Adaptive mixtures of regressions: Improving predictive inference when population has changed

Abstract : The present work investigates the estimation of regression mixtures when population has changed between the training and the prediction stages. Two approaches are proposed: a parametric approach modelling the relationship between dependent variables of both populations, and a Bayesian approach in which the priors on the prediction population depend on the mixture regression parameters of the training population. The relevance of both approaches is illustrated on simulations and on an environmental dataset.
Complete list of metadatas

Cited literature [30 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00477597
Contributor : Julien Jacques <>
Submitted on : Saturday, October 13, 2012 - 10:23:12 AM
Last modification on : Tuesday, July 23, 2019 - 11:34:23 AM
Long-term archiving on: Saturday, December 17, 2016 - 12:41:13 AM

File

AdaptMixtReg-v2.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Charles Bouveyron, Julien Jacques. Adaptive mixtures of regressions: Improving predictive inference when population has changed. Communications in Statistics - Simulation and Computation, Taylor & Francis, 2014, 43 (10), pp.22. ⟨10.1080/03610918.2012.758737⟩. ⟨hal-00477597v3⟩

Share

Metrics

Record views

543

Files downloads

519