{"id":160,"date":"2025-07-27T13:06:26","date_gmt":"2025-07-27T11:06:26","guid":{"rendered":"https:\/\/giulia-governatori.alwaysdata.net\/?p=160"},"modified":"2025-08-12T20:35:56","modified_gmt":"2025-08-12T18:35:56","slug":"warning-fake-analyst","status":"publish","type":"post","link":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/warning-fake-analyst\/","title":{"rendered":"Statistiques trompeuses: m\u00e9fiez-vous des faux experts"},"content":{"rendered":"<hr class=\"wp-block-separator aligncenter has-alpha-channel-opacity is-style-wide\"\/>\n\n\n\n<p style=\"font-size:23px\"><strong>Les statistiques aident quand on les lit avec recul; l\u2019interpr\u00e9tation fait la diff\u00e9rence \u2014 m\u00e9fiez-vous des \u00ab analystes \u00bb autoproclam\u00e9s qui agitent des pourcentages pour vous orienter.\u00a0<\/strong><\/p>\n\n\n<style>.wp-block-kadence-advancedheading.kt-adv-heading160_01530c-af, .wp-block-kadence-advancedheading.kt-adv-heading160_01530c-af[data-kb-block=\"kb-adv-heading160_01530c-af\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading160_01530c-af mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading160_01530c-af[data-kb-block=\"kb-adv-heading160_01530c-af\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading160_01530c-af img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading160_01530c-af[data-kb-block=\"kb-adv-heading160_01530c-af\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h2 class=\"kt-adv-heading160_01530c-af wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading160_01530c-af\">Le pi\u00e8ge des chiffres bruts<\/h2>\n\n\n\n<p class=\"translation-block\">Nous vivons aujourd\u2019hui dans un monde o\u00f9 chacun peut facilement publier des chiffres, partager les  r\u00e9sultats d\u2019un sondage ou m\u00eame s\u2019autoproclamer \u00ab expert en donn\u00e9es \u00bb apr\u00e8s quelques rapides  recherches sur Internet. Cependant, comme le rappelle brillamment le statisticien David  Spiegelhalter dans son ouvrage The Art of Statistics, les donn\u00e9es en elles-m\u00eames ne disent pas tout :  leur interpr\u00e9tation peut radicalement changer la donne.<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-style-default is-layout-flow wp-block-quote-is-layout-flow\">\n<p class=\"has-text-align-center\"><strong>\u201cData do not speak for themselves. We speak for them.\u201d<\/strong><br>\u2014 <em>David Spiegelhalter<\/em><\/p>\n<\/blockquote>\n\n\n<style>.wp-block-kadence-advancedheading.kt-adv-heading160_989096-c5, .wp-block-kadence-advancedheading.kt-adv-heading160_989096-c5[data-kb-block=\"kb-adv-heading160_989096-c5\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading160_989096-c5 mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading160_989096-c5[data-kb-block=\"kb-adv-heading160_989096-c5\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading160_989096-c5 img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading160_989096-c5[data-kb-block=\"kb-adv-heading160_989096-c5\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h3 class=\"kt-adv-heading160_989096-c5 wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading160_989096-c5\">L\u2019exemple trompeur des 99%<\/h3>\n\n\n<style>.kb-image160_c29467-33.kb-image-is-ratio-size, .kb-image160_c29467-33 .kb-image-is-ratio-size{max-width:228px;width:100%;}.wp-block-kadence-column > .kt-inside-inner-col > .kb-image160_c29467-33.kb-image-is-ratio-size, .wp-block-kadence-column > .kt-inside-inner-col > .kb-image160_c29467-33 .kb-image-is-ratio-size{align-self:unset;}.kb-image160_c29467-33 figure{max-width:228px;}.kb-image160_c29467-33 .image-is-svg, .kb-image160_c29467-33 .image-is-svg img{width:100%;}.kb-image160_c29467-33 .kb-image-has-overlay:after{opacity:0.3;}<\/style>\n<div class=\"wp-block-kadence-image kb-image160_c29467-33\"><figure class=\"alignright size-medium\"><img loading=\"lazy\" decoding=\"async\" width=\"368\" height=\"600\" src=\"https:\/\/giulia-governatori.alwaysdata.net\/wp-content\/uploads\/71HNF5BMTCL._UF10001000_QL80_-copie-368x600.webp\" alt=\"couverture livre &quot;The art of Statistics&quot; de David Spiegelhalter\" class=\"kb-img wp-image-1288\" srcset=\"https:\/\/giulia-governatori.alwaysdata.net\/wp-content\/uploads\/71HNF5BMTCL._UF10001000_QL80_-copie-368x600.webp 368w, https:\/\/giulia-governatori.alwaysdata.net\/wp-content\/uploads\/71HNF5BMTCL._UF10001000_QL80_-copie-92x150.webp 92w, https:\/\/giulia-governatori.alwaysdata.net\/wp-content\/uploads\/71HNF5BMTCL._UF10001000_QL80_-copie-7x12.webp 7w, https:\/\/giulia-governatori.alwaysdata.net\/wp-content\/uploads\/71HNF5BMTCL._UF10001000_QL80_-copie.webp 613w\" sizes=\"auto, (max-width: 368px) 100vw, 368px\" \/><\/figure><\/div>\n\n\n\n<p>Prenons l\u2019exemple concret que Spiegelhalter mentionne, tir\u00e9 d\u2019une campagne publicitaire men\u00e9e  par la ville de Londres. Celle-ci annon\u00e7ait fi\u00e8rement : \u00ab 99% des jeunes Londoniens ne commettent  pas d'actes violents graves \u00bb. \u00c0 premi\u00e8re vue, ce message est rassurant et positif. Pourtant, si l\u2019on y  regarde de plus pr\u00e8s, ce 1% restant correspond tout de m\u00eame \u00e0 environ 10000 jeunes, ce qui  implique une r\u00e9alit\u00e9 beaucoup plus inqui\u00e9tante. Ainsi, ce chiffre cens\u00e9 rassurer r\u00e9v\u00e8le en r\u00e9alit\u00e9 une  situation pr\u00e9occupante.&nbsp;<\/p>\n\n\n\n<p>Imaginons maintenant lire un gros titre comme \u00ab La majorit\u00e9 des crimes en France est commise par  des \u00e9trangers \u00bb. Un tel message attire imm\u00e9diatement l\u2019attention et peut susciter l\u2019inqui\u00e9tude. Mais  en creusant davantage, on d\u00e9couvre que les statistiques sous-jacentes sont simplifi\u00e9es et trompeuses.&nbsp;<\/p>\n\n\n\n<p>En effet, les statistiques utilisent souvent une classification binaire : \u00ab fran\u00e7ais \u00bb ou \u00ab non fran\u00e7ais \u00bb.  Toutefois, cette cat\u00e9gorie \u00ab non fran\u00e7ais \u00bb comprend aussi toutes les personnes dont l\u2019origine  pr\u00e9cise est inconnue, par exemple des individus sans papiers au moment de leur arrestation, ceux  qui refusent de communiquer leur origine, ou m\u00eame des personnes n\u00e9es en France mais n\u2019ayant pas  encore la nationalit\u00e9. <\/p>\n\n\n\n<p>Le r\u00e9sultat est une cat\u00e9gorie artificiellement gonfl\u00e9e, donnant ainsi une image d\u00e9form\u00e9e de la r\u00e9alit\u00e9, ce qui peut alimenter injustement certains st\u00e9r\u00e9otypes.&nbsp;<\/p>\n\n\n<style>.wp-block-kadence-advancedheading.kt-adv-heading160_b6a20e-1d, .wp-block-kadence-advancedheading.kt-adv-heading160_b6a20e-1d[data-kb-block=\"kb-adv-heading160_b6a20e-1d\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading160_b6a20e-1d mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading160_b6a20e-1d[data-kb-block=\"kb-adv-heading160_b6a20e-1d\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading160_b6a20e-1d img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading160_b6a20e-1d[data-kb-block=\"kb-adv-heading160_b6a20e-1d\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h2 class=\"kt-adv-heading160_b6a20e-1d wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading160_b6a20e-1d\">Le contexte change tout<\/h2>\n\n\n\n<p>Cet exemple illustre parfaitement comment des donn\u00e9es mal interpr\u00e9t\u00e9es peuvent induire le public  en erreur. Il souligne l\u2019importance capitale d\u2019une analyse effectu\u00e9e par des professionnels  comp\u00e9tents.&nbsp;<\/p>\n\n\n\n<p>De m\u00eame, Spiegelhalter \u00e9voque souvent un autre cas c\u00e9l\u00e8bre : le risque accru de cancer colorectal  chez les amateurs de sandwichs au bacon. Affirmer qu\u2019il augmente de \u00ab 18% \u00bb peut sembler  effrayant. Pourtant, concr\u00e8tement, cela signifie simplement passer de 6 \u00e0 7 cas pour 100 personnes.  Pr\u00e9sent\u00e9e sans contexte clair, cette statistique peut donc facilement induire une perception erron\u00e9e  et alarmiste.&nbsp;<\/p>\n\n\n<style>.wp-block-kadence-advancedheading.kt-adv-heading160_049169-92, .wp-block-kadence-advancedheading.kt-adv-heading160_049169-92[data-kb-block=\"kb-adv-heading160_049169-92\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading160_049169-92 mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading160_049169-92[data-kb-block=\"kb-adv-heading160_049169-92\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading160_049169-92 img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading160_049169-92[data-kb-block=\"kb-adv-heading160_049169-92\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h3 class=\"kt-adv-heading160_049169-92 wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading160_049169-92\">Comment \u00e9viter les pi\u00e8ges statistiques<\/h3>\n\n\n\n<p>Alors comment \u00e9viter de tomber dans ces pi\u00e8ges statistiques ? Voici quelques conseils inspir\u00e9s par  l'approche rigoureuse des vrais professionnels du secteur :&nbsp;<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>V\u00e9rifiez la m\u00e9thodologie<\/strong>: Un grand nombre de r\u00e9ponses ne garantit pas un \u00e9chantillon repr\u00e9sentatif. Les vrais analystes savent qu'une \u00e9tude s\u00e9rieuse n\u00e9cessite une m\u00e9thodologie rigoureuse.<\/li>\n\n\n\n<li><strong>M\u00e9fiez-vous des graphiques s\u00e9duisants<\/strong>: Un graphique peut facilement tromper en  utilisant une \u00e9chelle tronqu\u00e9e ou en manipulant la pr\u00e9sentation visuelle.&nbsp;<\/li>\n\n\n\n<li><strong>Distinction entre corr\u00e9lation et causalit\u00e9<\/strong>: Deux variables qui \u00e9voluent simultan\u00e9ment ne  sont pas n\u00e9cessairement li\u00e9es par une relation de cause \u00e0 effet. L'exp\u00e9rience et la formation  professionnelle permettent de distinguer ces nuances essentielles.&nbsp;<\/li>\n<\/ul>\n\n\n<style>.wp-block-kadence-advancedheading.kt-adv-heading160_6d5792-8e, .wp-block-kadence-advancedheading.kt-adv-heading160_6d5792-8e[data-kb-block=\"kb-adv-heading160_6d5792-8e\"]{font-style:normal;}.wp-block-kadence-advancedheading.kt-adv-heading160_6d5792-8e mark.kt-highlight, .wp-block-kadence-advancedheading.kt-adv-heading160_6d5792-8e[data-kb-block=\"kb-adv-heading160_6d5792-8e\"] mark.kt-highlight{font-style:normal;color:#f76a0c;-webkit-box-decoration-break:clone;box-decoration-break:clone;padding-top:0px;padding-right:0px;padding-bottom:0px;padding-left:0px;}.wp-block-kadence-advancedheading.kt-adv-heading160_6d5792-8e img.kb-inline-image, .wp-block-kadence-advancedheading.kt-adv-heading160_6d5792-8e[data-kb-block=\"kb-adv-heading160_6d5792-8e\"] img.kb-inline-image{width:150px;vertical-align:baseline;}<\/style>\n<h2 class=\"kt-adv-heading160_6d5792-8e wp-block-kadence-advancedheading\" data-kb-block=\"kb-adv-heading160_6d5792-8e\">Conclusion : des chiffres, oui, mais bien interpr\u00e9t\u00e9s<\/h2>\n\n\n\n<p>Faire confiance aux donn\u00e9es, c'est bien. Mais faire confiance \u00e0 celui ou celle qui les interpr\u00e8te  aveugl\u00e9ment, c'est risqu\u00e9. La v\u00e9ritable ma\u00eetrise des statistiques demande des \u00e9tudes, de pratique, de  m\u00e9thodologie et de r\u00e9flexion critique. Alors, avant d\u2019accepter une conclusion spectaculaire, assurez vous que derri\u00e8re les chiffres se trouve un v\u00e9ritable professionnel de l\u2019analyse des donn\u00e9es.<\/p>","protected":false},"excerpt":{"rendered":"<p>Statistics help when read with care; interpretation makes the difference \u2014 beware of self\u2011styled \u201canalysts\u201d who sling percentages to steer you.\u00a0 The trap of raw numbers Today, we live in a world where anyone can easily publish numbers, share survey results, or even&nbsp; claim to be a \u201cdata expert\u201d after a few quick Google searches&#8230;.<\/p>","protected":false},"author":1,"featured_media":184,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_kad_post_transparent":"","_kad_post_title":"","_kad_post_layout":"","_kad_post_sidebar_id":"","_kad_post_content_style":"","_kad_post_vertical_padding":"","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"_kad_post_classname":"","footnotes":""},"categories":[1],"tags":[],"class_list":["post-160","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-non-classe"],"_links":{"self":[{"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/posts\/160","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/comments?post=160"}],"version-history":[{"count":0,"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/posts\/160\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/media\/184"}],"wp:attachment":[{"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/media?parent=160"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/categories?post=160"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/giulia-governatori.alwaysdata.net\/fr\/wp-json\/wp\/v2\/tags?post=160"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}