Calibration and empirical Bayes variable selection

By Edward I. George, Dean Phillips Foster. 2000

503 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/69b865c41e7e263b32854488ad09a63e1e7465d2

How researchers see this paper

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

In Analytical Chemistry

In Statistics and Probability

Citations in the corpus

Efficient Empirical Bayes Variable Selection and Estimation in Linear Models (2005, methodology): “The connection with the LASSO estimator also highlights a distinction between our empirical Bayes methods and earlier proposals, such as that of George and Foster (2000) which can be implemented only in a stepwise fashion in most practical situations.”
Rough and lonely road to prosperity: a reexamination of the sources of growth in Africa using Bayesian model averaging (2008, background): “For this reason, new research is diverting focus on data-dependent proper priors as in Raftery et al. (1997) or on prior hyperparameters as in Fernàndez, Ley and Steel (2001b), and George and Foster (1997).”
BAYESIAN LINEAR REGRESSION WITH SPARSE PRIORS (2014, background): “2) were considered by many authors, including [8, 20, 21, 26, 34, 41, 48].”
Optimal Model Assessment, Selection, and Combination (2006, methodology): “George and Foster (2000) and Shen and Ye (2002) studied (18) without x0 and compared AIC, BIC, RIC, CIC, GDF, and an empirical Bayes method in variable selection.”
Compatibility of prior specifications across linear models (2008, methodology): “Goutis and Robert (1998) and Dupuis and Robert (2003) use KL-projection for comparing models, but do not rely on the idea of KL-priors.”
Can the Strengths of AIC and BIC Be Shared (2005, background): “Foster and George (2000) proposed new Bayesian model selection criteria based on empirical Bayes approaches to have an adaptive penalty term that acts like BIC or RIC (note that RIC has a penalty of AIC type when the number of models does not grow in the sample size).”
Benchmark Priors Revisited: On Adaptive Shrinkage and the Supermodel Effect in Bayesian Model Averaging (2009, unknown): “Several more ’automatic’ specifications for g have been proposed (cf. Fernández et al. 2001a, George and Foster 2000 or Eicher et al. 2009), but the ones above have resurfaced most frequently and also serve as a benchmark reference for Liang et al. (2008).”
Forecasting U.S. Inflation by Bayesian Model Averaging (2003, methodology): “…realized inflation in this regression will however clearly be endogenous and so researchers look for instruments that will be correlated with , 4t tπ + , but 6 This is similar in spirit to the empirical Bayes methodology, considered in the context of model selection by George and Foster (2000).”
On the non‐negative garrotte estimator (2007, methodology): “Various other variable selection methods have been introduced in recent years (George and McCulloch, 1993; Foster and George, 1994; Breiman, 1995; Tibshirani, 1996; George and Foster, 2000; Fan and Li, 2001; Shen and Ye, 2002; Efron et al., 2004; Yuan and Lin, 2005; Zou and Hastie, 2005).”
MODEL SELECTION FOR HIGH-DIMENSIONAL, MULTI-SEQUENCE CHANGE-POINT PROBLEMS (2012, methodology): “Such an empirical Bayes approach to the BIC has been used earlier for regular models by George and Foster (2000) and in a regression setting by Chen and Chen (2008).”
Complete subset regressions (2013, background): “5 This approach avoids using uniformpriors over themodel space, which can lead to undesirable properties, particularly when regressors are correlated, see George and Foster (2000). 3.”