Goodness of Fit via Non‐parametric Likelihood Ratios

57 citations recorded by the source corpus.

How researchers see this paper

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

The Focused Information Criterion (2003, methodology): “…regularly they are the core of formal lack-of- t tests; see, for example, the AIC-based order selection tests of Eubank and Hart (1992) and Aerts, Claeskens, and Hart (1999, 2000), the BICtype test statistic of Ledwina (1994), and the general goodnessof- t tests of Claeskens and Hjort (2003).”
Asymptotic post‐selection inference for the Akaike information criterion (2018, background): “See Claeskens & Hjort (2004) for some selection properties under local misspecification.”
Perturbation selection and influence measures in local influence analysis (2007, methodology): “The maximum value of FIf,h is ∇Tf ∇f = n ∑m j=1 ψj(θ)2/E0(ψ2j ), which is the well-known score test statistic for testing H0 :ω = 0 when θ is either known or replaced by its estimate (Claeskens and Hjort [5]).”
Focused Information Criteria and Model Averaging for the Cox Hazard Regression Model (2006, background): “It follows that BIC penalises su‐ciently heavily for complexity, when n grows, for the narrow model S = ; to be the winner, with probability converging to 1; see Claeskens and Hjort (2004) for some more formal arguments and further discussion in a difierent but similar context.”