The Focused Information Criterion

By Gerda Claeskens, Nils Lid Hjort. 2003

385 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/cd1f00921fe786ad4e858985eea98910db016d00

How researchers see this paper

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

In Statistics and Probability

Citations in the corpus

Using Stacking to Average Bayesian Predictive Distributions (with Discussion) (2017, background): “†Noah Harding Assistant Professor, Department of Statistics, Rice University, Houston, TX, U.S.A., meng@rice.com application—similar principle has been demonstrated by Claeskens and Hjort (2003) that model selection may focus on the parameter singled out for interest.”
SHRINKAGE, PRETEST AND ABSOLUTE PENALTY ESTIMATORS IN PARTIALLY LINEAR MODELS (2007, background): “Such sequences of models have been considered in the estimation context by Bickel (1984) and Claeskens & Hjort (2003), among others.”
Frequentist Model Average Estimators (2003, methodology): “In contrast, Claeskens and Hjort (2003) developed a focused information criterion that speci cally aims at nding the best candidate model for a given focus parameter 1.”
Focused Information Criteria, Model Selection, and Model Averaging in a Tobit Model With a Nonzero Threshold (2012, methodology): “Department of Management Sciences, City University of Hong Kong, Kowloon, Hong Kong (msawan@cityu.edu.hk; zhefzhou@cityu.edu.hk) Claeskens and Hjort (2003) have developed a focused information criterion (FIC) for model selection that selects different models based on different focused functions…”
Model Selection (2018, methodology): “Of course, model averaging methods have also been analyzed from a frequentist perspective; see, for example, Buckland, Burnham, and Augustin (1997), Magnus (2002), Juditsky and Nemirovski (2000), Yang (2001, 2003), Hjort and Claeskens (2003), Danilov and Magnus (2004), Leung and Barron (2006), as we”
Focused Information Criteria and Model Averaging for the Cox Hazard Regression Model (2006, result): “The theory and results for our FIC and model average estimators parallel the development and findings in our earlier articles (Claeskens and Hjort 2003; Hjort and Claeskens 2003a,b, hereafter referred to as CH and HC 2003). These articles were concerned with likelihood methods for general parametric”
Optimal Model Assessment, Selection, and Combination (2006, background): “A partial list of more recently proposed model selection criteria includes the risk inflation criterion (RIC) (George and Foster 1994), the covariance inflation criterion (CIC) (Tibshirani and Knight 1999), a Cauchy prior modification of BIC (Kass and Wasserman 1995), the least absolute shrinkage an”
Model Selection in the Presence of Incidental Parameters (2015, neutral): “The new criteria are shown to control for over/under-selection probabilities in these models and lead to consistent order selection criteria.”
On model selection and model misspecification in causal inference (2012, positive): “Modelselection procedures – in particular variable selection procedures – are routinely employed in this process, but rarely with regard to the ultimate focus on causal effects.(1,2) In addition, the reliance on model-selection procedures is commonly ignored when causal inferences are ultimately dra”
Global Validation of Linear Model Assumptions (2006, methodology): “was revealed using a half-normal plot of Cook’s (1977) statistic.”
PREDICTION‐FOCUSED MODEL SELECTION FOR AUTOREGRESSIVE MODELS (2007, methodology): “The main ingredient of the FIC in this model is the information matrix J T,full of the largest model under consideration (see Claeskens & Hjort, 2003, sections 2 and 3 for more details).”
Parametric or nonparametric? A parametricness index for model selection (2011, background): “For instance, the focused information criterion (FIC) [17, 18] emphasizes performance at a given estimand, and it seems interesting to understand when FIC improves over AIC and how to take advantages of both in an implementable fashion.”
Phenomics: the next challenge (2010, methodology): “Where prior information is insufficient to choose among models, we should use information from all reasonable model”
Model Averaging in Economics: An Overview (2015, neutral): “The model selection literature has proposed different alternatives to carry out the selection step; the book by Claeskens and Hjort (2008) is an excellent reference.”
Least Squares Model Averaging (2007, neutral): “Cn (W ) = 3 Y −XMΘ̂ ́0 3 Y −XMΘ̂ ́ + 2σ(2)k (W ) (11)”