{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "df863c1d-0eee-4851-8c0a-39e39f7a50e6",
   "metadata": {},
   "source": [
    "(reglin-ml-notebook)=\n",
    "# Modello di Regressione Bivariato e ML"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7f3d677a-dcd5-4c0b-8a54-97c7943c5721",
   "metadata": {},
   "source": [
    "Il modello di regressione bivariato stimato con il metodo della massima verosimiglianza (ML) produce risultati sostanzialmente simili a quelli ottenuti con l'approccio bayesiano, a patto che si utilizzino prioris debolmente informativi. Solo in casi di modelli più complessi, come quelli gerarchici, i due approcci divergono significativamente.\n",
    "\n",
    "Per semplicità, in questo capitolo ci concentreremo sul modello di regressione bivariato stimato con il metodo ML."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "54b975a9-9d7d-4220-a798-1cf8315ac261",
   "metadata": {},
   "source": [
    "## Preparazione del Notebook"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "cf16f40f-f73b-4448-8ef2-da87eee8d1f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import scipy as sc\n",
    "import statistics as st\n",
    "import arviz as az\n",
    "import pingouin as pg\n",
    "import warnings\n",
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "5b9af9fd-566b-4020-a417-e42acb02908c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# set seed to make the results fully reproducible\n",
    "seed: int = sum(map(ord, \"regression_ml\"))\n",
    "rng: np.random.Generator = np.random.default_rng(seed=seed)\n",
    "\n",
    "az.style.use(\"arviz-darkgrid\")\n",
    "plt.rcParams[\"figure.dpi\"] = 100\n",
    "plt.rcParams[\"figure.facecolor\"] = \"white\"\n",
    "\n",
    "%config InlineBackend.figure_format = \"retina\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1c31f3e4-c42c-48fe-9942-2ba619e6052b",
   "metadata": {},
   "source": [
    "## Stima dei Coefficienti del Modello di Regressione"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bb739a78-7e19-48a8-bb90-9cb2149de33b",
   "metadata": {},
   "source": [
    "Consideriamo i dati forniti dal dataset `kidiq`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "af25600b-f94f-4653-8be3-b3e3968c446d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>kid_score</th>\n",
       "      <th>mom_hs</th>\n",
       "      <th>mom_iq</th>\n",
       "      <th>mom_work</th>\n",
       "      <th>mom_age</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>65</td>\n",
       "      <td>1.0</td>\n",
       "      <td>121.117529</td>\n",
       "      <td>4</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>98</td>\n",
       "      <td>1.0</td>\n",
       "      <td>89.361882</td>\n",
       "      <td>4</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>85</td>\n",
       "      <td>1.0</td>\n",
       "      <td>115.443165</td>\n",
       "      <td>4</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>83</td>\n",
       "      <td>1.0</td>\n",
       "      <td>99.449639</td>\n",
       "      <td>3</td>\n",
       "      <td>25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>115</td>\n",
       "      <td>1.0</td>\n",
       "      <td>92.745710</td>\n",
       "      <td>4</td>\n",
       "      <td>27</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   kid_score  mom_hs      mom_iq  mom_work  mom_age\n",
       "0         65     1.0  121.117529         4       27\n",
       "1         98     1.0   89.361882         4       25\n",
       "2         85     1.0  115.443165         4       27\n",
       "3         83     1.0   99.449639         3       25\n",
       "4        115     1.0   92.745710         4       27"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "kidiq = pd.read_stata(\"../data/kidiq.dta\")\n",
    "kidiq.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d2c0d7c8-09e4-4773-af68-bd8c5f79fcc5",
   "metadata": {},
   "source": [
    "Ci concentreremo sulla relazione lineare tra l'intelligenza del bambino e l'intelligenza della madre.\n",
    "\n",
    "Iniziamo rinominando le due variabili di interesse."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2d9c82fe-6db3-488d-bbad-aa8e7bfd33e4",
   "metadata": {},
   "outputs": [],
   "source": [
    "x = kidiq[\"mom_iq\"]\n",
    "y = kidiq[\"kid_score\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "14172169-05ea-456e-912d-1bae6437473e",
   "metadata": {},
   "source": [
    "Un diagramma a dispersione evidenzia un'associazione tra le due variabili in esame, che può essere ragionevolmente approssimata da una retta. Tuttavia, il grafico suggerisce anche che la relazione tra le variabili non sia particolarmente forte.\n",
    "\n",
    "In questo contesto, ci poniamo il duplice obiettivo di individuare la retta che meglio si adatta ai dati del diagramma e di quantificare la bontà di questo adattamento. In altre parole, vogliamo valutare quanto, in media, i punti del diagramma si discostano dalla retta individuata."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "0ddb5fbb-47d7-48a2-a470-d5efa32cc777",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x480 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 491,
       "width": 731
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(x, y, \"x\")\n",
    "plt.xlabel(\"Intelligenza della madre\")\n",
    "_ = plt.ylabel(\"Intelligenza del bambino\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "69f308c9-f235-4f8a-b175-9ae21ffd5f58",
   "metadata": {},
   "source": [
    "Calcoliamo i coefficienti del modello \n",
    "\n",
    "$$\n",
    "y_i = \\beta_0 + \\beta_1 x_i + e_i\n",
    "$$\n",
    "\n",
    "con il metodo della massima verosimiglianza. A questo scopo usiamo la funzione `linear_regression()` del pacchetto `pingouin`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "aaee27d5-d0be-4635-8697-ab6f981d1783",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>names</th>\n",
       "      <th>coef</th>\n",
       "      <th>se</th>\n",
       "      <th>T</th>\n",
       "      <th>pval</th>\n",
       "      <th>r2</th>\n",
       "      <th>adj_r2</th>\n",
       "      <th>CI[2.5%]</th>\n",
       "      <th>CI[97.5%]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Intercept</td>\n",
       "      <td>25.80</td>\n",
       "      <td>5.92</td>\n",
       "      <td>4.36</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.2</td>\n",
       "      <td>14.17</td>\n",
       "      <td>37.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>mom_iq</td>\n",
       "      <td>0.61</td>\n",
       "      <td>0.06</td>\n",
       "      <td>10.42</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.49</td>\n",
       "      <td>0.72</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       names   coef    se      T  pval   r2  adj_r2  CI[2.5%]  CI[97.5%]\n",
       "0  Intercept  25.80  5.92   4.36   0.0  0.2     0.2     14.17      37.43\n",
       "1     mom_iq   0.61  0.06  10.42   0.0  0.2     0.2      0.49       0.72"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lm = pg.linear_regression(x, y)\n",
    "lm.round(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "665d9543-f318-443e-8f96-4602ddde7193",
   "metadata": {},
   "source": [
    "Recuperiamo i coefficienti `b0` e `b1` dall'oggetto `lm` creato da `linear_regression()`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e59ed1d7-2c6b-4c7c-bfae-08a7c8175e7f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    25.799778\n",
       "1     0.609975\n",
       "Name: coef, dtype: float64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "beta = lm[\"coef\"]  # Coefficienti\n",
    "beta"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d82e9902-0084-4826-bb14-bd15a4f0b940",
   "metadata": {},
   "outputs": [],
   "source": [
    "b0 = beta[0]\n",
    "b1 = beta[1]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cbbaea41-ef8f-4ccc-aa40-9e5a8b0f218f",
   "metadata": {},
   "source": [
    "Calcoliamo i valori predetti dal modello di regressione:\n",
    "\n",
    "$$\n",
    "\\hat{y}_i = \\beta_0 + \\beta_1 x_i\n",
    "$$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "04b2f163-cb5c-439e-be39-a7caf771725e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0      99.678390\n",
       "1      80.308253\n",
       "2      96.217173\n",
       "3      86.461529\n",
       "4      82.372303\n",
       "         ...    \n",
       "429    77.572841\n",
       "430    82.521552\n",
       "431    83.661788\n",
       "432    84.879856\n",
       "433    81.461993\n",
       "Name: mom_iq, Length: 434, dtype: float64"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "yhat = b0 + b1 * x\n",
    "yhat"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a06b7772-9df4-43e6-913e-b6c21d7c0949",
   "metadata": {},
   "source": [
    "I modelli predetti $\\yhat$ corrispondono alla retta di regressione."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "efc0b95e-c6b6-4994-aa79-796682fb9f37",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x480 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 491,
       "width": 731
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(x, yhat)\n",
    "plt.xlabel(\"Intelligenza della madre\")\n",
    "plt.ylabel(\"Intelligenza predetta del bambino, $\\hat{y}$\")\n",
    "_ = plt.title(\"Retta di regressione\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c36d069e-e5a8-4e23-ba2b-b56edbb284b1",
   "metadata": {},
   "source": [
    "Aggiungiamo i dati osservati al grafico."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "1f3f568c-1ba7-46af-8660-a05cba11bcba",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 720x480 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 491,
       "width": 731
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(x, yhat)\n",
    "plt.plot(x, y, \"x\")\n",
    "plt.xlabel(\"Intelligenza della madre\")\n",
    "plt.ylabel(\"Intelligenza predetta del bambino, $\\hat{y}$\")\n",
    "_ = plt.title(\"Retta di regressione\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6f44a1ad-3de7-4530-a850-2bb3d09c508e",
   "metadata": {},
   "source": [
    "### Interpretazione\n",
    "\n",
    "Il coefficiente $\\beta_0$ indica il valore atteso della distribuzione condizionata $p(y_i \\mid x_i = 0)$. Nel caso presente, indica la media del quoziente d'intelligenza del bambino quando la madre ha un quoziente di intelligenza uguale a 0. Ovviamente questa non è un'informazione di una qualche importanza pratica. Vedremo come migliorare l'interpretabilità dell'intercetta usando una parametrizzazione alternativa dei dati.\n",
    "\n",
    "Il coefficiente $\\beta_1$ indica il cambiamento del valore atteso della variabile dipendente quando la variabile indipendente aumenta di un'unità. Nel caso presente abbiamo che il punteggio del quoziente di intelligenza del bambino aumenta in media di 0.61 punti quando il quoziente di intelligenza della madre aumenta di un punto. In una parametrizzazione alternativa, standardizzando la variabile indipendente, $\\beta_1$ indicherebbe di quanto varia in media il quoziente di intelligenza del bambino quando il quoziente di intelligenza della madre aumenta di una deviazione standard."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bc08a6f7-e13f-41c6-af96-54b5b956757e",
   "metadata": {},
   "source": [
    "## Residui"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7801610a-55de-4849-9d6e-9e82415f06d3",
   "metadata": {},
   "source": [
    "Calcoliamo i residui\n",
    "\n",
    "$$\n",
    "e_i = y_i - \\hat{y}_i\n",
    "$$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "00ca8233-fc5c-45fe-9793-8c0e5dfaa1db",
   "metadata": {},
   "outputs": [],
   "source": [
    "e = y - yhat"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1bb67ebe-58ff-4bea-9caa-ba8ef1887d65",
   "metadata": {},
   "source": [
    "La retta di regressine calcolata con il metodo della massima verosimiglianza ha le seguenti proprietà:\n",
    "\n",
    "- il valore atteso dei residui è zero,\n",
    "- i residui sono incorrelati con i valori predetti."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "35cacdcb-5972-45fd-b7d1-0c1edc85b137",
   "metadata": {},
   "source": [
    "Valutiamo la media dei residui:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "44a4e904-5e6a-49d7-9ee7-e696cd1aa6a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-1.5455123100404022e-14"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.mean(e)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f2c87468-711f-46a0-a35a-dc1a5cd2e0b2",
   "metadata": {},
   "source": [
    "Calcoliamo la correlazione tra i residui $e$ e i valori predetti $\\hat{y}$:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "f4459130-9eb0-4786-b428-e96c620e2bd3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1.6170164072555654e-16"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.corrcoef(e, yhat)[0, 1]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c09fce18-e330-4980-a9cb-a4db75df0c78",
   "metadata": {},
   "source": [
    "Il modello di regressione bivariato \n",
    "\n",
    "$$\n",
    "y_i = \\beta_0 + \\beta_1 x_i + e_i\n",
    "$$\n",
    "\n",
    "scompone la variabile dipendente $y_i$ in due componenti tra loro incorrelate, una componente deterministica\n",
    "\n",
    "$$\n",
    "\\hat{y}_i = \\beta_0 + \\beta_1 x_i \n",
    "$$\n",
    "\n",
    "e una componente aleatoria\n",
    "\n",
    "$$\n",
    "e_i = y_i - \\hat{y}_i.\n",
    "$$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "1abcebf1-87bc-4e49-b6f3-7c4b89c11617",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>yhat</th>\n",
       "      <th>e</th>\n",
       "      <th>sum</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>121.117529</td>\n",
       "      <td>65</td>\n",
       "      <td>99.678390</td>\n",
       "      <td>-34.678390</td>\n",
       "      <td>65.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>89.361882</td>\n",
       "      <td>98</td>\n",
       "      <td>80.308253</td>\n",
       "      <td>17.691747</td>\n",
       "      <td>98.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>115.443165</td>\n",
       "      <td>85</td>\n",
       "      <td>96.217173</td>\n",
       "      <td>-11.217173</td>\n",
       "      <td>85.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>99.449639</td>\n",
       "      <td>83</td>\n",
       "      <td>86.461529</td>\n",
       "      <td>-3.461529</td>\n",
       "      <td>83.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>92.745710</td>\n",
       "      <td>115</td>\n",
       "      <td>82.372303</td>\n",
       "      <td>32.627697</td>\n",
       "      <td>115.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>429</th>\n",
       "      <td>84.877412</td>\n",
       "      <td>94</td>\n",
       "      <td>77.572841</td>\n",
       "      <td>16.427159</td>\n",
       "      <td>94.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>430</th>\n",
       "      <td>92.990392</td>\n",
       "      <td>76</td>\n",
       "      <td>82.521552</td>\n",
       "      <td>-6.521552</td>\n",
       "      <td>76.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>431</th>\n",
       "      <td>94.859708</td>\n",
       "      <td>50</td>\n",
       "      <td>83.661788</td>\n",
       "      <td>-33.661788</td>\n",
       "      <td>50.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>432</th>\n",
       "      <td>96.856624</td>\n",
       "      <td>88</td>\n",
       "      <td>84.879856</td>\n",
       "      <td>3.120144</td>\n",
       "      <td>88.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>433</th>\n",
       "      <td>91.253336</td>\n",
       "      <td>70</td>\n",
       "      <td>81.461993</td>\n",
       "      <td>-11.461993</td>\n",
       "      <td>70.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>434 rows × 5 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "              x    y       yhat          e    sum\n",
       "0    121.117529   65  99.678390 -34.678390   65.0\n",
       "1     89.361882   98  80.308253  17.691747   98.0\n",
       "2    115.443165   85  96.217173 -11.217173   85.0\n",
       "3     99.449639   83  86.461529  -3.461529   83.0\n",
       "4     92.745710  115  82.372303  32.627697  115.0\n",
       "..          ...  ...        ...        ...    ...\n",
       "429   84.877412   94  77.572841  16.427159   94.0\n",
       "430   92.990392   76  82.521552  -6.521552   76.0\n",
       "431   94.859708   50  83.661788 -33.661788   50.0\n",
       "432   96.856624   88  84.879856   3.120144   88.0\n",
       "433   91.253336   70  81.461993 -11.461993   70.0\n",
       "\n",
       "[434 rows x 5 columns]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame()\n",
    "df[\"x\"] = x\n",
    "df[\"y\"] = y\n",
    "df[\"yhat\"] = yhat\n",
    "df[\"e\"] = e\n",
    "df[\"sum\"] = df[\"yhat\"] + df[\"e\"]\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1546346d-8cf3-47f2-921a-724b19ad77d1",
   "metadata": {},
   "source": [
    "## Errore Standard della Regressione\n",
    "\n",
    "L'errore standard della regressione rappresenta la stima della deviazione standard dei residui nell'intera popolazione. Questo parametro può essere calcolato attraverso la formula:\n",
    "\n",
    "$$\n",
    "\\hat{\\sigma}_e = \\sqrt{\\frac{\\sum_i (e_i - \\bar{e})^2}{n-2}},\n",
    "$$\n",
    "\n",
    "dove $ \\bar{e} $ indica la media dei residui, che teoricamente è zero dato che si assume che la media degli errori sia zero.\n",
    "\n",
    "Il denominatore \"n-2\" deriva dalla perdita di due gradi di libertà, necessaria per la stima dei due coefficienti, $ \\beta_0 $ (intercetta) e $ \\beta_1 $ (pendenza), che sono utilizzati per calcolare le stime previste $ \\hat{y}_i = \\beta_0 + \\beta_1 x_i $. Questi gradi di libertà vengono sottratti perché ciascun parametro stimato consuma un grado di libertà dal totale disponibile."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "833ae928-4a62-4ea7-befa-2687e017025d",
   "metadata": {},
   "source": [
    "Nel caso dell'esempio, la numerosità campionaria è"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "2e603385-0173-45fb-8836-6b29c97a0fcf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "434"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "n = len(x)\n",
    "n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b2bc78d3-0281-49c7-b341-1e89398009ab",
   "metadata": {},
   "source": [
    "L'errore standard della regressione diventa"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "ab4c7794-0d11-4798-9649-be68483c77a2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "18.266122792299274"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.sqrt(np.sum(e**2) / (n-2))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e356b88e-f239-4bbb-928b-08682fc7fb5f",
   "metadata": {},
   "source": [
    "Questo valore indica che, in media, nella popolazione la distanza tra i valori osservati e la retta di regressione è di 18.3 punti."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fda59109-a3eb-40ec-bb51-ff0ca95f3179",
   "metadata": {},
   "source": [
    "Come discusso da {cite}`gelman2020regression`, la radice quadrata media dei residui, $ \\frac{1}{n} \\sum_{i=1}^n (y_i - (\\hat{a} + \\hat{b}x_i))^2 $, tende a sottostimare la deviazione standard $\\sigma$ dell'errore nel modello di regressione. Questa sottostima è spesso il risultato di un sovradimensionamento, dato che i parametri $a$ e $b$ sono stimati utilizzando gli stessi $n$ punti dati usati anche per calcolare i residui.\n",
    "\n",
    "La validazione incrociata rappresenta un approccio alternativo per valutare l'errore predittivo che evita alcuni dei problemi legati al sovradimensionamento. La versione più semplice della validazione incrociata è l'approccio leave-one-out, in cui il modello è adattato $n$ volte, escludendo ogni volta un punto dati, adattando il modello ai rimanenti $n-1$ punti dati, e utilizzando questo modello adattato per predire l'osservazione esclusa:\n",
    "- Per $i = 1, \\ldots, n$:\n",
    "  - Adatta il modello $y = a + bx + \\text{errore}$ ai $n-1$ punti dati $(x,y)_j, j \\neq i$. Denomina i coefficienti di regressione stimati come $\\hat{a}_{-i}, \\hat{b}_{-i}$.\n",
    "  - Calcola il residuo validato incrociato, $ r_{\\text{CV}} = y_i - (\\hat{a}_{-i} + \\hat{b}_{-i} x_i) $.\n",
    "  - Calcola la stima di $\\sigma_{\\text{CV}} = \\frac{1}{n} \\sum_{i=1}^n r_{\\text{CV}}^2$.\n",
    "\n",
    "Per fare un esempio, eseguiamo i passaggi sopra descritti per il modello dell'intelligenza del bambino predetta dall'intelligenza della madre. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "709129b6-114f-427b-ac28-08d97d771f7f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Stima di σ_CV: 18.306662828465665\n"
     ]
    }
   ],
   "source": [
    "# Inizializzazione di un modello di regressione lineare\n",
    "model = LinearRegression()\n",
    "\n",
    "# Array per salvare i residui cross-validated\n",
    "residuals_cv = []\n",
    "\n",
    "# Loop per la validazione incrociata leave-one-out\n",
    "for i in range(len(df)):\n",
    "    # Dati di training escludendo l'i-esimo punto\n",
    "    X_train = df.loc[df.index != i, [\"x\"]]\n",
    "    y_train = df.loc[df.index != i, \"y\"]\n",
    "\n",
    "    # Dati di test\n",
    "    X_test = df.loc[[i], [\"x\"]]\n",
    "    y_test = df.loc[i, \"y\"]\n",
    "\n",
    "    # Addestramento del modello\n",
    "    model.fit(X_train, y_train)\n",
    "\n",
    "    # Predizione sull'i-esimo punto\n",
    "    y_pred = model.predict(X_test)\n",
    "\n",
    "    # Calcolo del residuo validato incrociato\n",
    "    residual_cv = y_test - y_pred[0]\n",
    "    residuals_cv.append(residual_cv**2)\n",
    "\n",
    "# Calcolo di sigma_cv\n",
    "sigma_cv = np.sqrt(np.mean(residuals_cv))\n",
    "\n",
    "print(\"Stima di σ_CV:\", sigma_cv)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b944c277-fd23-4d69-b4fb-299fea5af080",
   "metadata": {},
   "source": [
    "Nel caso dei dati analizzati, si osserva che la stima ottenuta attraverso la validazione incrociata è leggermente superiore rispetto a quella calcolata usando la formula \n",
    "$\n",
    "\\hat{\\sigma}_e = \\sqrt{\\frac{\\sum_i (e_i - \\bar{e})^2}{n-2}}\n",
    "$.\n",
    "Questo incremento, sebbene minimo, riflette le differenze metodologiche tra i due approcci di stima dell'errore standard."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e66b72ea-2723-4371-b862-61929c594233",
   "metadata": {},
   "source": [
    "## Parametrizzazione Alternativa\n",
    "\n",
    "Per consentire una migliore interpretazione dell'intercetta, centriamo i valori della variabile indipendente."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "6d8e85ec-50a9-443b-aded-6e9bef058a82",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "7.858537169696961e-16"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "xc = x - np.mean(x)\n",
    "np.mean(xc)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1b9200ba-2cb2-492f-865d-e143a65c067b",
   "metadata": {},
   "source": [
    "Eseguiamo l'analisi di regressione."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "728ae6b2-a7db-4714-bd87-a6559000f8ec",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>names</th>\n",
       "      <th>coef</th>\n",
       "      <th>se</th>\n",
       "      <th>T</th>\n",
       "      <th>pval</th>\n",
       "      <th>r2</th>\n",
       "      <th>adj_r2</th>\n",
       "      <th>CI[2.5%]</th>\n",
       "      <th>CI[97.5%]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Intercept</td>\n",
       "      <td>86.80</td>\n",
       "      <td>0.88</td>\n",
       "      <td>98.99</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.2</td>\n",
       "      <td>85.07</td>\n",
       "      <td>88.52</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>mom_iq</td>\n",
       "      <td>0.61</td>\n",
       "      <td>0.06</td>\n",
       "      <td>10.42</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.49</td>\n",
       "      <td>0.72</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       names   coef    se      T  pval   r2  adj_r2  CI[2.5%]  CI[97.5%]\n",
       "0  Intercept  86.80  0.88  98.99   0.0  0.2     0.2     85.07      88.52\n",
       "1     mom_iq   0.61  0.06  10.42   0.0  0.2     0.2      0.49       0.72"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lm2 = pg.linear_regression(xc, y)\n",
    "lm2.round(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9efdc073-d20f-494e-a08c-51ea28f5841a",
   "metadata": {},
   "source": [
    "Notiamo che la stima della pendenza della retta di regressione è rimasta immutata, mentre cambia il coefficiente $\\beta_0$. Nel caso in cui la variabile indipendente sia centrata, il coefficiente $\\beta_0$ rappresenta il valore atteso della variabile dipendente quando la variabile indipendente assume il suo valore medio.\n",
    "\n",
    "Nel caso presente, il valore 86.80 indica la media del quoziente di intelligenza del bambino quando il quoziente di intelligenza della madre assume il valore medio nel campione."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "55f27eac-fbe1-4216-80a8-024bc6af78cd",
   "metadata": {},
   "source": [
    "Adesso standardizziamo sia la variabile dipendente che la variabile indipendente."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "81850fff-3f0c-4314-82c3-23f66b10cce2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "4.9115857310606007e-17 0.9999999999999999\n"
     ]
    }
   ],
   "source": [
    "x_mean = np.mean(x)\n",
    "x_std = np.std(x, ddof=0)\n",
    "\n",
    "# Standardizzazione\n",
    "zx = (x - x_mean) / x_std\n",
    "\n",
    "print(np.mean(zx), np.std(zx))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "e62a6a6e-45d0-4470-8d39-338d5ea60b14",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_mean = np.mean(y)\n",
    "y_std = np.std(y, ddof=0)\n",
    "\n",
    "# Standardizzazione\n",
    "zy = (y - y_mean) / y_std"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "20b71daf-8570-41fd-8c0b-696349f150b2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>names</th>\n",
       "      <th>coef</th>\n",
       "      <th>se</th>\n",
       "      <th>T</th>\n",
       "      <th>pval</th>\n",
       "      <th>r2</th>\n",
       "      <th>adj_r2</th>\n",
       "      <th>CI[2.5%]</th>\n",
       "      <th>CI[97.5%]</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Intercept</td>\n",
       "      <td>-0.00</td>\n",
       "      <td>0.04</td>\n",
       "      <td>-0.00</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.2</td>\n",
       "      <td>-0.08</td>\n",
       "      <td>0.08</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>mom_iq</td>\n",
       "      <td>0.45</td>\n",
       "      <td>0.04</td>\n",
       "      <td>10.42</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.2</td>\n",
       "      <td>0.36</td>\n",
       "      <td>0.53</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       names  coef    se      T  pval   r2  adj_r2  CI[2.5%]  CI[97.5%]\n",
       "0  Intercept -0.00  0.04  -0.00   1.0  0.2     0.2     -0.08       0.08\n",
       "1     mom_iq  0.45  0.04  10.42   0.0  0.2     0.2      0.36       0.53"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "lm3 = pg.linear_regression(zx, zy)\n",
    "lm3.round(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "22bb3971-dd03-479d-809e-083246f8714b",
   "metadata": {},
   "source": [
    "Dopo aver standardizzato entrambe le variabili, i coefficienti di regressione possono essere interpretati nel seguente modo:\n",
    "\n",
    "- **$\\beta_0$ = 0**: Questo si verifica perché la retta di regressione, calcolata attraverso il metodo dei minimi quadrati (ML), interseca il punto delle medie delle variabili standardizzate, ovvero $(\\bar{X}, \\bar{Y})$.\n",
    "- **$\\beta_1$**: Rappresenta la variazione media della variabile dipendente, espressa in termini di deviazioni standard, per ogni aumento di una deviazione standard nella variabile indipendente."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5f36abbe-cd03-4090-9d8f-7476314b64d6",
   "metadata": {},
   "source": [
    "## Teorema della scomposizione della devianza\n",
    "\n",
    "Il teorema della scomposizione della devianza nel modello di regressione lineare ci aiuta a comprendere quanto bene il modello si adatta ai dati. Esso scompone la variazione totale dei dati in componenti attribuibili all'effetto del modello e alla variazione residua non spiegata dal modello. \n",
    "\n",
    "### Formulazione del Teorema\n",
    "\n",
    "Dato un set di dati $ y_1, y_2, \\dots, y_n $, dove $ y_i $ rappresenta l'i-esimo valore della variabile dipendente, e $ \\bar{y} $ è la media campionaria di $ y $, la devianza totale (o variazione totale) dei dati può essere scomposta nel seguente modo:\n",
    "\n",
    "1. **Devianza Totale (VT)**: Misura la dispersione totale dei dati intorno alla loro media.\n",
    "   $$\n",
    "   DT = \\sum_{i=1}^n (y_i - \\bar{y})^2\n",
    "   $$\n",
    "\n",
    "2. **Devianza Spiegata (VS)**: Misura quanto della variazione totale è spiegata dal modello di regressione.\n",
    "   $$\n",
    "   DS = \\sum_{i=1}^n (\\hat{y}_i - \\bar{y})^2\n",
    "   $$\n",
    "   dove $ \\hat{y}_i $ è il valore predetto dalla regressione per l'i-esimo osservazione.\n",
    "\n",
    "3. **Devianza Residua (VR)**: Misura la variazione dei dati che il modello non riesce a spiegare.\n",
    "   $$\n",
    "   DR = \\sum_{i=1}^n (y_i - \\hat{y}_i)^2\n",
    "   $$\n",
    "\n",
    "### Teorema di Scomposizione della Devianza\n",
    "\n",
    "Il teorema afferma che la variazione totale $ DT $ è uguale alla somma della variazione spiegata $ DS $ e della variazione residua $ DR $:\n",
    "\n",
    "$$\n",
    "DT = DS + DR\n",
    "$$\n",
    "\n",
    "### Dimostrazione\n",
    "\n",
    "La dimostrazione di questa identità si basa sul principio di ortogonalità dei residui e delle stime. I residui $ y_i - \\hat{y}_i $ sono ortogonali alle predizioni $ \\hat{y}_i - \\bar{y} $ nel contesto della regressione lineare. Matematicamente, ciò è espresso da:\n",
    "\n",
    "$$\n",
    "\\sum_{i=1}^n (\\hat{y}_i - \\bar{y})(y_i - \\hat{y}_i) = 0\n",
    "$$\n",
    "\n",
    "Utilizzando l'ortogonalità, possiamo scrivere la variazione totale come segue:\n",
    "\n",
    "$$\n",
    "\\begin{align*}\n",
    "DT &= \\sum_{i=1}^n (y_i - \\bar{y})^2 \\\\\n",
    "   &= \\sum_{i=1}^n [(y_i - \\hat{y}_i) + (\\hat{y}_i - \\bar{y})]^2 \\\\\n",
    "   &= \\sum_{i=1}^n (y_i - \\hat{y}_i)^2 + 2\\sum_{i=1}^n (y_i - \\hat{y}_i)(\\hat{y}_i - \\bar{y}) + \\sum_{i=1}^n (\\hat{y}_i - \\bar{y})^2 \\\\\n",
    "   &= DR + 2 \\cdot 0 + DS \\\\\n",
    "   &= DR + DS\n",
    "\\end{align*}\n",
    "$$\n",
    "\n",
    "Questa dimostrazione chiarisce che la variazione totale è esattamente uguale alla somma della devianza spiegata dal modello e quella non spiegata (residua). Il coefficiente di determinazione $ R^2 $, che è definito come $ R^2 = \\frac{DS}{DT} $, offre una misura della proporzione della variazione totale spiegata dal modello."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb8bda54-f377-4ac3-8dcf-accf30c6298f",
   "metadata": {},
   "source": [
    "Applichiamo ora il teorema di scomposizione della devianza ai dati in esame. Usando `pg.linear_regression(x, y)` calcoliamo il coefficiente di determinazione."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "5dfc91d3-4fb8-41f1-b52c-190f0ff6850e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.20095123075855126\n"
     ]
    }
   ],
   "source": [
    "r_squared = lm[\"r2\"][0] # R-squared del modello\n",
    "print(r_squared)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "82c44105-6b93-435a-9062-9e8d297ad097",
   "metadata": {},
   "source": [
    "Calcoliamo la devianza totale."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "e129b8d2-9011-4128-9ce0-f5250351390c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "180386.15668202768\n"
     ]
    }
   ],
   "source": [
    "DT = np.sum((y - np.mean(y))**2)\n",
    "print(DT)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49ba8d51-33b4-486d-8176-41250ff53888",
   "metadata": {},
   "source": [
    "Calcoliamo la devianza spiegata."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "8c171dac-6ec5-4cf2-93e4-87a7a7c54fea",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "36248.82019705826\n"
     ]
    }
   ],
   "source": [
    "DS = np.sum((yhat - np.mean(y)) ** 2)\n",
    "print(DS)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ede086a0-8766-4138-a4b4-692e2ccdbe2e",
   "metadata": {},
   "source": [
    "Calcoliamo la devianza residua."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "06776e1e-9d97-44c3-b71a-918337de389c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "144137.33648496936\n"
     ]
    }
   ],
   "source": [
    "DR = np.sum((y - yhat) ** 2)\n",
    "print(DR)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c9f9672e-2f15-493b-b77f-e6d42ffc9772",
   "metadata": {},
   "source": [
    "La devianza totale è la somma della devianza spiegata e della devianza residua."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "287c2a09-7e25-4290-8aca-4772fece8df2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "180386.15668202762"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "DS + DR"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "00b69089-8dff-49da-ba32-d1c157bc1186",
   "metadata": {},
   "source": [
    "Il coefficiente di determinazione è il rapporto tra la devianza spiegata e la devianza totale."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "11d4f4e9-1156-49a8-86fe-9834b91e86b7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.2009512307585509\n"
     ]
    }
   ],
   "source": [
    "Rsq = DS / DT\n",
    "print(Rsq)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aea9371d-dd21-4971-ac15-5fad19ef205d",
   "metadata": {},
   "source": [
    "## Inferenza\n",
    "\n",
    "Esistono due principali approcci di inferenza statistica applicabili ai modelli di regressione: l'inferenza frequentista e l'inferenza bayesiana.\n",
    "\n",
    "### Inferenza Frequentista\n",
    "L'inferenza frequentista stabilisce le sue basi analizzando la distribuzione campionaria delle stime dei coefficienti di regressione e calcolando l'errore standard associato. Questo metodo si focalizza prevalentemente sul test delle ipotesi e sulla costruzione degli intervalli di fiducia. Tuttavia, il test dell'ipotesi nulla è spesso criticato nel dibattito metodologico contemporaneo per la sua rigidezza e limitazioni interpretative. Analogamente, gli intervalli di fiducia possono risultare contro-intuitivi e di limitata utilità pratica, dato che richiedono un'interpretazione che non riflette direttamente la probabilità che il parametro si trovi all'interno dell'intervallo specificato.\n",
    "\n",
    "### Inferenza Bayesiana\n",
    "Contrariamente all'approccio frequentista, l'inferenza bayesiana offre un quadro più flessibile e intuitivo per l'analisi statistica. Attraverso l'utilizzo degli intervalli di credibilità, l'inferenza bayesiana permette di incorporare conoscenze pregresse e aggiornarle alla luce di nuovi dati. Gli intervalli di credibilità forniscono una stima diretta della probabilità che un parametro si trovi all'interno di un certo intervallo, basata sulla distribuzione a posteriori. Questo rende l'interpretazione più diretta e gli intervalli di credibilità risultano essere strumenti praticamente più utili nell'inferenza statistica.\n",
    "\n",
    "Per queste ragioni, molti ricercatori e analisti preferiscono sviluppare inferenze tramite l'approccio bayesiano, specialmente quando le situazioni richiedono una maggiore flessibilità interpretativa e l'integrazione di informazioni pregresse nel modello analitico."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d14e5107-b851-4db4-a9e8-ef65fc69e168",
   "metadata": {},
   "source": [
    "## Informazioni sull'Ambiente di Sviluppo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "0c20e39a-54e4-4b23-88c7-0287d6819150",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Last updated: Wed May 22 2024\n",
      "\n",
      "Python implementation: CPython\n",
      "Python version       : 3.12.3\n",
      "IPython version      : 8.24.0\n",
      "\n",
      "Compiler    : Clang 16.0.6 \n",
      "OS          : Darwin\n",
      "Release     : 23.4.0\n",
      "Machine     : arm64\n",
      "Processor   : arm\n",
      "CPU cores   : 8\n",
      "Architecture: 64bit\n",
      "\n",
      "scipy     : 1.13.0\n",
      "numpy     : 1.26.4\n",
      "seaborn   : 0.13.2\n",
      "pandas    : 2.2.2\n",
      "matplotlib: 3.8.4\n",
      "arviz     : 0.18.0\n",
      "pingouin  : 0.5.4\n",
      "\n",
      "Watermark: 2.4.3\n",
      "\n"
     ]
    }
   ],
   "source": [
    "%load_ext watermark\n",
    "%watermark -n -u -v -iv -w -m "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "pymc_env",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}