Dynamic latent class model averaging for online prediction

DOI10.1002/FOR.2315MaRDI QIDQ5270441zbMATH OpenOpenAlexFDO

Authors Hongxia Yang, Yasuo Amemiya, Jonathan R. M. Hosking

Publication date 23 June 2017

Published in Journal of Forecasting (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/for.2315

zbMATH Keywords

analysisclusteringexponential forgettingforward filtering backward samplingGibbs algorithmMarkov chain modelpolychotomous regression model

Mathematics Subject Classification ID

Prediction theory (aspects of stochastic processes) (60G25) Computational methods in Markov chains (60J22) Inference from stochastic processes and prediction (62M20) Applications of statistics to economics (62P20) Numerical analysis or methods applied to Markov chains (65C40)

Recommendations

• Likelihood tempering in dynamic model averaging
• Dynamic logistic regression and dynamic model averaging for binary classification
• Combining model selection procedures for online prediction
• Dynamic Generalized Linear Models and Bayesian Forecasting
• Improvement over bayes prediction in small samples in the presence of model uncertainty

Cites work

• A New Approach to the Economic Analysis of Nonstationary Time Series and the Business Cycle
• A Semiparametric Approach to Density Estimation
• Adaptive Regression by Mixing
• Bayesian auxiliary variable models for binary and multinomial regression
• Bayesian forecasting and dynamic models.
• Bayesian model averaging: A tutorial. (with comments and a rejoinder).
• Combining Estiamates in Regression and Classification
• DATA AUGMENTATION AND DYNAMIC LINEAR MODELS
• Estimation and Forecasting of Dynamic Conditional Covariance: A Semiparametric Multivariate Model
• Exact and approximate sum representations for the Dirichlet process
• Functional aggregation for nonparametric regression.
• Is combining classifiers with stacking better than selecting the best one?
• Nonparametric Bayes stochastically ordered latent class models
• On Gibbs sampling for state space models

Cited in

(3)

• Combining model selection procedures for online prediction
• Dynamic logistic regression and dynamic model averaging for binary classification
• Likelihood tempering in dynamic model averaging

This page was built for publication: Dynamic latent class model averaging for online prediction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5270441)