An empirical study of minimum description length model selection with infinite parametric complexity

DOI10.1016/j.jmp.2005.11.008zbMath1098.62008MaRDI QIDQ2507908

Peter D. Grünwald, Steven de Rooij

Publication date: 5 October 2006

Published in: Journal of Mathematical Psychology (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jmp.2005.11.008

zbMATH Keywords

model selection; minimum description length; coding; parametric complexity; prequential code

Mathematics Subject Classification ID

62F15: Bayesian inference

62C10: Bayesian problems; characterization of Bayes procedures

62A01: Foundations and philosophical topics in statistics

62B10: Statistical aspects of information-theoretic topics

Related Items

Accumulative prediction error and the selection of time series models

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Modeling by shortest data description
• On predictive least squares principles
• Estimating the dimension of a model
• Prequential and cross-validated regression estimation
• Jeffreys' prior is asymptotically least favorable under entropy risk
• Model selection based on minimum description length
• Accumulative prediction error and the selection of time series models
• A Predictive Least-Squares Principle
• Statistical Inference, Occam's Razor, and Statistical Mechanics on the Space of Probability Distributions
• Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
• Information-theoretic asymptotics of Bayes methods
• Universal coding, information, prediction, and estimation
• Counting probability distributions: Differential geometry and model selection
• MDL denoising
• The minimum description length principle in coding and modeling
• A Note on the Applied Use of MDL Approximations
• Fisher information and stochastic complexity
• Learning Theory
• A Chain Rule for use with Determinants and Permutations