{"id":3172,"date":"2015-07-21T07:53:40","date_gmt":"2015-07-21T06:53:40","guid":{"rendered":"https:\/\/abcdr.guyader.pro\/?p=3172"},"modified":"2018-04-08T00:02:16","modified_gmt":"2018-04-07T23:02:16","slug":"comment-comparer-deux-moyennes-sur-r-lorsque-les-donnees-ne-suivent-pas-une-loi-normale-wilcox-test","status":"publish","type":"post","link":"https:\/\/thinkr.fr\/abcdr\/comment-comparer-deux-moyennes-sur-r-lorsque-les-donnees-ne-suivent-pas-une-loi-normale-wilcox-test\/","title":{"rendered":"Comment comparer deux moyennes sur R lorsque les donn\u00e9es ne suivent pas une loi Normale ? wilcox.test"},"content":{"rendered":"<p>Le test non-param\u00e9trique de Wilcoxon permet de tester l\u2019\u00e9galit\u00e9 de deux moyennes lorsque l\u2019hypoth\u00e8se de normalit\u00e9 n\u2019est pas valid\u00e9e. L\u2019hypoth\u00e8se H0 est \u00ab\u00a0les moyennes sont \u00e9gales\u00a0\u00bb ou \u00ab\u00a0la moyenne vaut une valeur x\u00a0\u00bb.<\/p>\n<p>Pour r\u00e9aliser ce test il est n\u00e9cessaire d\u2019avoir un \u00e9chantillonnage al\u00e9atoire et que les lois suivies par les deux variables \u00e9tudi\u00e9es soient les m\u00eames. Pour tester l\u2019hypoth\u00e8se H0 on utilise la fonction <b>wilcox.test().<\/b><\/p>\n<pre><code><br \/>A&lt;-subset(iris,Species==\"setosa\")[,4]\n\n#\u00e9chantillonnage de la largeur des p\u00e9tales chez l\u2019esp\u00e8ce Setosa.\n\n\u00a0\n\nB&lt;-subset(iris,Species==\"versicolor\")[,4]\n\n#\u00e9chantillonnage de la largeur des p\u00e9tales chez l\u2019esp\u00e8ce Versicolor.\n\n\u00a0\u00a0\u00a0\u00a0\n\n#On test si la moyenne de la largeur des p\u00e9tales de l'esp\u00e8ce Setosa vaut 0.5 :\n\nwilcox.test(A,0.5)\n\n\u00a0\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 Wilcoxon rank sum test with continuity correction\n\n\u00a0\n\ndata:\u00a0 A and 0.5\n\nW = 1.5, p-value = 0.08259\n\nalternative hypothesis: true location shift is not equal to 0\u00a0\n\n<\/code><\/pre>\n<p>La p-value vaut 0.08 ce qui est sup\u00e9rieure \u00e0 0.05. Cela signifie que la moyenne de la largeur des p\u00e9tales pour l\u2019esp\u00e8ce setosa n\u2019est pas significativement diff\u00e9rente de 0.5.<\/p>\n<p>\u00a0<\/p>\n<p>On test si la moyenne de la largeur des p\u00e9tales de l&rsquo;esp\u00e8ce Setosa et celle de Versicolor sont \u00e9gales ou non\u00a0:<\/p>\n<pre><code><br \/>wilcox.test(A,B)\n\n\u00a0\n\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 Wilcoxon rank sum test with continuity correction\n\n\u00a0\n\ndata:\u00a0 A and B\n\nW = 0, p-value &lt; 2.2e-16\n\nalternative hypothesis: true location shift is not equal to 0\n\n<\/code><\/pre>\n<p>\u00a0<\/p>\n<p>La p-value est inf\u00e9rieure \u00e0 0.05. Cela signifie que la moyenne de la largeur des p\u00e9tales pour l\u2019esp\u00e8ce setosa est significativement diff\u00e9rente de celle de l\u2019esp\u00e8ce Versicolor.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Le test non-param\u00e9trique de Wilcoxon permet de tester l\u2019\u00e9galit\u00e9 de deux moyennes lorsque l\u2019hypoth\u00e8se de normalit\u00e9 n\u2019est pas valid\u00e9e. L\u2019hypoth\u00e8se H0 est \u00ab\u00a0les moyennes sont \u00e9gales\u00a0\u00bb ou \u00ab\u00a0la moyenne vaut une valeur x\u00a0\u00bb. Pour r\u00e9aliser ce test il est n\u00e9cessaire d\u2019avoir un \u00e9chantillonnage al\u00e9atoire et que les lois suivies par les deux variables \u00e9tudi\u00e9es soient les m\u00eames. Pour tester l\u2019hypoth\u00e8se H0 on utilise la fonction wilcox.test(). A&lt;-subset(iris,Species==\u00a0\u00bbsetosa\u00a0\u00bb)[,4] #\u00e9chantillonnage de la largeur des p\u00e9tales chez l\u2019esp\u00e8ce Setosa. \u00a0 B&lt;-subset(iris,Species==\u00a0\u00bbversicolor\u00a0\u00bb)[,4] #\u00e9chantillonnage de la largeur des p\u00e9tales chez l\u2019esp\u00e8ce Versicolor. \u00a0\u00a0\u00a0\u00a0 #On test si la moyenne de la largeur des p\u00e9tales de l&rsquo;esp\u00e8ce Setosa vaut 0.5 : wilcox.test(A,0.5)<a class=\"more-link\" href=\"https:\/\/thinkr.fr\/abcdr\/comment-comparer-deux-moyennes-sur-r-lorsque-les-donnees-ne-suivent-pas-une-loi-normale-wilcox-test\/\">Read More &rarr;<\/a><\/p>\n","protected":false},"author":13,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","rop_custom_images_group":[],"rop_custom_messages_group":[],"rop_publish_now":"initial","rop_publish_now_accounts":{"twitter_399453572_399453572":""},"rop_publish_now_history":[],"rop_publish_now_status":"pending","jetpack_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[21],"tags":[],"class_list":{"0":"entry","1":"post","2":"publish","3":"author-helene","4":"post-3172","6":"format-standard","7":"category-test"},"acf":[],"jetpack_featured_media_url":"","jetpack_shortlink":"https:\/\/wp.me\/p9O7Sx-Pa","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/posts\/3172","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/users\/13"}],"replies":[{"embeddable":true,"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/comments?post=3172"}],"version-history":[{"count":2,"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/posts\/3172\/revisions"}],"predecessor-version":[{"id":4291,"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/posts\/3172\/revisions\/4291"}],"wp:attachment":[{"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/media?parent=3172"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/categories?post=3172"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/thinkr.fr\/abcdr\/wp-json\/wp\/v2\/tags?post=3172"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}