High-dimensional generalizations of asymmetric least squares regression and their applications

Gu, Yuwen; Zou, Hui

doi:10.1214/15-aos1431

Cited by 53 publications

(36 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A includes some preliminary knowledge on generalized subdifferentials and Clarke Jacobian, and some lemmas used in Section 2-5; Appendix B includes the proof of Theorem 2 and Theorem 3; Appendix C introduces the semismooth Newton method and the semi-proximal ADMM in Gu and Zou (2016); Appendix D includes performance comparisons of MSCRA IPM, MSCRA ADMM and MSCRA PPA on some synthetic data and real data.…”

Section: Supplementary Materialsmentioning

confidence: 99%

A proximal dual semismooth Newton method for zero-norm penalized quantile regression estimator

Zhang¹,

Pan²,

Bi³

2022

STAT SINICA

View full text Add to dashboard Cite

Section: Supplementary Materialsmentioning

confidence: 99%

A proximal dual semismooth Newton method for zero-norm penalized quantile regression estimator

Zhang¹,

Pan²,

Bi³

2022

STAT SINICA

View full text Add to dashboard Cite

“…As mentioned, for example, in Gu and Zou (2016) AIC and BIC often overfit the model. These properties hold for almost any reasonable choice of penalty function depending on the number of deemed not equal to 0.…”

Section: How To Construct a Gbic Proceduresmentioning

confidence: 99%

“…Although they are, implicitly, doing multiple testing to fit a model, the issue of error rates of the tests rarely comes up. As mentioned, for example, in Gu and Zou (2016) AIC and BIC often overfit the model. The issue of unknown error control could be a contributing factor.…”

Section: How To Construct a Gbic Proceduresmentioning

confidence: 99%

Penalized likelihood and multiple testing

2018

View full text Add to dashboard Cite

The classical multiple testing model remains an important practical area of statistics with new approaches still being developed. In this paper we develop a new multiple testing procedure inspired by a method sometimes used in a problem with a different focus. Namely, the inference after model selection problem. We note that solutions to that problem are often accomplished by making use of a penalized likelihood function.A classic example is the Bayesian information criterion (BIC) method. In this paper we construct a generalized BIC method and evaluate its properties as a multiple testing procedure. The procedure is applicable to a wide variety of statistical models including regression, contrasts, treatment versus control, change point, and others. Numerical work indicates that, in particular, for sparse models the new generalized BIC would be preferred over existing multiple testing procedures. K E Y W O R D Sconsistency, convexity, information criteria, pairwise comparisons, sparsity 62

show abstract

“…For a detailed and systematic introduction to quantile regression and some interesting extensions of basic quantile-based models, we refer to Koenker (2005), Engle and Manganelli (2004), Kim (2007), Cai and Xu (2008), Cai and Xiao (2012), Andriyana et al (2016) and Koenker (2017), among others. More expectile-based models can be found in Efron (1991), Yao and Tong (1996), Granger and Sin (1997), Taylor (2008), Kuan et al (2009), Gu and Zou (2016), Farooq and Steinwart (2017), among others. Ehm et al (2016) considered the problems involving prediction for expectiles.…”

Section: Introductionmentioning

confidence: 99%