Efficient parameter estimation in longitudinal data analysis using a hybrid GEE method

The method of generalized estimating equations (GEEs) provides consistent estimates of the regression parameters in a marginal regression model for longitudinal data, even when the working correlation model is misspecified (Liang and Zeger, 1986). However, the efficiency of a GEE estimate can be seriously affected by the choice of the working correlation model. This study addresses this problem by proposing a hybrid method that combines multiple GEEs based on different working correlation models, using the empirical likelihood method (Qin and Lawless, 1994). Analyses show that this hybrid method is more efficient than a GEE using a misspecified working correlation model. Furthermore, if one of the working correlation structures correctly models the within-subject correlations, then this hybrid method provides the most efficient parameter estimates. In simulations, the hybrid method's finite-sample performance is superior to a GEE under any of the commonly used working correlation models and is almost fully efficient in all scenarios studied. The hybrid method is illustrated using data from a longitudinal study of the respiratory infection rates in 275 Indonesian children.

Criteria for working-correlation-structure selection in GEE: Assessment via simulation

Efficiency of analysis using generalized estimation equations is enhanced when intracluster correlation structure is accurately modeled. We compare two existing criteria (a quasi-likelihood information criterion, and the Rotnitzky-Jewell criterion) to identify the true correlation structure via simulations with Gaussian or binomial response, covariates varying at cluster or observation level, and exchangeable or AR(l) intracluster correlation structure. Rotnitzky and Jewell's approach performs better when the true intracluster correlation structure is exchangeable, while the quasi-likelihood criteria performs better for an AR(l) structure.

[Le cheval de course Flowershop monté par le jockey Mac Gee, gagnant du prix de Diane, se tenant exceptionnellement à Lonchamp le 6/6/20] : [photographie de presse] / [Agence Rol]

Référence bibliographique : Rol, 59578

Correlation structure and model selection for negative binomial distribution in GEE

A new model selection criterion, termed as the “quasi-likelihood under the independence model criterion” (QIC), was proposed by Pan (2001) for GEE models. Cui (2007) developed a general computing program to implement the QIC method for a range of statistical distributions. However, only a special case of the negative binomial distribution was considered in Cui (2007), where the dispersion parameter equals to unity. This article introduces a new computing program that can be applied for the general negative binomial model, where the dispersion parameter can be any fixed value. An example is also given in this article.

Selection of working correlation structure and best model in GEE analyses of longitudinal data

The Generalized Estimating Equations (GEE) method is one of the most commonly used statistical methods for the analysis of longitudinal data in epidemiological studies. A working correlation structure for the repeated measures of the outcome variable of a subject needs to be specified by this method. However, statistical criteria for selecting the best correlation structure and the best subset of explanatory variables in GEE are only available recently because the GEE method is developed on the basis of quasi-likelihood theory. Maximum likelihood based model selection methods, such as the widely used Akaike Information Criterion (AIC), are not applicable to GEE directly. Pan (2001) proposed a selection method called QIC which can be used to select the best correlation structure and the best subset of explanatory variables. Based on the QIC method, we developed a computing program to calculate the QIC value for a range of different distributions, link functions and correlation structures. This program was written in Stata software. In this article, we introduce this program and demonstrate how to use it to select the most parsimonious model in GEE analyses of longitudinal data through several representative examples.

纵向数据准似然独立准则在GEE模型中的应用纵向数据准似然独立准则在GEE模型中的应用

目的 探讨医学研究中纵向数据广义估计方程(GEE)的准似然独立准则(QIC)分析技术,应用此技术结合医学实例说明.方法采用Stata10.0软件,对GEE进行QIC分析并找出最佳模型.结果比较不同的工作相关结构后,可交换相关结构的QIC值最小,因此被选为最佳结构模型.在此基础上,最佳GEE模型也被选出.结论利用Stata软件,使用该方法通过临床实例的计算,得到的最佳模型更科学和有说服力,其优势在于用QIC标准选择了最佳相关结构和最佳模型.当有更多的协变量进行分析时.比较方程的次数较多,需要探索进一步的简化计算程序.

Análise dos recursos do Programa ABC : foco na Amazônia Legal – potencial de redução de GEE e estudo de caso sobre o Programa ABC em Paragominas

Este é o relatório final acerca do desembolso do Programa ABC e que compõe, entre outras, as atividades do segundo ano de trabalho do Observatório do Plano ABC. Seu principal objetivo é analisar quantitativa e qualitativamente o desempenho – contratação – da principal linha de crédito para o financiamento da agricultura de baixa emissão de carbono no Brasil, o Programa ABC. O relatório apresenta as atualizações referentes à parcela da safra 2014/15 (de julho de 2014 a fevereiro de 2015), trazendo, também, uma análise focada nos recursos contratados via BNDES e nas finalidades de investimento às quais se destinam. Além disso, é apresentado um estudo de caso realizado no estado do Pará, e é discutido, também, o potencial de contribuição ao alcance das metas de redução de emissões pela região da Amazônia Legal.

Abertura do Seminário emissões brasileiras de GEE (1990-2012)

O Seminário Estimativa de emissões brasileiras de gases de efeito estufa apresentou as estimativas produzidas por um grupo de instituições e pesquisadores coordenado por Tasso Azevedo, para o período 1990-2012, em uma iniciativa do Observatório do Clima, com apoio de comunicação do GVces. Na ocasião foi lançado o Sistema Estimativas de Emissões de GEE (SEEG)

Estimativa de emissões de GEE no Brasil (1990-2012)

O Seminário estimativa de emissões brasileiras de gases de efeito estufa apresentou as estimativas produzidas por um grupo de instituições e pesquisadores coordenado por Tasso Azevedo, para o período 1990-2012, em uma iniciativa do Observatório do Clima, com apoio de comunicação do GVces. Na ocasião foi lançado o Sistema Estimativas de Emissões de GEE (SEEG)

Nathaniel Gist Gee Papers - Accession 395

The Nathaniel Gist Gee Papers consist of various papers concerning Gee’s years in China including correspondence, reports, newspaper and magazine clippings, Chinese poetry, statistics, manifestos, statements, his professional papers concerned primarily with freshwater sponges, and professional papers and publications he collected that chronicle China’s growth. Many of the records are concerned with China’s political and social changes including China’s Nationalist and Student Movements during Gee’s stay in China. Nathaniel Gist Gee (1876-1937), born in Union, SC, was a professor of Natural Science at Soochow University and Yenching University in China from 1901-1932.

Christine South Gee Papers - Accession 10

The Christine South Gee Papers include family histories; biographical data; annual reports of home demonstration work in South Carolina (1920-1922) compiled by Mrs. Gee; speeches; magazine articles (1935-1963); newspaper clippings (1934-1968); photographs (1903-1954) and certificates of awards. The collection primarily pertains to Mrs. Gee’s work as South Carolina State Home Demonstration Agent (1918-1923); her role in the formation of the South Carolina Extension Homemakers’ Council (1921), formerly the South Carolina Council of Farm Women; her activities as president of the South Carolina Council for the Common Good (1943-1945); her study of development in programs for adult education and rural women; and her historical interest in South Carolina statesmen and political leaders. Family histories include information on the Puckett, Smith, Martin, Hudgens, McNeese, Rodgers, and Saxon families.

Emissão de gases de efeito estufa (GEE) pela pecuária: situação e perspectivas para criação de um mercado de crédito de carbono

O mercado mundial de carbono desenvolveu-se rapidamente com a ratificação do Protocolo de Quioto, sendo considerado como base para a implantação deste mercado. O objetivo do presente estudo foi analisar a situação e perspectivas da emissão de gases de efeito estufa (GEE) pela pecuária, e a possível criação de um mercado de crédito de carbono. Pelos dados levantados, pode-se afirmar que o Brasil tem um grande potencial para a criação deste mercado, por possuir o maior rebanho bovino comercial do mundo e importante participação na emissão de GEE, principalmente o metano. Com um horizonte de crescimento para o setor, a melhora da eficiência técnica e a utilização dos preceitos de sustentabilidade são fatores importantes para quem almeja um desenvolvimento sólido e sustentável.