Cross Validation and Maximum Likelihood estimation of hyper-parameters of Gaussian processes with model misspecification - Archive ouverte HAL
Article Dans Une Revue Computational Statistics and Data Analysis Année : 2013

Cross Validation and Maximum Likelihood estimation of hyper-parameters of Gaussian processes with model misspecification

Résumé

The Maximum Likelihood (ML) and Cross Validation (CV) methods for estimating covariance hyper-parameters are compared, in the context of Kriging with a misspecified covariance structure. A two-step approach is used. First, the case of the estimation of a single variance hyper-parameter is addressed, for which the fixed correlation function is misspecified. A predictive variance based quality criterion is introduced and a closed-form expression of this criterion is derived. It is shown that when the correlation function is misspecified, the CV does better compared to ML, while ML is optimal when the model is well-specified. In the second step, the results of the first step are extended to the case when the hyper-parameters of the correlation function are also estimated from data.
Fichier principal
Vignette du fichier
CV_ML_model_misspecification.pdf (444.74 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00905400 , version 1 (18-11-2013)

Identifiants

  • HAL Id : hal-00905400 , version 1

Citer

François Bachoc. Cross Validation and Maximum Likelihood estimation of hyper-parameters of Gaussian processes with model misspecification. Computational Statistics and Data Analysis, 2013, 66, pp.55-69. ⟨hal-00905400⟩
304 Consultations
1289 Téléchargements

Partager

More