Extended Bayesian information criteria for model selection with large model spaces

By Jiahua Chen, Zehua Chen. 2008

2,019 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/88a2f5129a01f5a7b1a2bb4e802d046822f65a39

How researchers see this paper

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

In Genetics

In Plant Science

Citations in the corpus

Tuning parameter selection in high dimensional penalized likelihood (2013, methodology): “We also refer to Chen and Chen (2008) for a recent study on an extended BIC and its property for Gaussian linear models, and Wang and Zhu (2011) for tuning parameter selection in high dimensional penalized least squares.”
Forward Regression for Ultra-High Dimensional Variable Screening (2009, methodology): “As theoretically proved by Chen and Chen (2008), the BIC criterion (3.2) is selection consistent if d = O(nα) for some α > 0; see Theorem 1 in Chen and Chen (2008).”
Stability and variability of personality networks. A tutorial on recent developments in network psychometrics (2017, methodology): “Established ways to select a value for the tuning parameter include selection according to an information criterion, such as the Extended BIC (EBIC; Chen & Chen, 2008; Epskamp, 2016; Foygel & Drton, 2010), or via cross-validation (e.g., Krämer, Schäfer, & Boulesteix, 2009).”
Estimation and Selection of Spatial Weight Matrix in a Spatial Lag Model (2019, positive): “To get γ̂ , we can consider the problem min α,γ T∑ t=1 ∥∥yt − α − Btγ∥∥2, 4We also experimented with the extended BIC of Chen and Chen (2008) and obtained similar results. where we have the solution γ̂ = ( T∑ t=1 (Bt − B̄)T(Bt − B̄) )−1 T∑ t=1 (Bt − B̄)T(yt − ȳ).”
Sensitivity and Specificity of Information Criteria (2018, positive): “However, sometimes they might need to be adapted (see, e.g., Chen and Chen, 2008; Pan et al., 2016; Mestres et al., 2018).”
On constrained and regularized high-dimensional regression (2013, background): “In Chen and Chen (2008), it is showed that a modiﬁed BIC is selection consistent when p is of order of n κ for some κ > 0; Liu and Yang (2010) proved that another modiﬁed BIC allows p to be an order of exp ( cp 0 n ) for some c > 0.”
Variable selection using pseudo-variables (2018, background): “Accordingly, there is an extensive literature on tuning parameter selection including information-based criteria (Chen and Chen, 2008; Wang et al., 2009; Zhang et al., 2010; Fan and Tang, 2013; Hui et al., 2015), resampling methods (Hall et al.”
Exploratory graph analysis: A new approach for estimating the number of dimensions in psychological research (2016, methodology): “As shown in our simulation study, EGA performed comparable to parallel analysis, EBIC, eBIC and to Kaiser-Guttman rule in a number of situations, especially when the number of factors was two.”
Investigating the performance of Exploratory Graph analysis and traditional techniques to identify the number of latent factors: a simulation and tutorial (2018, methodology): “However, when gamma is zero, BIC is computed instead (for more details, see Chen & Chen, 2008).”
A Bayesian information criterion for singular models (2013, methodology): “to adopt non-uniform prior model probabilities; compare for example the work on regression models by Chen and Chen (2008) and Scott and Berger (2010), and the work on graphical models by Foygel and Drton (2010) and Gao et al. (2012). As mentioned in remark 3, it would be straightforward to incorpora”
Estimation and model selection in generalized additive partial linear models for correlated data with diverging number of covariates (2014, methodology): “We propose to use the extended Bayesian Information Criterion (EBIC) to select the optimal tuning parameters based on [3] and [13].”
The Gaussian Graphical Model in Cross-Sectional and Time-Series Data (2016, methodology): “LASSO utilizes a tuning parameter which can be chosen in a way that optimizes cross-validated prediction accuracy or that minimizes information criteria such as the extended Bayesian information criterion (EBIC; Chen & Chen, 2008).”
High-dimensional consistency in score-based and hybrid structure learning (2015, methodology): “We recommend to apply the stability selection approach of Meinshausen and Bühlmann (2010) or to use the extended BIC criterion [Chen and Chen (2008), Foygel and Drton (2010)], which has been shown to work better in sparse high-dimensional settings than the BIC criterion.”
Regularized Gaussian Psychological Networks: Brief Report on the Performance of Extended BIC Model Selection (2016, positive): “The extended Bayesian Information Criterion (EBIC; Chen and Chen 2008; Foygel and Drton 2010) adds an extra penalty for model complexity to the typical BIC and has been shown to work well in high-dimensional network model selection (Foygel and Drton, 2010; Barber et al.”
An Iterative Coordinate Descent Algorithm for High-Dimensional Nonconvex Penalized Quantile Regression (2015, neutral): “…p then r ← r + 1 j ← j + 1 (mod p) until β(k)(r)j converge to β ∗ β (k) ← β∗ until β (k) converge to β̂ then return (β̂) High-dimensional BIC-type criterion for nonconvex penalized least-squares regression with diverging p was recently investigated by Wang, Li, and Leng (2009), Chen and…”