A pairwise likelihood approach to analyzing correlated binary data

By Anthony Y. C. Kuk, David J. Nott. 2000

91 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/5a7bde4e51978cadb821b3bd5e88377e6afe2384

How researchers see this paper

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

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

COMMENTS ON PAIRWISE LIKELIHOOD IN TIME SERIES MODELS (2011, methodology): “…pairwise likelihood, it has been applied in many fields in statistics, including image analysis (Nott and Ryden (1999)), longitudinal binary data (Kuk and Nott (2000)), multivariate survival data analysis (Parner (2001)), multilevel models (Renard, Molenberghs and Geys (2004)), frailty models…”
A latent variable representation of count data models to accommodate spatial and temporal dependence: application to predicting crash frequency at intersections (2011, background): “The only minor difference is that a weight needs to be placed for each unit in the CML estimation approach (see Kuk and Nott, 2000, Joe and Lee, 2009, and Bhat, 2011).”
A note on pseudolikelihood constructed from marginal densities (2004, methodology): “methods for correlated binary data are discussed in Kuk and Nott (2000) and”
Fitting and Testing Vast Dimensional Time-Varying Covariance Models (2007, methodology): “by Fearnhead (2003) in bioinformatics, deLeon (2005) on grouped data, Kuk and Nott (2000) and”
A robust pairwise likelihood method for incomplete longitudinal binary data arising in clusters (2011, methodology): “With correlated binary data, for example, Kuk & Nott (2000) investigated the relative performance of using a DOI: 10.1002/cjs The Canadian Journal of Statistics / La revue canadienne de statistique PWL to the GEE approach.”
ISSUES AND STRATEGIES IN THE SELECTION OF COMPOSITE LIKELIHOODS (2011, background): “…likelihood, has received increasing attention in recent years due to the simplicity in defining the objective function and computational advantages when dealing with data with complex structure (e.g., Kuk and Nott (2000); Zhao and Joe (2005); Fieuws and Verbeke (2006); Dillon and Lebanon (2009)).”
AN OVERVIEW OF COMPOSITE LIKELIHOOD METHODS (2011, background): “The weights 1/(mi−1), recommended in Kuk and Nott (2000), LeCessie and van Houwelingen (1994), and Zhao and Joe (2005), are suitable for the limiting case of independence within clusters, but the weights 1/{mi(mi−1)} are optimal for very strong dependence.”
The maximum approximate composite marginal likelihood (MACML) estimation of multinomial probit-based unordered response choice models (2011, methodology): “To address this situation, a weighted CML function may be used (see Kuk and Nott, 2000, Renard et al., 2004).”
A comparison of the maximum simulated likelihood and composite marginal likelihood estimation approaches in the context of the multivariate ordered-response model (2010, background): “(2004), Zhao and Joe (2005), and Kuk and Nott (2000) in other model contexts, where the CML has been shown to lose efficiency relative to a maximum likelihood approach.”
The Composite Marginal Likelihood (CML) Inference Approach with Applications to Discrete and Mixed Dependent Variable Models (2014, background): “But, as emphasized by McMillen (2010), the use of a parametric spatial error structure is “troublesome because it requires the researcher to specify the actual structure of the errors”, while it is much easier to justify a parametric spatial lag structure when accommodating spatial dependence.”
On composite likelihood estimation of a multivariate INAR(1) model (2013, background): “Also KuK and Nott (2000) and later Joe and Lee (2009) show that the best choice of weights depends on which parameter is to be estimated.”
Joint composite estimating functions in spatiotemporal models (2012, background): “Nott and Rydén (1999) and Kuk and Nott (2000) are among those researchers who have advocated the incorporation of correlations between composite pairs into the estimation.”
Pairwise likelihood approach to grouped continuous model and its extension (2005, unknown): “Observe that this is similar to the clustered data case considered by Kuk and Nott (2000) where a cluster here corresponds to a subject.”