COMMENTS ON PAIRWISE LIKELIHOOD IN TIME SERIES MODELS

By Richard A. Davis, Chun Yip Yau. 2011

83 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/9f392987a7fced79d40db26f8e67b4c196e39c1f

How researchers see this paper

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

Citations in the corpus

Joint composite estimating functions in spatiotemporal models (2012, methodology): “3(b) show that, for the JCEF, increasing spatial and temporal lags do not improve the estimates, which is consistent with findings in the current literature (e.g. Varin et al. (2005) and Davis and Yau (2011)).”
Likelihood estimators for multivariate extremes (2014, background): “However, the former are more variable than the latter, and require a special treatment of uncertainty (Cox and Reid, 2004; Padoan et al, 2010; Davis and Yau, 2011; Huser and Davison, 2013).”
Statistical Modeling of Spatial Extremes (2012, background): “Davison and Gholamrezaee (2012) fit models based on (22) and (23) to extreme temperature data.”
Statistical inference for max‐stable processes in space and time (2012, background): “As already pointed out by Davis and Yau (2011) and Huser and Davison (2013), there might be a loss in efficiency if too many pairs are included in the estimation.”
AN OVERVIEW OF COMPOSITE LIKELIHOOD METHODS (2011, background): “Several recent papers, including some in this special issue (Okabayashi, Johnson and Geyer (2011)); Davis and Yau (2011); Ng et al.”
Space–time modelling of extreme events (2012, background): “With the random-set parameter μ known, the MSE is minimized for K = {1}, whatever the estimation procedure, corroborating the findings of Davis and Yau (2011) for AR(1) or MA(1) processes.”
Geostatistics of Dependent and Asymptotically Independent Extremes (2013, background): “Under mild conditions, maximum composite likelihood estimators are strongly consistent and have asymptotic normal distributions, though they may be much more variable than ordinary maximum likelihood estimators (Huser and Davison 2013; Davis and Yau 2011).”