Efficient Algorithms for Robust Estimation in Linear Mixed-Effects Models Using the Multivariate t Distribution

By J. C. Pinheiro, Chuanhai Liu, Ying Wu. 2001

356 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/9445ef865c4eb1431f9cb2abdb5efc1c361172cc

How researchers see this paper

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

In Statistics and Probability

Citations in the corpus

On the Conditional Distribution of the Multivariate t Distribution (2016, methodology): “…theMVTdistribution iswidely applied in robust data analysis including linear and nonlinear regressions (Lange, Little, and Taylor 1989; Liu 1994, 2004; Gelman et al. 2014), linear mixed effects models (Pinheiro, Liu, and Wu 2001), and sample selection models (Marchenko and Genton 2012; Ding 2014).”
MAXIMUM LIKELIHOOD INFERENCE IN ROBUST LINEAR MIXED-EFFECTS MODELS USING MULTIVARIATE t DISTRIBUTIONS (2007, methodology): “This section presents a simulation study that aims to compare the MBP algorithm to the EM algorithm in the t-normal LMM. Pinheiro et al. (2001) established the EM algorithm for the t-t LMM, which is different from the one we derive in this section.”
Penalising Model Component Complexity: A Principled, Practical Approach to Constructing Priors (2014, methodology): “This can result in a significant degradation of estimation performance (Lange et al., 1989; Pinheiro et al., 2001; Masreliez and Martin, 1977), and using the Student-t distribution can account for deviations caused by heavier tails, see for example Chib et al. (2002) and Jacquier et al. (1994) for…”
High-Breakdown Inference for Mixed Linear Models (2006, methodology): “Others have proposed instead using a multivariate t distribution to accommodate outlying observations, as proposed by Lange, Little, and Taylor (1989) (see, e.g., Pinheiro, Liu, and Wu 2001).”
Robust Linear Mixed Models with Normal/Independent Distributions and Bayesian MCMC Implementation (2003, methodology): “Our work expands that of Strandén and Gianola (1999) and Pinheiro et al. (2001), who focused on t-distributions, within a Bayesian and maximum likelihood perspectives, respectively.”
Latent Variable Modelling: A Survey * (2007, methodology): “Approaches to relaxing this assumption include using multivariate t-distributions (e.g. Pinheiro et al., 2001), finite mixtures of normal distributions (e.g. Uebersax, 1993; Magder & Zeger, 1996), truncated Hermite series expansions (e.g. Gallant & © Board of the Foundation of the Scandinavian…”
Maximization by Parts in Likelihood Inference (2005, methodology): “Pinheiro et al. (2001) developed EM-type algorithms for maximum likelihood estimation in such a setting.”
A New Robust Regression Model for Proportions (2012, methodology): “Following Pinheiro et al. (2001) and Barnett and Lewis (1995), we refer to an outlier as an observation (or set of observations) that appears to be inconsistent with the rest of the data.”
Likelihood-based Inference For Mixed-effects Models With Censored Response Using The Multivariate-t Distribution (2013, methodology): “In a simulation study, Pinheiro, Liu, and Wu (2001) showed that the t-LME substantially outperforms the normal or standard LME when outliers are present in the data.”
Bayesian Inference and Application of Robust Growth Curve Models Using Student's t Distribution (2013, methodology): “Pinheiro et al. (2001) discussed the use of t distributions for linear mixed-effects models (see also Song et al., 2007).”
Joint modelling of location and scale parameters of the t distribution (2004, methodology): “Lange et al. (1989), Liu and Rubin (1994, 1995) and Pinheiro et al. (2001) include the estimation of n in an EM framework.”
Simplex Mixed‐Effects Models for Longitudinal Proportional Data (2008, unknown): “See, for instance, Pinheiro et al. (2001) and Song et al. (2007).”
Robust linear mixed models with skew-normal independent distributions from a Bayesian perspective (2009, unknown): “Pinheiro et al. (2001) proposed a multivariate tlinear mixed model and showed that it would perform well in the presence of outliers.”