Can the Strengths of AIC and BIC Be Shared

By Yuhong Yang. 2005

707 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Statistics and Probability

How researchers see this paper

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

In Control and Systems Engineering

1. Xinyu Zhang
2. Guohua Zou
3. Serena Ng
4. Hua Liang
5. Annie Qu
6. Yuhong Yang
7. L. Wolstenholme
8. Gerda Claeskens

In Statistics and Probability

1. Hua Liang
2. Chenlei Leng
3. Xinyu Zhang
4. Guohua Zou
5. Hansheng Wang
6. Cheng Yong Tang
7. Yingying Fan
8. Lan Wang

Citations in the corpus

• Learning generative models for protein fold families (2011, background): “In general, they do not however select the same model and their strengths cannot be shared [39].”
• Model selection for ecologists: the worldviews of AIC and BIC. (2014, methodology): “This view is supported mathematically by Yang (2005) who showed that while BIC is consistent in optimal model selection, it cannot be optimal for regression function estimation in the sense of multi-model inference, and that while AIC represents minimax-rate optimal rules for estimating the…”
• Model Selection in the Presence of Incidental Parameters (2015, neutral): “12 Weconjecture that LICAIC is asymptotically optimal (i.e., plim n,T→∞[LIC AIC (p∗)/ infp≥0 LICAIC (p)] = 1, where p∗ is the lag order estimator from LICAIC (p), e.g., Shibata (1980), Li (1987) and Yang (2005)) if the true data generating model is AR(∞)with finite σ 2 .”
• A Bayesian information criterion for singular models (2013, background): “At a high-level, they fall into two categories (Yang, 2005).”
• Envelopes and reduced-rank regression (2015, background): “There are many articles388 comparing AIC and BIC, from both theoretical and practical points of view, for example Shao389 (1997) and Yang (2005).390 The rank d and envelope dimension u can also be determined by cross-validation or by391 using hold-out samples.”
• Model Selection (2018, background): “…framework (Yang (2007), Ing (2007)), it is not surprising – given the preceding discussion – that it is impossible to achieve this goal in a uniform sense: No model selection procedure can simultaneously be consistent (like BIC) and minimax-rate adaptive (like AIC) as shown in Yang (2005).”
• Finding and Leveraging Structure in Learning Problems (2012, background): “In general, they do not however select the same model [207].”
• Applied Linear Regression (2004, background): “In this case, for a large enough sample, aic will perform better (Yang, 2005).”
• Model selection and psychological theory: A discussion of the differences between the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC) (2012, background): “Reconciling the differences between AIC and BIC appears to be very diffcult, if not impossible (e.g., Y. Yang, 2005).”
• Integrating Moderation and Mediation (2016, background): “Both Burnham and Anderson (2002) and Yang (2005) demonstrate 738 Organizational Research Methods 20(4) T a b le 5 .”
• Consistency of AIC and BIC in estimating the number of significant components in high-dimensional principal component analysis (2018, background): “These were discussed by Shibata (1976), Shao (1997), Yang (2005), etc. Kim, Kwon and Choi (2012) studied model selection consistency when the number of regressors exceeds the sample size.”
• Model Selection Techniques: An Overview (2018, background): “, [49] and [90]).”
• Sensitivity and Specificity of Information Criteria (2018, positive): “This is intuitively why a criterion with constant An cannot be asymptotically consistent even though it may be more powerful for a given n (see Claeskens and Hjort, 2008; Yang, 2005; Kieseppä, 2003).”
• To Combine Forecasts or to Combine Information? (2010, background): “Yang (2005) shows that for any model selection criterion to be consistent, it must behave suboptimally for estimating the regression function in terms of minimax rate of convergence.”