{ "cells": [ { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "# Autour du Paradoxe de Simpson" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Import des bibliothèses Pyhtons" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", "import pandas as pd\n", "import statsmodels.formula.api as smf\n", "import seaborn as sns" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Contexte et objectifs du travail" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "### Quelques éléments de contexte" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "En 1972-1974, à Whickham, une ville du nord-est de l'Angleterre, située à environ 6,5 kilomètres au sud ouest de Newcastle upon Tyne, un sondage d'un sixième des électeurs a été effectué afin d'éclairer des travaux sur les maladies thyroïdiennes et cardiaques (Tunbridge et al. 1977). Une suite de cette étude a été menée vingt ans plus tard (Vanderpump et al. 1995). Certains des résultats avaient trait au tabagisme et à savoir si les individus étaient toujours en vie lors de la seconde étude. Par simplicité, nous nous restreindrons aux femmes et parmi celles-ci aux 1314 qui ont été catégorisées comme \"fumant actuellement\" ou \"n'ayant jamais fumé\". Il y avait relativement peu de femmes dans le sondage initial ayant fumé mais ayant arrêté depuis (162) et très peu pour lesquelles l'information n'était pas disponible (18). La survie à 20 ans a été déterminée pour l'ensemble des femmes du premier sondage." ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "### Objectifs du travail" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "1. Représentez dans un tableau le nombre total de femmes vivantes et décédées sur la période en fonction de leur habitude de tabagisme. Calculez dans chaque groupe (fumeuses/ non fumeuses) le taux de mortalité (le rapport entre le nombre de femmes décédées dans un groupe avec le nombre total de femmes dans ce groupe). Vous pourrez proposer une représentation graphique de ces données et calculer des intervalles de confiance si vous le souhaitez. En quoi ce résultat est-il surprenant ?\n", "2. Reprenez la question 1 (effectifs et taux de mortalité) en rajoutant une nouvelle catégorie liée à la classe d'âge. On considérera par exemple les classes suivantes: 18-34 ans, 34-54 ans, 55-64 ans, plus de 65 ans. En quoi ce résultat est-il surprenant ? Arrivez vous à expliquer ce paradoxe ? De même, vous pourrez proposer une représentation graphique de ces données pour étayer vos explications.\n", "3. Afin d'éviter un biais induis par des regroupements en tranches d'âges arbitraires et non régulières, il est envisageable d'essayer de réaliser une régression logistique. Si on introduit une variable Death valant 1 ou 0 pour indiquer si l'individu est décédé durant la période de 20 ans, on peut étudier le modèle Death ~ Age pour étudier la probabilité de décès en fonction de l'âge selon que l'on considère le groupe des fumeuses ou des non fumeuses. Ces régressions vous permettent de conclure ou pas sur la nocivité du tabagisme ? Vous pourrez proposer une représentation graphique de ces régressions (en n'omettant pas les régions de confiance)." ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "## Réponse aux objectifs" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Les données sont disponibles sur l'espace gitlab [suivant](https://gitlab.inria.fr/learninglab/mooc-rr/mooc-rr-ressources/blob/master/module3/Practical_session/Subject6_smoking.csv). Elles sont importées directement depuis le lien correspondant dans la variable data_url:" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "data_url = \"https://gitlab.inria.fr/learninglab/mooc-rr/mooc-rr-ressources/-/raw/master/module3/Practical_session/Subject6_smoking.csv?inline=false\"" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Import des données dans Python et vérification que le fichier ne contient pas de ligne vide (ce n'est pas le cas)." ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
SmokerStatusAge
\n", "
" ], "text/plain": [ "Empty DataFrame\n", "Columns: [Smoker, Status, Age]\n", "Index: []" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "raw_data = pd.read_csv(data_url)\n", "raw_data[raw_data.isnull().any(axis=1)]" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "### Relation décès - tabagisme" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Affichage d'un tableau représentant le nombre total de femmes vivantes et décédées sur la période en fonction de leur habitude de tabagisme ainsi que le taux de mortalité." ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Smoker Status\n", "No Alive 502\n", " Dead 230\n", "Yes Alive 443\n", " Dead 139\n", "Name: Status, dtype: int64\n" ] } ], "source": [ "Table_1 = raw_data.groupby('Smoker').Status.value_counts()\n", "print(Table_1)" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Calcul du taux de mortalité par groupe et affichage des résultats." ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Taux_mortalite_fumeur = 0.23883161512027493\n", "Taux_mortalite_non_fumeur = 0.31420765027322406\n" ] } ], "source": [ "Taux_mortalite_fumeur = Table_1.Yes.Dead /(Table_1.Yes.Dead + Table_1.Yes.Alive)\n", "Taux_mortalite_non_fumeur = Table_1.No.Dead/(Table_1.No.Dead + Table_1.No.Alive)\n", "print(\"Taux_mortalite_fumeur =\", Taux_mortalite_fumeur)\n", "print(\"Taux_mortalite_non_fumeur =\", Taux_mortalite_non_fumeur)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "hideCode": false, "hidePrompt": false, "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "Taux_vivant = [1-Taux_mortalite_fumeur, 1-Taux_mortalite_non_fumeur]\n", "Taux_mort = [Taux_mortalite_fumeur, Taux_mortalite_non_fumeur]\n", "Habitude_tabagisme = ['Fumeuse','Non fumeuse']\n", "\n", "width = 0.35\n", "x = np.arange(len(Habitude_tabagisme))\n", "\n", "fig, ax = plt.subplots()\n", "ax.bar(x - width/2, Taux_mort, width,label = 'Mortes', color='k')\n", "ax.bar(x + width/2, Taux_vivant, width,label = 'Vivantes', color='b')\n", "\n", "ax.set_ylabel('Taux')\n", "ax.set_title('Taux de femmes mortes et vivantes suivant leur habitude de tabagisme')\n", "ax.set_xticks(x)\n", "ax.set_xticklabels(Habitude_tabagisme)\n", "ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "A première vue ces résultats sont donc contre-intuitifs et indiquent une mortalité plus importantes chez les individus non-fumeuses. L'analyse requiert donc une investigation supplémentaire des données." ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "### Prise en compte de l'age des individus" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Afin d'approfondir l'analyse, prenons en compte l'age des individus en les répatissant en quatre classes d'age : 18-34 ans, 35-54 ans, 55-64 ans, plus de 65 ans. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Création de la colonne listant les catégories d'age." ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "hideCode": false, "hidePrompt": false }, "outputs": [], "source": [ "Data_cat = raw_data\n", "Classe_age = [\"18-34\", \"35-54\", \"55-64\", \"65+\" ]\n", "Data_cat['Cat_age'] = pd.cut(Data_cat.Age, [18, 34, 54, 64, 200],include_lowest = True, labels=Classe_age)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Reprenons l'analyse précédente mais cette fois par classe d'age et non par habitude de tabagisme." ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Smoker Status\n", "No Alive 502\n", " Dead 230\n", "Yes Alive 443\n", " Dead 139\n", "Name: Status, dtype: int64\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "Table_2 = raw_data.groupby('Cat_age').Status.value_counts()\n", "print(Table_1)\n", "\n", "Taux_m_clas1 = Table_2['18-34'].Dead /(Table_2['18-34'].Dead + Table_2['18-34'].Alive)\n", "Taux_m_clas2 = Table_2['35-54'].Dead /(Table_2['35-54'].Dead + Table_2['35-54'].Alive)\n", "Taux_m_clas3 = Table_2['55-64'].Dead /(Table_2['55-64'].Dead + Table_2['55-64'].Alive)\n", "Taux_m_clas4 = Table_2['65+'].Dead /(Table_2['65+'].Dead + Table_2['65+'].Alive)\n", "\n", "Taux_vivant = [1-Taux_m_clas1, 1-Taux_m_clas2, 1-Taux_m_clas3, 1-Taux_m_clas4]\n", "Taux_mort = [Taux_m_clas1, Taux_m_clas2, Taux_m_clas3, Taux_m_clas4]\n", "\n", "width = 0.35\n", "x = np.arange(len(Classe_age))\n", "\n", "fig, ax = plt.subplots()\n", "ax.bar(x - width/2, Taux_mort, width,label = 'Mortes', color='k')\n", "ax.bar(x + width/2, Taux_vivant, width,label = 'Vivantes', color='b')\n", "\n", "ax.set_ylabel('Taux')\n", "ax.set_title('Taux de femmes mortes et vivantes suivant leur age')\n", "ax.set_xticks(x)\n", "ax.set_xticklabels(Classe_age)\n", "ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Or, il apparait que les individus \"fumeuses\" de l'échantillon sont plus jeunes que les \"non-fumeuses\". Les moyennes d'age pour chaque groupe sont en effet de:" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Age\n", "Smoker \n", "No 49.815847\n", "Yes 44.269759\n" ] } ], "source": [ "Moyenne_age = raw_data.groupby('Smoker').mean()\n", "print(Moyenne_age)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Avec un écart type de :" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Age\n", "Smoker \n", "No 20.898294\n", "Yes 16.217886\n" ] } ], "source": [ "Std_age = raw_data.groupby('Smoker').std()\n", "print(Std_age)" ] }, { "cell_type": "markdown", "metadata": { "hideCode": false, "hidePrompt": false }, "source": [ "Visualisons la répartition en classe d'age par habitude de tabagisme." ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "Table_2 = raw_data.groupby('Smoker').Cat_age.value_counts()\n", "Habitude_tabagisme = ['Fumeuse','Non fumeuse']\n", "Clas_1 = [Table_2.Yes['18-34'], Table_2.No['18-34']]\n", "Clas_2 = [Table_2.Yes['35-54'], Table_2.No['35-54']]\n", "Clas_3 = [Table_2.Yes['55-64'], Table_2.No['55-64']]\n", "Clas_4 = [Table_2.Yes['65+'], Table_2.No['65+']]\n", "\n", "width = 0.2\n", "x = np.arange(len(Habitude_tabagisme))\n", "\n", "fig, ax = plt.subplots()\n", "ax.bar(x - 3*width/2, Clas_1, width,label = '18-34')\n", "ax.bar(x - width/2, Clas_2, width,label = '35-54')\n", "ax.bar(x + width/2, Clas_3, width,label = '55-64')\n", "ax.bar(x + 3*width/2, Clas_4, width,label = '65+')\n", "\n", "ax.set_ylabel('Taux')\n", "ax.set_title('Taux de femmes mortes et vivantes suivant leur habitude de tabagisme')\n", "ax.set_xticks(x)\n", "ax.set_xticklabels(Habitude_tabagisme)\n", "ax.legend(loc='center left', bbox_to_anchor=(1, 0.5))\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Cete analyse complémentaire semble ainsi montrer que la surmortalité chez les non-fumeuse est avant tout liée à une suresprésentation des catégories d'age plus élevée, le taux de mortalité étant fortement lié à l'age." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Utilisation d'une regression logistique" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Afin d'éviter un biais induis par des regroupements en tranches d'âges arbitraires et non régulières, utilisons une regresion logistique. " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Une variable Death qui vaut 0 ou 1 suivant que l'individu est décédé ou non est introduite." ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5,1,'Regression logistique - Death vs Age')" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "Data_deat = raw_data\n", "Data_deat['Death'] = np.where(Data_deat['Status'] == 'Alive', 0, 1)\n", "\n", "sns.regplot(x= Data_deat.Age, y= Data_deat.Death, logistic= True).set_title(\"Regression logistique - Death vs Age\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Cette regression logistique confirme bien la forte dépendance entre age et taux de mortalité." ] } ], "metadata": { "hide_code_all_hidden": false, "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.4" } }, "nbformat": 4, "nbformat_minor": 2 }