Geometry of the log-likelihood ratio statistic in misspecified models

DOI10.1016/j.jspi.2010.12.019zbMath1419.62058OpenAlexW2017124996MaRDI QIDQ630939

Nicholas M. Kiefer, Hwan-sik Choi

Publication date: 22 March 2011

Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)

Full work available at URL: https://cae.economics.cornell.edu/09-08.pdf

zbMATH Keywords

differential geometrylog-likelihood ratioasymptotic meanexponential curvaturenon-nested hypothesispreferred point geometry

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Applications of statistics to economics (62P20) Parametric hypothesis testing (62F03) Parametric inference (62F99)

Related Items (2)

Geodesic hypothesis testing for comparing location parameters in elliptical populations ⋮ STATISTICAL INFERENCE WITH F-STATISTICS WHEN FITTING SIMPLE MODELS TO HIGH-DIMENSIONAL DATA

Cites Work

• Unnamed Item
• Likelihood Ratio Tests for Model Selection and Non-Nested Hypotheses
• Selecting the best linear regression model. A classical approach
• The geometry of exponential families
• Defining the curvature of a statistical problem (with applications to second order efficiency)
• Preferred point geometry and statistical manifolds
• Improving predictive inference under covariate shift by weighting the log-likelihood function
• Preferred point geometry and the local differential geometry of the Kullback-Leibler divergence
• Invariants and likelihood ratio statistics
• Differential geometry of curved exponential families. Curvatures and information loss
• Differential-geometrical methods in statistics
• Empirical likelihood is Bartlett-correctable
• Approximating exponential models
• Improving robust model selection tests for dynamic models
• A NEW ASYMPTOTIC THEORY FOR HETEROSKEDASTICITY-AUTOCORRELATION ROBUST TESTS
• Several Tests for Model Specification in the Presence of Alternative Hypotheses
• Model selection tests for nonlinear dynamic models
• Heteroskedasticity-Autocorrelation Robust Standard Errors Using The Bartlett Kernel Without Truncation
• Properties of sufficiency and statistical tests
• On Information and Sufficiency

This page was built for publication: Geometry of the log-likelihood ratio statistic in misspecified models