{"id":947,"date":"2022-01-21T20:47:25","date_gmt":"2022-01-21T19:47:25","guid":{"rendered":"https:\/\/mastermas.univ-lyon1.fr\/?page_id=947"},"modified":"2022-05-30T12:22:08","modified_gmt":"2022-05-30T10:22:08","slug":"regressions-et-grande-dimension","status":"publish","type":"page","link":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/regressions-et-grande-dimension\/","title":{"rendered":"REGRESSIONS ET GRANDE DIMENSION"},"content":{"rendered":"\n<p>R\u00e9gression lin\u00e9aire multiple.<\/p>\n\n\n\n<p>Mod\u00e8les d\u2019analyse de variance, r\u00e9gression logistique.<\/p>\n\n\n\n<p>Mod\u00e8les lin\u00e9aires sous des conditions non standard\u00a0: m\u00e9thodes d\u2019estimation quantile et expectile.<\/p>\n\n\n\n<p>R\u00e9gression PLS,<\/p>\n\n\n\n<p>Pour toutes ces mod\u00e8les param\u00e9triques, les propri\u00e9t\u00e9s th\u00e9oriques des estimateurs correspondants sont \u00e9tudi\u00e9es, avec comparaison entre diff\u00e9rentes m\u00e9thodes. Ces propri\u00e9t\u00e9s vont permettre de consid\u00e9rer des tests d\u2019hypoth\u00e8se. Les m\u00e9thodes num\u00e9riques pour trouver les estimations seront abord\u00e9es. Applications sur des donn\u00e9es r\u00e9elles en utilisant les logiciels sp\u00e9cifiques R ou SAS.<\/p>\n\n\n\n<p>Pour les mod\u00e8les lin\u00e9aires en grande et tr\u00e8s grande dimension, avec des variables group\u00e9es ou non group\u00e9es, les m\u00e9thodes de type LASSO permettent la s\u00e9lection automatique des variables. Les propri\u00e9t\u00e9s oracle et les algorithmes associ\u00e9s seront \u00e9tudi\u00e9s. Les fonctions de perte seront envisag\u00e9es par rapport aux suppositions du mod\u00e8le&nbsp;: moindres carr\u00e9s, quantile, expectile. Applications sur des donn\u00e9es r\u00e9elles en utilisant diff\u00e9rents packages du logiciel R.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>R\u00e9gression lin\u00e9aire multiple. Mod\u00e8les d\u2019analyse de variance, r\u00e9gression logistique. Mod\u00e8les lin\u00e9aires sous des conditions non standard\u00a0: m\u00e9thodes d\u2019estimation quantile et expectile. R\u00e9gression PLS, Pour toutes ces mod\u00e8les param\u00e9triques, les propri\u00e9t\u00e9s th\u00e9oriques des estimateurs correspondants sont \u00e9tudi\u00e9es, avec comparaison entre diff\u00e9rentes m\u00e9thodes. Ces propri\u00e9t\u00e9s vont permettre de consid\u00e9rer des tests d\u2019hypoth\u00e8se. Les m\u00e9thodes num\u00e9riques pour trouver <a class=\"more-link\" href=\"https:\/\/mastermas.univ-lyon1.fr\/index.php\/regressions-et-grande-dimension\/\">Lire plus &#8230;<\/a><\/p>\n","protected":false},"author":6,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-947","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/wp-json\/wp\/v2\/pages\/947","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/wp-json\/wp\/v2\/comments?post=947"}],"version-history":[{"count":2,"href":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/wp-json\/wp\/v2\/pages\/947\/revisions"}],"predecessor-version":[{"id":1113,"href":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/wp-json\/wp\/v2\/pages\/947\/revisions\/1113"}],"wp:attachment":[{"href":"https:\/\/mastermas.univ-lyon1.fr\/index.php\/wp-json\/wp\/v2\/media?parent=947"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}