Centre de documentation
scientifique

Semi-parametric segmentation of multiple series using a DP-Lasso strategy / Karine Bertin in Journal of Statistical Computation and Simulation, vol 87 n° 6 (2017)  

Public [article]  inJournal of Statistical Computation and Simulation > vol 87 n° 6 (2017) . - pp 1255 - 1268 Titre : Semi-parametric segmentation of multiple series using a DP-Lasso strategy Type de document : Article/Communication Auteurs : Karine Bertin, Auteur ; Xavier Collilieux , Auteur ; Emilie Lebarbier, Auteur ; Christian Meza, Auteur Année de publication : 2017 Projets : 3-projet - voir note / Article en page(s) : pp 1255 - 1268 Note générale : bibliographie This work was supported by FONDECYT [grant numbers 1141256 and 1141258]; ANILLO [grant number ACT-1112]; MATH-AmSud [grant number 16-MATH-03]; SIDRE and CONICYT [grant number 870100003]. Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie [Termes IGN] données géodésiques [Termes IGN] estimation statistique [Termes IGN] itération [Termes IGN] programmation dynamique [Termes IGN] segmentation Résumé : (auteur) We consider a semi-parametric approach to perform the joint segmentation of multiple series sharing a common functional part. We propose an iterative procedure based on Dynamic Programming for the segmentation part and Lasso estimators for the functional part. Our Lasso procedure, based on the dictionary approach, allows us to both estimate smooth functions and functions with local irregularity, which permits more flexibility than previous proposed methods. This yields to a better estimation of the functional part and improvements in the segmentation. The performance of our method is assessed using simulated data and real data from agriculture and geodetic studies. Our estimation procedure results to be a reliable tool to detect changes and to obtain an interpretable estimation of the functional part of the model in terms of known functions. Numéro de notice : A2017-870 Affiliation des auteurs : LASTIG LAREG+Ext (2012-mi2018) Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00949655.2016.1260726 Date de publication en ligne : 30/11/2016 En ligne : https://doi.org/10.1080/00949655.2016.1260726 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89907 [article]

Segmentation of multiple series using a Lasso strategy / Karine Bertin (25/06/2014)    

Public contenu dans ArXiv / Université Cornell (Etats-Unis) (1991)   Titre : Segmentation of multiple series using a Lasso strategy Type de document : Article/Communication Auteurs : Karine Bertin, Auteur ; Xavier Collilieux , Auteur ; Emilie Lebarbier, Auteur ; Christian Meza, Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 25/06/2014 Importance : 21 p. Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes IGN] coordonnées GPS [Termes IGN] détection de changement [Termes IGN] erreur systématique [Termes IGN] itération [Termes IGN] programmation dynamique [Termes IGN] segmentation [Termes IGN] série temporelle Résumé : (auteur) We propose a new semi-parametric approach to the joint segmentation of multiple series corrupted by a functional part. This problem appears in particular in geodesy where GPS permanent station coordinate series are affected by undocumented artificial abrupt changes and additionally show prominent periodic variations. Detecting and estimating them are crucial, since those series are used to determine averaged reference coordinates in geosciences and to infer small tectonic motions induced by climate change. We propose an iterative procedure based on Dynamic Programming for the segmentation part and Lasso estimators for the functional part. Our Lasso procedure, based on the dictionary approach, allows us to both estimate smooth functions and functions with local irregularity, which permits more flexibility than previous proposed methods. This yields to a better estimation of the bias part and improvements in the segmentation. The performance of our method is assessed using simulated and real data. In particular, we apply our method to data from four GPS stations in Yarragadee, Australia. Our estimation procedure results to be a reliable tool to assess series in terms of change detection and periodic variations estimation giving an interpretable estimation of the functional part of the model in terms of known functions. Numéro de notice : P2014-001 Affiliation des auteurs : LASTIG LAREG+Ext (2012-mi2018) Thématique : MATHEMATIQUE/POSITIONNEMENT Nature : Preprint nature-HAL : Préprint DOI : 10.48550/arXiv.1406.6627 Date de publication en ligne : 25/06/2014 En ligne : https://doi.org/10.48550/arXiv.1406.6627 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=78980

Documents numériques

peut être téléchargé Segmentation of multiple series ... - pdf auteur Adobe Acrobat PDF

LASSO-type estimators for semiparametric nonlinear mixed-effects models estimation / Ana Arribas-Gil in Statistics and Computing, vol 24 n° 3 (May 2014)  

Public [article]  inStatistics and Computing > vol 24 n° 3 (May 2014) . - pp 443 - 460 Titre : LASSO-type estimators for semiparametric nonlinear mixed-effects models estimation Type de document : Article/Communication Auteurs : Ana Arribas-Gil, Auteur ; Karine Bertin, Auteur ; Christian Meza, Auteur ; Vincent Rivoirard, Auteur Année de publication : 2014 Article en page(s) : pp 443 - 460 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Statistiques [Termes IGN] estimation statistique [Termes IGN] modèle non linéaire Résumé : (auteur) Parametric nonlinear mixed effects models (NLMEs) are now widely used in biometrical studies, especially in pharmacokinetics research and HIV dynamics models, due to, among other aspects, the computational advances achieved during the last years. However, this kind of models may not be flexible enough for complex longitudinal data analysis. Semiparametric NLMEs (SNMMs) have been proposed as an extension of NLMEs. These models are a good compromise and retain nice features of both parametric and nonparametric models resulting in more flexible models than standard parametric NLMEs. However, SNMMs are complex models for which estimation still remains a challenge. Previous estimation procedures are based on a combination of log-likelihood approximation methods for parametric estimation and smoothing splines techniques for nonparametric estimation. In this work, we propose new estimation strategies in SNMMs. On the one hand, we use the Stochastic Approximation version of EM algorithm (SAEM) to obtain exact ML and REML estimates of the fixed effects and variance components. On the other hand, we propose a LASSO-type method to estimate the unknown nonlinear function. We derive oracle inequalities for this nonparametric estimator. We combine the two approaches in a general estimation procedure that we illustrate with simulations and through the analysis of a real data set of price evolution in on-line auctions. Numéro de notice : A2014-790 Affiliation des auteurs : non IGN Thématique : MATHEMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11222-013-9380-x Date de publication en ligne : 07/02/2013 En ligne : http://dx.doi.org/10.1007/s11222-013-9380-x Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=79157 [article]