Models for Discrete Longitudinal Data

By Geert Molenberghs, Geert Verbeke. 2005

1,466 citations recorded by the source corpus.

Subfields: Information Systems, Management Science and Operations Research, Transportation

View Paper: https://www.semanticscholar.org/paper/8141b79fbe7a810dc26fd6aefb3018a37205f4d7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Management Science and Operations Research

In Transportation

Citations in the corpus

AN OVERVIEW OF COMPOSITE LIKELIHOOD METHODS (2011, background): “Molenberghs and Verbeke (2005) in the context of longitudinal studies, and Mardia et al. (2008) in bioinformatics, construct composite likelihoods by pooling pairwise conditional densities LC(θ; y) = m∏ r=1 m∏ s=1 f(yr|ys; θ), or by pooling full conditional densities LC(θ; y) = m∏ r=1 f(yr|y(−r);…”
The maximum approximate composite marginal likelihood (MACML) estimation of multinomial probit-based unordered response choice models (2011, background): “…the CML function can be maximized by solving the corresponding score equations; the conditions are too numerous to mention here, but are listed in Molenberghs and Verbeke, 2005, page 191), the maximization of the logarithm of the CML function in Equation (9) is achieved by solving the composite…”
A Commentary on Statistical Assessment of Violence Recidivism Risk (2015, methodology): “CM1’s and HC’s attempted confidence intervals for individual risks are analogous to this latter aspect of modeling repeated measures binary data using mixed logistic regression (Fitzmaurice et al. 2008; Molenberghs and Verbeke 2005; Vonesh 2012), but differ in that elements of the preceding formulat”
A comparison of the maximum simulated likelihood and composite marginal likelihood estimation approaches in the context of the multivariate ordered-response model (2010, background): “Specifically, under usual regularity assumptions (Molenberghs and Verbeke, 2005, page 191), the CML estimator is consistent and asymptotically normal distributed (this is because of the unbiasedness of the CML score function, which is a linear combination of proper score functions associated with…”
Copula Functions for Residual Dependency (2007, background): “A class of models that does not suffer from the aforementioned problems are the so-called marginal models (see, e.g., Molenberghs & Verbeke, 2005).”
Flexible Imputation of Missing Data (2012, background): “There is an extensive literature which often concentrates on the longitudinal case (Verbeke and Molenberghs, 2000; Molenberghs and Verbeke, 2005; Daniels and Hogan, 2008).”
The Effective Sample Size and an Alternative Small-Sample Degrees-of-Freedom Method (2009, methodology): “We now generate binary data from a beta-binomial model, where the outcomes within a cluster follow a binomial distribution, and the cluster-specific success probability is assumed to be drawn from a beta distribution (Molenberghs and Verbeke 2005).”
Actuarial statistics with generalized linear mixed models (2007, background): “The following models are considered Yij|bi ∼ Γ(ν, μij/ν) where log (μij) = log (Payrollij) + β0 + bi,0 (25) versus log (μij) = log (Payrollij) + β0 + β1Yearij + bi,0 (26) and log (μij) = log (Payrollij) + β0 + β1Yearij + bi,0 + bi,1Yearij.”
Missing data methods in longitudinal studies: a review (2009, methodology): “See also Verbeke and Molenberghs (2000) and Molenberghs and Verbeke (2005) for reviews.”
Bayesian composite marginal likelihoods (2011, background): “Under broad assumptions (see, e.g., Molenberghs and Verbeke (2005)), the maximum composite likelihood estimatorˆθ c is the solution of the composite score function s(θ) = ∇ log CL(θ) = ∑ m i=1 w i s i (θ), with s i (θ) = ∇ log f (y ∈ A i ; θ), i = 1, . . . , m.”