DIC in variable selection

By A. van der Linde. 2005

146 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/35e5668e623a8266131b5fa7882e75bb9dd55362

How researchers see this paper

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

In Artificial Intelligence

1. Aki Vehtari
2. Andrew Gelman
3. Steven L. Brunton
4. J. Nathan Kutz
5. Joshua L. Proctor
6. N. Mangan
7. Bradley P. Carlin
8. J. Bence

In Statistics and Probability

1. Andrew Gelman
2. Aki Vehtari
3. J. Nathan Kutz
4. Steven L. Brunton
5. David J. Spiegelhalter
6. N. G. Best
7. Bradley P. Carlin
8. J. Bence

Citations in the corpus

• Spatial modelling of claim frequency and claim size in non-life insurance (2007, methodology): “An information theoretic discussion of the DIC as criterion for posterior predictive model comparison is given in van der Linde (2005) .”
• Model selection for dynamical systems via sparse regression and information criteria (2017, methodology): “ictive power including popular methods such as the Akaike information criterion (AIC) [7,8], Bayesian information criterion (BIC) [9], cross-validation (CV) [20], deviance information criterion (DIC) [21], and minimum description length (MDL) [22]. Methods such as AIC explicitly balance parsimony an”
• The deviance information criterion: 12 years on (2014, methodology): “van der Linde (2005, 2012), Plummer (2008) and Ando (2012) have all concluded that DIC overfits because it uses a plug-in estimate in the predictive target rather than the proper predictive distribution, and all have concluded that a better method would be to increase the penalty: DICÅ =D.θ̄/+3pD =…”
• Performance of deviance information criterion model selection in statistical catch-at-age analysis (2008, background): “DIC is a general model selection criterion, and was developed to perform well in prediction of future data sets generated by the same mechanism (Spiegelhalter et al., 2002; van der Linde, 2005).”
• Understanding predictive information criteria for Bayesian models (2013, methodology): “For practical reasons alone, there remains a place for simple bias corrections such as AIC (Akaike, 1973), DIC (Spiegelhalter et al., 2002, van der Linde, 2005), and, more recently, WAIC (Watanabe, 2010), and all these can be viewed as approximations to different versions of cross-validation (Stone,…”