2001
DOI: 10.1198/016214501753168262
|View full text |Cite
|
Sign up to set email alerts
|

Adaptive Regression by Mixing

Abstract: Adaptation over different procedures is of practical importance. Different procedures perform well under different conditions. In many practical situations, it is rather hard to assess which conditions are (approximately) satisfied so as to identify the best procedure for the data at hand. Thus automatic adaptation over various scenarios is desirable. A practically feasible method, named adaptive regression by mixing (ARM), is proposed to convexly combine general candidate regression procedures. Under mild con… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

3
176
0

Year Published

2005
2005
2022
2022

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 258 publications
(179 citation statements)
references
References 23 publications
3
176
0
Order By: Relevance
“…normally distributed random variables with mean 0 and variance β/2. The idea of mixing with exponential weights has been discussed by many authors apparently since 1970-ies (see Yang 2001 for an overview of the subject). Most of the work has been focused on the important particular case where the set of estimators is finite, i.e., w.l.o.g.…”
Section: ))mentioning
confidence: 99%
“…normally distributed random variables with mean 0 and variance β/2. The idea of mixing with exponential weights has been discussed by many authors apparently since 1970-ies (see Yang 2001 for an overview of the subject). Most of the work has been focused on the important particular case where the set of estimators is finite, i.e., w.l.o.g.…”
Section: ))mentioning
confidence: 99%
“…There is also a rapidly-growing literature on frequentist methods for model averaging, including Buckland et al (1997), Juditsky and Nemirovski (2000), Yang (2001Yang ( , 2004, Hansen (2007), Goldenshluger (2009) and Wan et al (2010). Most of these methods involve sample splitting, which can be inefficient, and all exclude heteroskedasticity, which limits their applicability.…”
Section: Introductionmentioning
confidence: 99%
“…269-274) Raftery (1996, p. 252) for guidelines when using Bayes factors). Finally, alternative approaches for incorporating model uncertainty include forecast combinations (Timmermann 2005), Bayesian model averaging (e.g., Hoeting et al 1999), frequentist model averaging (Hjort and Claeskens 2003), and adaptive mixing of methods (Yang 2001). …”
mentioning
confidence: 99%