Use of Markov model in a longitudinal study with repeated measures of ordinal outcome

Jeyaseelan, L.; Antonysamy, B.; John, JK

doi:10.1016/0895-4356(96)89220-1

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This model is built under a hierarchical structure, in which the response variable/random‐effects are assumed to be Gaussian. However, there are plenty of experiments whose primary outcome is nonnormal (Kachman & Stroup, 1994), and a brief search on the extensive literature handling this case bring us some examples in which the response variable is binary (Gao, Pan, & Haber, 2012; Landerman, Mustillo, & Land, 2011; Williamson, Bangdiwala, Marshall, & Waller, 1996; Yin, Bapst, Von Borstel, Simianer, & König, 2014); is ordinal (Bürgin & Ritschard, 2015; Jeyaseelan, Antonysamy, & John, 1996; Li & Schafer, 2008; Rana, Roy, & Das, 2018); is a proportion (Bonat, Ribeiro, & Zeviani, 2015; Galvis, Bandyopadhyay, & Lachos, 2014; Hunger, Döring, & Holle, 2012; Xu et al., 2013).…”

Section: Introductionmentioning

confidence: 99%

A new mixed‐effects regression model for the analysis of zero‐modified hierarchical count data

et al. 2020

View full text Add to dashboard Cite

Count data sets are traditionally analyzed using the ordinary Poisson distribution. However, such a model has its applicability limited as it can be somewhat restrictive to handle specific data structures. In this case, it arises the need for obtaining alternative models that accommodate, for example, (a) zero‐modification (inflation or deflation at the frequency of zeros), (b) overdispersion, and (c) individual heterogeneity arising from clustering or repeated (correlated) measurements made on the same subject. Cases (a)–(b) and (b)–(c) are often treated together in the statistical literature with several practical applications, but models supporting all at once are less common. Hence, this paper's primary goal was to jointly address these issues by deriving a mixed‐effects regression model based on the hurdle version of the Poisson–Lindley distribution. In this framework, the zero‐modification is incorporated by assuming that a binary probability model determines which outcomes are zero‐valued, and a zero‐truncated process is responsible for generating positive observations. Approximate posterior inferences for the model parameters were obtained from a fully Bayesian approach based on the Adaptive Metropolis algorithm. Intensive Monte Carlo simulation studies were performed to assess the empirical properties of the Bayesian estimators. The proposed model was considered for the analysis of a real data set, and its competitiveness regarding some well‐established mixed‐effects models for count data was evaluated. A sensitivity analysis to detect observations that may impact parameter estimates was performed based on standard divergence measures. The Bayesian ‐value and the randomized quantile residuals were considered for model diagnostics.

show abstract

Section: Introductionmentioning

confidence: 99%

A new mixed‐effects regression model for the analysis of zero‐modified hierarchical count data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This model is built under a hierarchical structure, in which the response variable/random-effects are assumed to be Gaussian. However, there are plenty of experiments whose primary outcome is non-normal, and a brief search on the extensive literature handling this case brings us some examples of the analysis of repeated measures/longitudinal data, in which the response variable is binary (WILLIAMSON et al, 1996;LANDERMAN;MUSTILLO;LAND, 2011;GAO;PAN;HABER, 2012;YIN et al, 2014); is ordinal (JEYASEELAN; ANTONYSAMY; JOHN, 1996;SCHAFER, 2008;BÜRGIN;RITSCHARD, 2015;RANA;ROY;DAS, 2018); is a proportion (HUNGER;DÖRING;HOLLE, 2012;XU et al, 2013;GALVIS;BANDYOPADHYAY;LACHOS, 2014;BONAT;RIBEIRO JR.;ZEVIANI, 2015).…”

Section: Introduction 11 Backgroundmentioning

confidence: 99%

A new class of discrete models for the analysis of zero-modified count data

Silva¹

View full text Add to dashboard Cite

Gostaria de expressar meus sinceros agradecimentosAos meus pais, Edmilson e Sirlene, pela vida, pelos valores ensinados, pelo amor e apoio incondicionais, por compreenderem a ausência do primogênito ao longo dos últimos anos, e por serem os maiores exemplos de luta, trabalho e honestidade que eu levo para a vida, À minha noiva Deisy (que assumiu esse status exatamente no período em que ambos estavam em suas jornadas de doutorado), também pelo amor e apoio incondicionais, pelo carinho e paciência, pela sensibilidade e empatia, pelo companherismo, por ser minha inspiração e motivo de orgulho, por ser fantástica como ser humano, por ser a melhor companheira de viagem e, principalmente, por ter sido a grande responsável por hoje eu ser uma pessoa melhor, Aos meus familiares que me acompanham e me apoiam desde o início desta tragetória e que, apesar da ausência e da distância, acreditam na minha capacidade de superar barreiras, vencer desafios e alcançar objetivos, Ao Professor Francisco Louzada pela orientação, pela liberdade concedida e por acreditar na minha capacidade para desenvolver este trabalho, À Professora Katiane e ao Professor Marinho pela coorientação informal, pelas ideias perspicazes, e por terem sido diretamente responsáveis pela mudança no rumo do meu projeto de pesquisa, Aos professores e funcionários do Programa Interinstitucional de Pós-Graduação em Estatística (PIPGEs) por todo o conhecimento compartilhado e pelo apoio nas questões burocráticas, Aos amigos da minha turma de doutorado que, durante os quatro anos de curso, compartilharam experiências, opiniões e trouxeram momentos de descontração ao longo dos intensos dias de estudo; aos amigos que residem na cidade de São Paulo, pela amizade, pelos exemplos de luta e pelos divertidos momentos de confraternização,

show abstract

Use of Markov model in a longitudinal study with repeated measures of ordinal outcome

Cited by 2 publications

References 0 publications

A new mixed‐effects regression model for the analysis of zero‐modified hierarchical count data

A new mixed‐effects regression model for the analysis of zero‐modified hierarchical count data

A new class of discrete models for the analysis of zero-modified count data

Contact Info

Product

Resources

About