Generalized Linear Models with Random Effects: Unified Analysis via H-likelihood

By Youngjo Lee, John A. Nelder, Y. Pawitan. 2006

577 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/93232157956180e54f92d4afd7ae10f8aa5f3afb

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

Citations in the corpus

Repeatability for Gaussian and non‐Gaussian data: a practical guide for biologists (2010, methodology): “The (latentscale) distribution-specific variance is π2/3 for the logit model (i.e. the variance for the logistic distribution; Isberg et al., 2005; Lee et al., 2006; Snijders & Bosker, 1999) and hence the latent-scale residual variance is σ 2 ε = ω·(π2/3).”
Latent Variable Modelling: A Survey * (2007, unknown): “…Davidian & Gallant, 1992), non-parametric maximum-likelihood estimation (e.g. Lindsay, 1995), other non-normal distributions (e.g. Lee & Nelder, 1996; Wedel & Kamakura, 2001; Lee et al., 2006) or, in a Bayesian setting, semiparametric mixtures of Dirichlet processes (e.g. Müller & Roeder, 1997).”
BLUP for phenotypic selection in plant breeding and variety testing (2008, methodology): “Furthermore, the theory of James and Stein (1961) justifies the use of BLUP even if we think of the parameters as fixed, provided the number of parameters is large (Lee et al. 2006, pp. 151–152).”
To transform or not to transform: using generalized linear mixed models to analyse reaction time data (2015, background): “…in computation may allow non-normally distributed random factors to be specified in doubly generalized linear mixed-effect models as described by Lee et al. (2006). words, and item-specific variability in the stimulus quality effect which can be distinguished from variability associated with…”
Modelling skewness and kurtosis with the BCPE density in GAMLSS (2012, methodology): “using local maximum-likelihood method or a PQL method, as in [12].”
Smoothing parameter selection for a class of semiparametric linear models (2009, unknown): “The right-hand side equals ‖y − ŷ‖2={n − tr.Hλ/}, an estimate of σ2 that is based on viewing tr.Hλ/ as the degrees of freedom of the smoother (see Pawitan (2001), page 487, and Lee et al. (2006), page 279).”
Foundations of Linear and Generalized Linear Models (2015, background): “The h-likelihood approach essentially treats random effects like parameters and is also computationally simpler (Lee and Nelder 1996; Lee et al. 2006), but its justification is unclear (Meng 2009).”
Statistical process control for multistage processes with binary outputs (2013, methodology): “Yun and Lee (2004) and Lee et al. (2006) implemented the h-likelihood proposed by Lee and Nelder (1996) to make inferences from the MGLMM and compare it with the GHQ method for binary outcomes.”
Log-Normal Versus Gamma Models for Analyzing Data from Quality-Improvement Experiments (2008, methodology): “The whole estimation process is done iteratively by using two interconnected iterative weighted least squares (Lee et al., 2006).”
How to make a common species rare: A case against conservation complacency (2011, methodology): “The new results reported in this paper were obtained by fitting Hierarchical Generalized Linear Models (HGLMs) (Lee et al., 2006) to our major datasets.”