A note on composite likelihood inference and model selection

By Cristiano Varin, Paolo Vidoni. 2005

398 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Environmental Engineering, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/5c6163d2616d208dcf79f0fc63b0a27b83221c7a

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 Environmental Engineering

In Statistics and Probability

Citations in the corpus

Fitting Vast Dimensional Time-Varying Covariance Models (2020, positive): “To achieve this aim, we use the composite likelihood (CL) method (Lindsay 1988; Cox and Reid 2004; Varin and Vidoni 2005; Varin, Reid, and Firth 2011).”
Likelihood-Based Inference for Max-Stable Processes (2009, methodology): “In contrast the CLIC statistic demonstrates poor performance, with the rejection rate under the true model reaching only 20%.”
The Composite Marginal Likelihood (CML) Inference Approach with Applications to Discrete and Mixed Dependent Variable Models (2014, methodology): “When the null hypothesis entails model selection between two competing non-nested models, the composite likelihood information criterion (CLIC) introduced by Varin and Vidoni (2005) may be used.”
Spatial modeling of extreme snow depth (2011, methodology): “As in Padoan, Ribatet and Sisson (2010), we propose to use the composite likelihood information criterion [Varin and Vidoni (2005)], which extends the TIC [Takeuchi (1976)] to the composite likelihood setting, and is defined as CLIC = −2 p(β̌) + 2 tr{H(β̌)−1J (β̌)}, where H and J are, respectively,…”
On composite likelihood estimation of a multivariate INAR(1) model (2013, methodology): “For example, in clustered data the weights are chosen so as to eliminate distant pairs of observations which tend to be less informative (Nott and Rydén, 1999; Varin and Vidoni, 2005).”
AN OVERVIEW OF COMPOSITE LIKELIHOOD METHODS (2011, methodology): “Varin and Vidoni (2005) argue this from the point of view of Kullback-Leibler divergence, whereas Faes et al. (2008) devise a method of relating individual parameters in component densities to a common parameter of interest.”
Composite Likelihood Methods (2012, methodology): “…depend on ergodicity conditions and the above n is replaced by the observation length m. • The composite likelihood version of AIC, as given in Varin and Vidoni (2005), is CL−AIC = −2 ∑ i cl(θ̂,yi) + 2tr(J(θ̂)H −1(θ̂)) • The composite likelihood version of BIC, as given in Gao and Song…”
On the likelihood function of Gaussian max-stable processes (2011, background): “…z(1), . . . , z(N ) from the model f (z; θ) on R K with K fixed, under the usual regularity conditions, θ̂ is a consistent parameter estimator (Lindsay, 1988; Varin & Vidoni, 2005): N 1/2(θ̂ − θ)→ Nq{0, H(θ)−1 J (θ)H(θ)−1} (8) in distribution as N→+∞, where H(θ)= E{−∇2 c(θ)} and J (θ)= var{∇ c(θ)}.”
Statistical inference for max‐stable processes in space and time (2012, methodology): “These methods go back to Besag (1974), and an extensive literature is available dealing with applications and properties of the estimates; see for example Cox and Reid (2004), Lindsay (1988), Varin (2007) or Varin and Vidoni (2005).”
Likelihood estimators for multivariate extremes (2014, background): “21 is through composite likelihoods; see, e.g., Lindsay (1988), Varin and Vidoni (2005), or Varin et al. (2011).”
Fitting and Testing Vast Dimensional Time-Varying Covariance Models (2007, neutral): “See Varin and Vidoni (2005).”
Non‐stationary intensity‐duration‐frequency curves integrating information concerning teleconnections and climate change (2018, neutral): “They are used in several applications as surrogates for the ordinary likelihood when it is too cumbersome or impractical to compute the full likelihood (Varin and Vidoni, 2005).”
Disaggregating daily precipitations into hourly values with a transformed censored latent Gaussian process (2015, positive): “Bevilacqua et al. (2012), following Varin and Vidoni (2005), proposed to use a Composite Likelihood Information Criterion (CLIC) for selecting the correlation model.”
High-Dimensional Copula-Based Distributions with Mixed Frequency Data (2016, positive): “We rst de ne the composite Kullback-Leibler information criterion (cKLIC) following Varin and Vidoni (2005).”
Spatial extremes: Max-stable processes at work (2013, methodology): “Although the inference procedure introduced in Section 5 is non standard, model selection using (adapted) information criterion Varin and Vidoni (2005) or (composite) likelihood ratio tests Chandler and Bate (2007) is possible.”