias. In this paper, we introduce a Bayesian approach to estimate the sensitivity and the specificity for two diagnostic tests considering verified and unverified individuals, a result that generalizes the usual situation based on only one diagnostic test.