From b7e1d6466ea9b125c2bbb3215c186562fd30f18c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fran=C3=A7ois=20Laurent?= <francois.laurent@posteo.net>
Date: Sun, 26 Sep 2021 19:52:25 +0200
Subject: [PATCH] small additions in conf. int. and lin. regr.

---
 notebooks/scipy_TP.ipynb           | 666 +++++++++++++++++++++++++++++
 notebooks/scipy_TP_solutions.ipynb | 416 +++++++++++++-----
 notebooks/scipy_cours.ipynb        | 282 ++++++++++--
 3 files changed, 1217 insertions(+), 147 deletions(-)
 create mode 100644 notebooks/scipy_TP.ipynb

diff --git a/notebooks/scipy_TP.ipynb b/notebooks/scipy_TP.ipynb
new file mode 100644
index 0000000..c5ddcb4
--- /dev/null
+++ b/notebooks/scipy_TP.ipynb
@@ -0,0 +1,666 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a5a5210d",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Import `numpy`, `pandas`, the `pyplot` module from `matplotlib`, `seaborn`, and the `stats` module from `scipy`."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5ac6cc32",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "529c5f56",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93ad4aaf",
+   "metadata": {},
+   "source": [
+    "# Comparison of two group means"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0e4fd0d9",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Load the `mi.csv` data file located in the `data` directory of the course repository."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "08c1dd12",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "00130518",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9cc036b2",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Anything missing?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "99d5dc74",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8a648a9b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3512f950",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Show a summary table for these data."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6984434b",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7a7d087",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "04163591",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Inspect the distribution of variables `Age` and `OwnsHouse`."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d6baac23",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5de6412d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e94c17b",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Isolate the house-owners group from the others, draw their respective age distributions and report their mean ages as $99\\%$ confidence intervals."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "497142f3",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "55d18f16",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ea79970d",
+   "metadata": {},
+   "source": [
+    "## Q\n",
+    "\n",
+    "Check the age is normally distributed in any one group, first following a graphical approach."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c23a350",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15e4d4c9",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## A (with nested Q&A)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "id": "ddf5d4b0",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "(theoretical_quantiles, observed_quantiles), (slope, intercept, _) = stats.probplot(house_owners_age, fit=True)\n",
+    "plt.scatter(theoretical_quantiles, observed_quantiles, marker='+', color='b')\n",
+    "plt.axline((0, intercept), slope=slope, color='r')\n",
+    "plt.xlabel('theoretical quantiles')\n",
+    "plt.ylabel('ordered observations (age)');"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "24b49c4c",
+   "metadata": {
+    "hidden": true
+   },
+   "source": [
+    "The red line is fitted to the blue points and does not align well on the linear part.\n",
+    "\n",
+    "### Q\n",
+    "\n",
+    "To better illustrate that the central part is approximately linear, perform a linear regression with the observations whose corresponding theoretical quantiles (abscissa) fall in the $[-1,1]$ interval, and make a probability plot replacing the default regression line by your regression line."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e6f91f58",
+   "metadata": {
+    "hidden": true
+   },
+   "source": [
+    "### A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0f888c53",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2cc80be1",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Are the sample size and variance of the two groups similar enough for running a standard $t$ test?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cd58c73a",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0dbb79f7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d61f454a",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Test the group mean ages equal."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b076e8e6",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1d238900",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "62b30b76",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "How would you report the result of this test?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "efeac3ab",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "341157b6",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f72698b7",
+   "metadata": {},
+   "source": [
+    "## Q\n",
+    "\n",
+    "\\[optional; good for playing with Python rather than statistical methods\\]\n",
+    "\n",
+    "Although tractable in principle, the group difference in variance is quite large and -- had we smaller samples -- we could instead use the Welch's $t$ test that is known to better control for type-1 errors in cases of differing variances, but also a slightly lower power.\n",
+    "\n",
+    "As it is now clear we have a relationship between age and owning a house, let us compute the rejection rate (or power) as a function of sample size.\n",
+    "\n",
+    "Proposal:\n",
+    "* loop over decreasing sample sizes (*e.g.* 200, 50, 20, 10, 5),\n",
+    "* randomly pick a subsample of that size from each group,\n",
+    "* compare their means using the standard Student $t$-test and Welch $t$-test,\n",
+    "* observe whether each test successfully rejects $H_0$ for a constant significance level (*e.g.* 5%),\n",
+    "* replicate this procedure many times (*e.g.* 100)\n",
+    "* and compute the rejection rate for each sample size and type of test."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b7d5d56",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Help: subsampling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "ee947953",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# let us consider an example sample\n",
+    "sample = others_age\n",
+    "\n",
+    "# and a subsample size\n",
+    "n = 200\n",
+    "\n",
+    "# we need a random generator\n",
+    "rng = np.random.default_rng()\n",
+    "\n",
+    "# now we can pick n observations from the original sample\n",
+    "# calling the `choice` method of the random generator\n",
+    "subsample = rng.choice(sample, n)\n",
+    "\n",
+    "# in principle the smaller sample will exhibit similar\n",
+    "# properties as the original sample; both are drawn from\n",
+    "# the population in similar ways\n",
+    "bins = np.arange(20, 70+1, 5)\n",
+    "sns.histplot(sample, bins=bins)\n",
+    "sns.histplot(subsample, bins=bins);"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b44a7b2b",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "81e31c08",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b7d98432",
+   "metadata": {},
+   "source": [
+    "# Comparing two distributions"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7f5453a9",
+   "metadata": {},
+   "source": [
+    "Now let proceed to comparing age between people living with kids and those living without kids.\n",
+    "Plot the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "0aeaeee7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "02cbfb3c",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "How do the common descriptive statistics (mean, variance) compare?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d2f481d2",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e9c1cc3c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "34b67889",
+   "metadata": {},
+   "source": [
+    "## Q\n",
+    "\n",
+    "How can we compare the two groups to state they differ from one another?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dd8085f4",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89181560",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## A (with nested Q&A)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef4093df",
+   "metadata": {
+    "hidden": true
+   },
+   "source": [
+    "We need a two-sample goodness-of-fit test.\n",
+    "\n",
+    "This can be done in two ways:\n",
+    "\n",
+    "* with a $\\chi^2$ test of homogeneity, binning the age;\n",
+    "* with a two-sample Kolmogorov-Smirnov test.\n",
+    "\n",
+    "### Q\n",
+    "\n",
+    "Bin the two groups, first with 5-year-wide bins, extract frequencies and proceed to performing a $\\chi^2$ test."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4338fe92",
+   "metadata": {
+    "hidden": true
+   },
+   "source": [
+    "### A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f57a8ff6",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "218a59ec",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Are all the assumptions met? Adjust the procedure if necessary. Any interpretation?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "abdce59a",
+   "metadata": {},
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3e64b5ce",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1be0bd8d",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "# ..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f2a026da",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.8.10"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": false,
+   "sideBar": false,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "384px"
+   },
+   "toc_section_display": false,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/scipy_TP_solutions.ipynb b/notebooks/scipy_TP_solutions.ipynb
index 878502a..9d54cb7 100644
--- a/notebooks/scipy_TP_solutions.ipynb
+++ b/notebooks/scipy_TP_solutions.ipynb
@@ -3,7 +3,9 @@
   {
    "cell_type": "markdown",
    "id": "a5a5210d",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -47,7 +49,9 @@
   {
    "cell_type": "markdown",
    "id": "0e4fd0d9",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -287,7 +291,9 @@
   {
    "cell_type": "markdown",
    "id": "9cc036b2",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -708,7 +714,9 @@
   {
    "cell_type": "markdown",
    "id": "3512f950",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -992,7 +1000,9 @@
   {
    "cell_type": "markdown",
    "id": "04163591",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -1074,7 +1084,17 @@
    "source": [
     "## Q\n",
     "\n",
-    "Isolate the house-owners group from the others, draw their respective age distributions and check they are normally distributed."
+    "Isolate the house-owners group from the others, draw their respective age distributions and report their mean ages as $99\\%$ confidence intervals."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "497142f3",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## A"
    ]
   },
   {
@@ -1118,9 +1138,81 @@
     "sns.histplot(hue='OwnsHouse', y='Age', data=df, kde=True);"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "a721a374",
+   "metadata": {
+    "hidden": true
+   },
+   "source": [
+    "For the confidence intervals, we need to evaluate the inverse survival function of the standard normal distribution at $0.5\\%$."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "1fca5a60",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [],
+   "source": [
+    "alpha = 0.01\n",
+    "z = stats.norm().isf(alpha / 2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "9f044f06",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "House owners: 39.82 ± 2.25 years old on average\n",
+      "Others: 50.12 ± 1.32 years old on average\n"
+     ]
+    }
+   ],
+   "source": [
+    "for group_name, group_age in (\n",
+    "    ('House owners', house_owners_age),\n",
+    "    ('Others', others_age),\n",
+    "):\n",
+    "    m = np.mean(group_age)\n",
+    "    z_times_sem = z * stats.sem(group_age)\n",
+    "    print(f'{group_name}: {m:.2f} ± {z_times_sem:.2f} years old on average')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ea79970d",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Check the age is normally distributed in any one group, first following a graphical approach."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15e4d4c9",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## A (with nested Q&A)"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 37,
    "id": "ddf5d4b0",
    "metadata": {
     "hidden": true
@@ -1128,7 +1220,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -1142,7 +1234,9 @@
    "source": [
     "(theoretical_quantiles, observed_quantiles), (slope, intercept, _) = stats.probplot(house_owners_age, fit=True)\n",
     "plt.scatter(theoretical_quantiles, observed_quantiles, marker='+', color='b')\n",
-    "plt.axline((0, intercept), slope=slope, color='r');"
+    "plt.axline((0, intercept), slope=slope, color='r')\n",
+    "plt.xlabel('theoretical quantiles')\n",
+    "plt.ylabel('ordered observations (age)');"
    ]
   },
   {
@@ -1152,12 +1246,27 @@
     "hidden": true
    },
    "source": [
-    "The red line is fitted to the blue points and does not align well on the linear part. To better illustrate what is the linear part, we reimplement the regression (the exact implementation is out of the scope of this session):"
+    "The red line is fitted to the blue points and does not align well on the linear part.\n",
+    "\n",
+    "### Q\n",
+    "\n",
+    "To better illustrate that the central part is approximately linear, perform a linear regression with the observations whose corresponding theoretical quantiles (abscissa) fall in the $[-1,1]$ interval, and make a probability plot replacing the default regression line by your regression line."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "153d570e",
+   "metadata": {
+    "heading_collapsed": true,
+    "hidden": true
+   },
+   "source": [
+    "### A"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 35,
    "id": "0f888c53",
    "metadata": {
     "hidden": true
@@ -1177,30 +1286,63 @@
     }
    ],
    "source": [
-    "import statsmodels.api as sm # anticipating the next class...\n",
-    "central = (-1<theoretical_quantiles) & (theoretical_quantiles<1)\n",
-    "model = sm.OLS(observed_quantiles[central], sm.add_constant(theoretical_quantiles[central])).fit()\n",
-    "a, b = model.params\n",
+    "central_part = (-1<theoretical_quantiles) & (theoretical_quantiles<1)\n",
+    "b, a, _, _, _ = stats.linregress(theoretical_quantiles[central_part], observed_quantiles[central_part])\n",
     "plt.scatter(theoretical_quantiles, observed_quantiles, marker='+', color='b')\n",
     "plt.axline((0, a), slope=b, color='r');"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "f35584b7",
+   "id": "7981096d",
    "metadata": {
     "hidden": true
    },
    "source": [
     "The misalignment of the default regression line on the central part of the distribution is indicative of some asymmetry, while the diverging tails also hint at some departure from normality (kurtosis). The sampling procedure clearly excluded people younger than 20 years old or elder than 70, which results in truncated distributions.\n",
     "\n",
+    "We can seek confirmation with a normality test, although it is already clear the age is not normally distributed in our sample:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "ed0042b6",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "NormaltestResult(statistic=148.99086986471391, pvalue=4.436532649003701e-33)"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "stats.normaltest(house_owners_age)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f35584b7",
+   "metadata": {
+    "hidden": true
+   },
+   "source": [
     "Here, we have comfortable sample sizes and these departures from normality may not affect the power of the statistical test."
    ]
   },
   {
    "cell_type": "markdown",
    "id": "2cc80be1",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -1247,13 +1389,16 @@
     "hidden": true
    },
    "source": [
-    "`ttest_ind` allows standard deviation ratios [up to $2$](https://en.wikipedia.org/wiki/Student%27s_t-test#Equal_or_unequal_sample_sizes,_similar_variances_(1/2_%3C_sX1/sX2_%3C_2)). The groups can have different sample sizes."
+    "`ttest_ind` allows standard deviation ratios [up to $2$](https://en.wikipedia.org/wiki/Student%27s_t-test#Equal_or_unequal_sample_sizes,_similar_variances_(1/2_%3C_sX1/sX2_%3C_2)).\n",
+    "The groups can have different sample sizes."
    ]
   },
   {
    "cell_type": "markdown",
    "id": "d61f454a",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -1300,7 +1445,9 @@
   {
    "cell_type": "markdown",
    "id": "62b30b76",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -1319,7 +1466,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 14,
    "id": "341157b6",
    "metadata": {
     "hidden": true
@@ -1331,7 +1478,7 @@
        "(814, -10.305953282828284, -0.7954424784394866, -0.7954424784394866)"
       ]
      },
-     "execution_count": 54,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1371,7 +1518,9 @@
   {
    "cell_type": "markdown",
    "id": "f72698b7",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -1392,7 +1541,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8a2bc253",
+   "id": "6b7d5d56",
    "metadata": {
     "heading_collapsed": true
    },
@@ -1402,15 +1551,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
-   "id": "fd050fbc",
+   "execution_count": 15,
+   "id": "ee947953",
    "metadata": {
     "hidden": true
    },
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -1455,8 +1604,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "35541f89",
+   "execution_count": 16,
+   "id": "81e31c08",
    "metadata": {
     "hidden": true
    },
@@ -1471,7 +1620,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 17,
    "id": "2ae175e5",
    "metadata": {
     "hidden": true
@@ -1507,8 +1656,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
-   "id": "d9641fa6",
+   "execution_count": 18,
+   "id": "d15c23da",
    "metadata": {
     "hidden": true
    },
@@ -1556,49 +1705,49 @@
        "      <th>2</th>\n",
        "      <td>57</td>\n",
        "      <td>Student</td>\n",
-       "      <td>0.97</td>\n",
+       "      <td>1.00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>57</td>\n",
        "      <td>Welch</td>\n",
-       "      <td>0.97</td>\n",
+       "      <td>1.00</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>28</td>\n",
        "      <td>Student</td>\n",
-       "      <td>0.80</td>\n",
+       "      <td>0.76</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
        "      <td>28</td>\n",
        "      <td>Welch</td>\n",
-       "      <td>0.80</td>\n",
+       "      <td>0.76</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
        "      <td>14</td>\n",
        "      <td>Student</td>\n",
-       "      <td>0.55</td>\n",
+       "      <td>0.51</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7</th>\n",
        "      <td>14</td>\n",
        "      <td>Welch</td>\n",
-       "      <td>0.55</td>\n",
+       "      <td>0.51</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8</th>\n",
        "      <td>7</td>\n",
        "      <td>Student</td>\n",
-       "      <td>0.25</td>\n",
+       "      <td>0.29</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9</th>\n",
        "      <td>7</td>\n",
        "      <td>Welch</td>\n",
-       "      <td>0.23</td>\n",
+       "      <td>0.29</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -1608,17 +1757,17 @@
        "   sample size     test  power\n",
        "0          288  Student   1.00\n",
        "1          288    Welch   1.00\n",
-       "2           57  Student   0.97\n",
-       "3           57    Welch   0.97\n",
-       "4           28  Student   0.80\n",
-       "5           28    Welch   0.80\n",
-       "6           14  Student   0.55\n",
-       "7           14    Welch   0.55\n",
-       "8            7  Student   0.25\n",
-       "9            7    Welch   0.23"
+       "2           57  Student   1.00\n",
+       "3           57    Welch   1.00\n",
+       "4           28  Student   0.76\n",
+       "5           28    Welch   0.76\n",
+       "6           14  Student   0.51\n",
+       "7           14    Welch   0.51\n",
+       "8            7  Student   0.29\n",
+       "9            7    Welch   0.29"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1629,7 +1778,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f0ffbdab",
+   "id": "c4c702bc",
    "metadata": {
     "hidden": true
    },
@@ -1659,7 +1808,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 19,
    "id": "0aeaeee7",
    "metadata": {},
    "outputs": [
@@ -1684,7 +1833,9 @@
   {
    "cell_type": "markdown",
    "id": "02cbfb3c",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Q\n",
     "\n",
@@ -1703,7 +1854,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 20,
    "id": "e9c1cc3c",
    "metadata": {
     "hidden": true
@@ -1715,7 +1866,7 @@
        "(47.758187772925766, 44.85779329608938, 16.298908849529322, 9.611832029475966)"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1741,7 +1892,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 21,
    "id": "b6bfdb58",
    "metadata": {
     "hidden": true
@@ -1789,15 +1940,19 @@
   {
    "cell_type": "markdown",
    "id": "89181560",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
-    "## A"
+    "## A (with nested Q&A)"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "ef4093df",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "We need a two-sample goodness-of-fit test.\n",
     "\n",
@@ -1808,22 +1963,27 @@
     "\n",
     "### Q\n",
     "\n",
-    "Bin the two groups, extract frequencies and proceed to performing a $\\chi^2$ test."
+    "Bin the two groups, first with 5-year-wide bins, extract frequencies and proceed to performing a $\\chi^2$ test."
    ]
   },
   {
    "cell_type": "markdown",
    "id": "4338fe92",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true,
+    "hidden": true
+   },
    "source": [
     "### A"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 22,
    "id": "f57a8ff6",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -1832,7 +1992,7 @@
        " array([ 2, 12, 44, 67, 65, 53, 57, 34, 16,  8]))"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1847,16 +2007,20 @@
   {
    "cell_type": "markdown",
    "id": "980a9794",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "Let us check we did not miss any observation:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 23,
    "id": "de19e80b",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -1864,7 +2028,7 @@
        "816"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1876,44 +2040,98 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bbbc965c",
-   "metadata": {},
+   "id": "0150c1f5",
+   "metadata": {
+    "hidden": true
+   },
    "source": [
-    "Check there are at least 5 observations per combination of factor levels:"
+    "Note that we have less than 5 observations in one combination of factor levels. In principle we should revise the binning so that all bins contain at least 5 observations.\n",
+    "\n",
+    "For the purpose of comparing the impact of the binning, let us run the test anyway."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
-   "id": "32afe08a",
-   "metadata": {},
+   "execution_count": 24,
+   "id": "b021e03f",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "χ²(9) = 228.0, p-value = 4.33e-44\n"
+     ]
+    }
+   ],
+   "source": [
+    "chi2, pvalue, dof, _ = stats.chi2_contingency(np.stack((lives_with_kids_freqs, lives_without_kids_freqs), axis=0))\n",
+    "print(f'χ²({dof}) = {chi2:.1f}, p-value = {pvalue:.3g}')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "218a59ec",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## Q\n",
+    "\n",
+    "Are all the assumptions met? Adjust the procedure if necessary. Any interpretation?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "abdce59a",
+   "metadata": {
+    "heading_collapsed": true
+   },
+   "source": [
+    "## A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "3e64b5ce",
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "(array([22, 23, 26]), array([ 2,  8, 12]))"
+       "(array([107,  49,  52,  95, 155]), array([ 14, 111, 118,  91,  24]))"
       ]
      },
-     "execution_count": 52,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "np.sort(lives_without_kids_freqs)[:3], np.sort(lives_with_kids_freqs)[:3]"
+    "bins = np.arange(20, 70+1, 10)\n",
+    "lives_without_kids_freqs, _ = np.histogram(lives_without_kids, bins)\n",
+    "lives_with_kids_freqs, _ = np.histogram(lives_with_kids, bins)\n",
+    "lives_without_kids_freqs, lives_with_kids_freqs"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
-   "id": "b021e03f",
-   "metadata": {},
+   "execution_count": 26,
+   "id": "e79b98f2",
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "χ²(9) = 228.0, p-value = 4.33e-44\n"
+      "χ²(4) = 208.0, p-value = 7.32e-44\n"
      ]
     }
    ],
@@ -1924,28 +2142,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3b829782",
-   "metadata": {},
-   "source": [
-    "### Q\n",
-    "\n",
-    "Similarly, perform a two-sample Kolmogorov-Smirnov test."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8e66c8ce",
+   "id": "949edcfb",
    "metadata": {
-    "heading_collapsed": true
+    "hidden": true
    },
    "source": [
-    "### A"
+    "The low frequency in one group, in the first case, did not affect the outcome of the test because of the relatively large number of bins.\n",
+    "\n",
+    "Although there is no doubt we do have an effect here, we can also run a two-sample Kolmogorov-Smirnov test. It is good practice to seek confirmation with different but equivalent tests."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
-   "id": "3c694746",
+   "execution_count": 27,
+   "id": "7ea01f76",
    "metadata": {
     "hidden": true
    },
@@ -1956,7 +2166,7 @@
        "KstestResult(statistic=0.31230026103290964, pvalue=1.1102230246251565e-16)"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1967,17 +2177,21 @@
   },
   {
    "cell_type": "markdown",
-   "id": "901dca51",
-   "metadata": {},
+   "id": "982eafde",
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
-    "# Correlations"
+    "# ..."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "73b4a48d",
-   "metadata": {},
+   "id": "09247a33",
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": []
   }
diff --git a/notebooks/scipy_cours.ipynb b/notebooks/scipy_cours.ipynb
index f6cea83..1b23c75 100644
--- a/notebooks/scipy_cours.ipynb
+++ b/notebooks/scipy_cours.ipynb
@@ -1068,7 +1068,7 @@
   {
    "cell_type": "code",
    "execution_count": 153,
-   "id": "c58a021f",
+   "id": "b00250f8",
    "metadata": {
     "hidden": true
    },
@@ -1103,7 +1103,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "60f07aba",
+   "id": "2b311609",
    "metadata": {
     "hidden": true
    },
@@ -1116,7 +1116,7 @@
   {
    "cell_type": "code",
    "execution_count": 154,
-   "id": "0b70263b",
+   "id": "e60ba8f3",
    "metadata": {
     "hidden": true
    },
@@ -1187,20 +1187,20 @@
   },
   {
    "cell_type": "markdown",
-   "id": "77dfe22a",
+   "id": "e2b36e29",
    "metadata": {
     "hidden": true
    },
    "source": [
     "As they may differ, instead of reporting the sample mean alone, we can report a range of possible values for the population mean, and this is made possible by the fact the mean estimator is known to be normally distributed.\n",
     "\n",
-    "Note: a normal distribution with mean $\\mu$ and variation $\\sigma^2$ can be represented in `scipy` with the `norm` class that features that many distribution related measurements:"
+    "Note: a normal distribution with mean $\\mu$ and variance $\\sigma^2$ can be represented in `scipy` with the `norm` class whose methods implement many distribution-related measurements:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 145,
-   "id": "8f54f1c4",
+   "id": "7e3b5520",
    "metadata": {
     "hidden": true
    },
@@ -1214,7 +1214,7 @@
   {
    "cell_type": "code",
    "execution_count": 151,
-   "id": "8eef01b5",
+   "id": "d6bbb149",
    "metadata": {
     "hidden": true
    },
@@ -1238,7 +1238,7 @@
   {
    "cell_type": "code",
    "execution_count": 152,
-   "id": "d93bb006",
+   "id": "1341b01d",
    "metadata": {
     "hidden": true
    },
@@ -1261,7 +1261,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "128bee18",
+   "id": "2b05f3b3",
    "metadata": {
     "hidden": true
    },
@@ -1269,16 +1269,16 @@
     "For example, we may report an interval around the sample mean that should include the population mean with a $1-\\alpha=95\\%$ probability:\n",
     "\n",
     "$$\n",
-    "\\bar{x} \\pm u_{\\alpha/2}\\frac{\\sigma}{\\sqrt{n}}\n",
+    "\\bar{x} \\pm z_{1-\\alpha/2}\\frac{\\sigma}{\\sqrt{n}}\n",
     "$$\n",
     "\n",
-    "$u_{\\alpha/2}$ is calculated as follows:"
+    "$z_{1-\\alpha/2}$ is calculated as follows:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 139,
-   "id": "db08728d",
+   "execution_count": 197,
+   "id": "62f75d44",
    "metadata": {
     "hidden": true
    },
@@ -1289,7 +1289,7 @@
        "1.9599639845400545"
       ]
      },
-     "execution_count": 139,
+     "execution_count": 197,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1301,12 +1301,13 @@
   },
   {
    "cell_type": "markdown",
-   "id": "705c2e67",
+   "id": "7728089e",
    "metadata": {
     "hidden": true
    },
    "source": [
-    "For a $95\\%$ confidence interval, we usually take $u\\approx 1.96$.\n",
+    "For a $95\\%$ confidence interval, we usually take $z\\approx 1.96$.\n",
+    "[isf](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.rv_continuous.isf.html) is the inverse survival function, here of the standard normal distribution (with null mean and unit variance).\n",
     "\n",
     "$\\frac{\\sigma}{\\sqrt{n}}$ is the standard deviation of the sample mean and can be calculated using the `sem` function from `scipy.stats`."
    ]
@@ -1314,7 +1315,7 @@
   {
    "cell_type": "code",
    "execution_count": 155,
-   "id": "86912ddf",
+   "id": "a2a23163",
    "metadata": {
     "hidden": true
    },
@@ -1337,7 +1338,7 @@
   {
    "cell_type": "code",
    "execution_count": 156,
-   "id": "9b723a68",
+   "id": "99fe274d",
    "metadata": {
     "hidden": true
    },
@@ -3355,7 +3356,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6277cebb",
+   "id": "ca862d48",
    "metadata": {
     "heading_collapsed": true,
     "hidden": true
@@ -3366,7 +3367,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "dde0e024",
+   "id": "2b1a4872",
    "metadata": {
     "hidden": true
    },
@@ -3384,6 +3385,7 @@
    "cell_type": "markdown",
    "id": "141dc10b-c964-4621-9e53-32f36c11d2da",
    "metadata": {
+    "heading_collapsed": true,
     "tags": []
    },
    "source": [
@@ -3394,6 +3396,7 @@
    "cell_type": "markdown",
    "id": "6efe325b",
    "metadata": {
+    "hidden": true,
     "tags": []
    },
    "source": [
@@ -3412,6 +3415,8 @@
    "cell_type": "markdown",
    "id": "344da42e-5707-4a0a-9b98-4cbf47781fbe",
    "metadata": {
+    "heading_collapsed": true,
+    "hidden": true,
     "tags": []
    },
    "source": [
@@ -3422,6 +3427,7 @@
    "cell_type": "markdown",
    "id": "0c8b61ee-e2da-4dc4-b3ad-02790d407d5b",
    "metadata": {
+    "hidden": true,
     "jp-MarkdownHeadingCollapsed": true,
     "tags": []
    },
@@ -3442,7 +3448,9 @@
    "cell_type": "code",
    "execution_count": 48,
    "id": "f5a36568-d5b5-4388-b3f9-f38855c58c80",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -3466,7 +3474,9 @@
   {
    "cell_type": "markdown",
    "id": "a9fbd953",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "The correlation coefficient is a commonly-used effect size for the linear relationship between the two variables, similarly to (but not to be confused with) a regression coefficient:"
    ]
@@ -3475,7 +3485,9 @@
    "cell_type": "code",
    "execution_count": 49,
    "id": "3581eeb0-f98d-4b2f-a0f1-bef073d86980",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -3499,7 +3511,9 @@
    "cell_type": "code",
    "execution_count": 50,
    "id": "730a1bd8-51b6-4c06-9431-9a0fce53c42c",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -3523,7 +3537,9 @@
    "cell_type": "code",
    "execution_count": 51,
    "id": "bfd1c00e-20b3-48bd-9724-7342ae70f626",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -3546,7 +3562,9 @@
   {
    "cell_type": "markdown",
    "id": "53338c9a-9345-4ead-8487-1b51254d7330",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "Pearson $r$ assumes the observations are drawn from normal distributions.\n",
     "\n",
@@ -3555,17 +3573,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 175,
    "id": "39423438-a688-4afa-b258-e17076ba1fbd",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "(7.087239246711281e-05, 8.421503263379038e-05)"
+       "(0.018346666276950804, 0.009331832682953218)"
       ]
      },
-     "execution_count": 52,
+     "execution_count": 175,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -3575,6 +3595,10 @@
     "x1 = rng.integers(10, size=30)\n",
     "x2 = x1 + rng.integers(10, size=x1.size)\n",
     "\n",
+    "# plus a few noisy observations\n",
+    "x1 = np.r_[x1, 9, 12]\n",
+    "x2 = np.r_[x2, 1, 2]\n",
+    "\n",
     "pearson_r, pearson_pv = stats.pearsonr(x1, x2)\n",
     "spearman_r, spearman_pv = stats.spearmanr(x1, x2)\n",
     "\n",
@@ -3583,13 +3607,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": 176,
    "id": "bca6551e-9ffb-4f60-8b96-9a085b2e2282",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -3607,13 +3633,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 177,
    "id": "a2dee6dc-0f17-4b33-9431-c6dc2d2bd418",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -3632,7 +3660,9 @@
   {
    "cell_type": "markdown",
    "id": "18902dd3-022a-447a-9681-6713b2e9296e",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "What could possibly go wrong?\n",
     "\n",
@@ -3643,10 +3673,155 @@
     "On the other side, Spearman coefficient is based on ranks and may catch less intuitive patterns."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "37816425",
+   "metadata": {
+    "heading_collapsed": true,
+    "hidden": true
+   },
+   "source": [
+    "### Linear regression"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8abb81b1",
+   "metadata": {
+    "hidden": true
+   },
+   "source": [
+    "As previously said, the correlation is not directly related to the regression lines we constantly plot to illustrate the relationship a correlation coefficent is supposed to quantify.\n",
+    "\n",
+    "The linear regression also offers an approach for quantifying an association between two quantitative variables."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 180,
+   "id": "fb9d664f",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(5.43327239488117, 0.5804387568555759, 0.01834666627695083)"
+      ]
+     },
+     "execution_count": 180,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "slope, intercept, R, pvalue, slope_std_err = stats.linregress(x1, x2)\n",
+    "intercept, slope, pvalue"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8cfc5265",
+   "metadata": {
+    "hidden": true
+   },
+   "source": [
+    "The $p$-value returned by [linregress](https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.linregress.html) is related to $H_0$: the slope is $0$.\n",
+    "\n",
+    "If there is no slope, there is no association between the variables.\n",
+    "\n",
+    "A linear regression is also a model that can predict the value of one variable from the value of the other variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 182,
+   "id": "7f69b66e",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "8.335466179159049"
+      ]
+     },
+     "execution_count": 182,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x1_observed = 5\n",
+    "x2_predicted = intercept + slope * x1_observed\n",
+    "x2_predicted"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 185,
+   "id": "14836378",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "7.867716535433071"
+      ]
+     },
+     "execution_count": 185,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x2_observed = 10\n",
+    "x1_predicted = (x2_observed - intercept) / slope\n",
+    "x1_predicted"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 191,
+   "id": "51bff28b",
+   "metadata": {
+    "hidden": true
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "ax = sns.regplot(x=x1, y=x2)\n",
+    "x1_min, _ = ax.get_xlim()\n",
+    "x2_min, x2_max = ax.get_ylim()\n",
+    "ax.plot([x1_min, x1_observed, x1_observed], [x2_predicted, x2_predicted, x2_min], 'r:', linewidth=1)\n",
+    "ax.plot([x1_min, x1_predicted, x1_predicted], [x2_observed, x2_observed, x2_min], 'r:', linewidth=1)\n",
+    "ax.set_ylim([x2_min, x2_max])\n",
+    "ax.set_xlabel('x1')\n",
+    "ax.set_ylabel('x2');"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "9f26feda-d0fd-4d9d-a748-b0b82d0f84b4",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Effect sizes and test power"
    ]
@@ -3654,7 +3829,9 @@
   {
    "cell_type": "markdown",
    "id": "5d8555e2-f91e-4ed8-b518-d95b1f46aa11",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "`scipy.stats` does not offer any helper for effect size and power calculation.\n",
     "\n",
@@ -3666,6 +3843,7 @@
    "execution_count": 55,
    "id": "78c838fa-6eff-459a-867c-b9e930b0cebd",
    "metadata": {
+    "hidden": true,
     "jupyter": {
      "outputs_hidden": true
     },
@@ -3714,7 +3892,9 @@
    "cell_type": "code",
    "execution_count": 56,
    "id": "5eaf887e-9310-4b89-acca-ccde9dff5f02",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "from statsmodels.stats import power\n",
@@ -3725,7 +3905,8 @@
    "cell_type": "markdown",
    "id": "5532ddbe-202e-48f5-96fd-825c465a503f",
    "metadata": {
-    "heading_collapsed": true
+    "heading_collapsed": true,
+    "hidden": true
    },
    "source": [
     "### Effect sizes"
@@ -3788,7 +3969,10 @@
   {
    "cell_type": "markdown",
    "id": "3b30414c-6575-4dff-9637-664cb0f29a5a",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true,
+    "hidden": true
+   },
    "source": [
     "### Power analysis"
    ]
@@ -3796,7 +3980,9 @@
   {
    "cell_type": "markdown",
    "id": "9b54a050-85cc-44c3-b406-650734d0d2ec",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "Prior to collecting data, in the presence of preliminary data to roughly predict the expected effect size, one can estimate the sample size necessary for a test to detect such an effect.\n",
     "\n",
@@ -3817,7 +4003,9 @@
    "cell_type": "code",
    "execution_count": 169,
    "id": "de47ba11-f486-44e3-9f3b-9ddffacc95ee",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -3843,8 +4031,10 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "fdbaf062",
-   "metadata": {},
+   "id": "084b9635",
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": []
   }
-- 
GitLab