Multivariate generalized linear mixed models (MGLMM) are used for jointly modeling the clustered mixed outcomes obtained when there are two or more responses repeatedly measured on each individual in scientific studies. The relationship among these responses is often of interest. In the clustered mixed data, the correlation could be present between repeated measurements either within the same observer or between different observers on the same subjects. This study proposes a series of in- dices, namely, intra, inter and total correlation coefficients, to measure the correlation under various circumstances of observations from a multivariate generalized linear model, especially for joint modeling of clustered count and continuous outcomes. Bayesian methods are widely used techniques for analyzing MGLMM. The need for noninformative priors arises when there is insufficient prior information on the model parameters. Another aim of this study is to propose an approximate uniform shrinkage prior for the random effect variance components in the Bayesian analysis for the MGLMM. This prior is an extension of the approximate uniform shrinkage prior. This prior is easy to apply and is shown to possess several nice properties. The methods are illustrated in terms of both a simulation study and a case example.

O sistema estrutural de pisos com lajes mistas, também chamadas de lajes com fôrma de aço incorporada e popularmente conhecido como steel deck®, é de desenvolvimento recente no Brasil e tem ganhado espaço na indústria da construção civil. Pesquisas internacionais recentes têm mostrado que os efeitos da retração não-uniforme, da fluência e da fissuração são significativos para a evolução dos deslocamentos verticais. No entanto, não há referências na literatura nacional de investigações sobre o tópico, como é usual para as estruturas de concreto armado. Desta forma, o presente trabalho tem como foco estudar o comportamento em serviço de lajes mistas de aço e concreto, com ênfase nos deslocamentos verticais (flechas) diferidos no tempo. São considerados os efeitos da retração e da fluência do concreto, além da interação entre o perfil de aço e o concreto. Um programa experimental exploratório com dois protótipos de lajes mistas idênticas, uma submetida a um carregamento imposto e outra sujeita apenas ao peso próprio, submetidos a um ensaio de longa duração de 260 dias. Os deslocamentos foram medidos diariamente e as condições de temperatura e umidade do ambiente foram monitoradas. Observou-se a evolução das flechas diferidas ao longo dos 260 dias na ordem de 3,20 vezes maior que as flechas imediatas. Ensaios de flexão a quatro pontos foram realizados com as duas lajes submetidas ao ensaio de longa duração e a outras duas com idade de 28 dias, não sendo observado influência do tempo quanto à capacidade resistente das lajes mistas. Finalmente, abordagens analíticas de previsão de flechas foram aplicadas aos protótipos testados e também a outros modelos experimentais presentes na literatura. Os valores previstos por diferentes abordagens de avaliação foram comparados aos resultados experimentais, observando-se que as abordagens que não levam em conta os efeitos da retração não-uniforme e fluência tendem a subestimar a previsão. As abordagens com consideração dos efeitos diferidos apresentaram boa acurácia e destaca-se a importância da consideração dos efeitos dependentes do tempo na previsão dos deslocamentos verticais das lajes estudadas. / The structural floor system using steel-concrete composite slabs also called slabs with profiled steel decking and popularly known as steel deck®, has a recent development in Brazil and has taken space in the civil construction industry. Recent international researches have shown that non-uniform shrinkage, creep and cracking are significant for the time-dependent deflections of those slabs. However, there is no reference in the Brazilian literature of any study investigating the time-dependent behavior of composite slabs, as it is usual for reinforced concrete structures. So, this work focuses on the study of the in-service behavior of steel-concrete composite slabs under long-term conditions. The main emphasis lies on considering the time-dependent effects due to concrete shrinkage and creep, besides the influence of the steel-concrete interaction to calculate the slabs deflections. An exploratory experimental program with two prototypes of identical composite slabs, one subjected to an imposed loading and another subject only to self-weight, submitted to the 260-day long test. During all testing time, they were taken daily measurements of deflection and temperature and humidity conditions were monitored to understand its influence. The time-dependent deflections during the 260-days on the order of 3.20 times greater than the instantaneous deflection were observed. Four-point bending tests were performed with the two slabs submitted to the long-duration test 260-day and two others with a 28-day age. No influence of time was observed on the resistant capacity of composite slabs. Finally, analytical approaches to predict the deflections of the slabs were applied to the prototypes tested and other experimental tests from the literature. The calculated values by different evaluation approaches were compared to the experimental results. The evaluation approaches that do not take into account the effects of non-uniform shrinkage and creep tend to underestimate the previsions. The evaluation approaches considering the time-dependent effects presented good accuracy. The importance of the time-dependent effects for the deflections is demonstrated.