{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Aula 8 - Testes T, Anova e Post-Hoc"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Teste T para Amostras Dependentes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Teste de Hipótese\n",
    "Qual o impacto da concussão na memória visual?\n",
    "- H0: visual_memory_baseline - visual_memory_retest == 0\n",
    "- HA: visual_memory_baseline - visual_memory_retest != 0\n",
    "\n",
    "- assumir grau de significância alpha = 0.05\n",
    "- amostras são dependentes: as entradas correspondem a antes e depois de uma mesma amostra"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importar bibliotecas\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pingouin\n",
    "import seaborn as sns\n",
    "from scipy.stats import t, levene"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importar base de dados impact\n",
    "impact = pd.read_csv('../data/impact.csv')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 40 entries, 0 to 39\n",
      "Data columns (total 14 columns):\n",
      " #   Column                       Non-Null Count  Dtype  \n",
      "---  ------                       --------------  -----  \n",
      " 0   subject                      40 non-null     int64  \n",
      " 1   condition                    40 non-null     object \n",
      " 2   verbal_memory_baseline       40 non-null     int64  \n",
      " 3   visual_memory_baseline       40 non-null     int64  \n",
      " 4   visual-motor_speed_baseline  40 non-null     float64\n",
      " 5   reaction_time_baseline       40 non-null     float64\n",
      " 6   impulse_control_baseline     40 non-null     int64  \n",
      " 7   total_symptom_baseline       40 non-null     int64  \n",
      " 8   verbal_memory_retest         40 non-null     int64  \n",
      " 9   visual_memory_retest         40 non-null     int64  \n",
      " 10  visual-motor_speed_retest    40 non-null     float64\n",
      " 11  reaction_time_retest         40 non-null     float64\n",
      " 12  impulse_control_retest       40 non-null     int64  \n",
      " 13  total_symptom_retest         40 non-null     int64  \n",
      "dtypes: float64(4), int64(9), object(1)\n",
      "memory usage: 4.5+ KB\n"
     ]
    }
   ],
   "source": [
    "# Informações gerais da base\n",
    "impact.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "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>subject</th>\n",
       "      <th>condition</th>\n",
       "      <th>verbal_memory_baseline</th>\n",
       "      <th>visual_memory_baseline</th>\n",
       "      <th>visual-motor_speed_baseline</th>\n",
       "      <th>reaction_time_baseline</th>\n",
       "      <th>impulse_control_baseline</th>\n",
       "      <th>total_symptom_baseline</th>\n",
       "      <th>verbal_memory_retest</th>\n",
       "      <th>visual_memory_retest</th>\n",
       "      <th>visual-motor_speed_retest</th>\n",
       "      <th>reaction_time_retest</th>\n",
       "      <th>impulse_control_retest</th>\n",
       "      <th>total_symptom_retest</th>\n",
       "      <th>vbm_diff</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9</td>\n",
       "      <td>control</td>\n",
       "      <td>93</td>\n",
       "      <td>85</td>\n",
       "      <td>39.59</td>\n",
       "      <td>0.68</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>91</td>\n",
       "      <td>83</td>\n",
       "      <td>37.42</td>\n",
       "      <td>0.65</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>13</td>\n",
       "      <td>control</td>\n",
       "      <td>79</td>\n",
       "      <td>60</td>\n",
       "      <td>40.39</td>\n",
       "      <td>0.82</td>\n",
       "      <td>12</td>\n",
       "      <td>0</td>\n",
       "      <td>84</td>\n",
       "      <td>67</td>\n",
       "      <td>43.70</td>\n",
       "      <td>0.57</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>-5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>14</td>\n",
       "      <td>control</td>\n",
       "      <td>86</td>\n",
       "      <td>59</td>\n",
       "      <td>32.88</td>\n",
       "      <td>0.59</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>81</td>\n",
       "      <td>71</td>\n",
       "      <td>32.40</td>\n",
       "      <td>0.69</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>30</td>\n",
       "      <td>concussed</td>\n",
       "      <td>97</td>\n",
       "      <td>73</td>\n",
       "      <td>28.89</td>\n",
       "      <td>0.71</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>90</td>\n",
       "      <td>73</td>\n",
       "      <td>25.70</td>\n",
       "      <td>0.73</td>\n",
       "      <td>3</td>\n",
       "      <td>25</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>38</td>\n",
       "      <td>concussed</td>\n",
       "      <td>95</td>\n",
       "      <td>63</td>\n",
       "      <td>35.06</td>\n",
       "      <td>0.84</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>62</td>\n",
       "      <td>54</td>\n",
       "      <td>35.09</td>\n",
       "      <td>1.24</td>\n",
       "      <td>2</td>\n",
       "      <td>15</td>\n",
       "      <td>33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>32</th>\n",
       "      <td>33</td>\n",
       "      <td>concussed</td>\n",
       "      <td>84</td>\n",
       "      <td>81</td>\n",
       "      <td>34.46</td>\n",
       "      <td>0.48</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>72</td>\n",
       "      <td>79</td>\n",
       "      <td>37.46</td>\n",
       "      <td>0.56</td>\n",
       "      <td>1</td>\n",
       "      <td>14</td>\n",
       "      <td>12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>36</th>\n",
       "      <td>37</td>\n",
       "      <td>concussed</td>\n",
       "      <td>97</td>\n",
       "      <td>70</td>\n",
       "      <td>39.01</td>\n",
       "      <td>0.60</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>74</td>\n",
       "      <td>62</td>\n",
       "      <td>39.66</td>\n",
       "      <td>0.74</td>\n",
       "      <td>5</td>\n",
       "      <td>27</td>\n",
       "      <td>23</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>27</td>\n",
       "      <td>concussed</td>\n",
       "      <td>84</td>\n",
       "      <td>78</td>\n",
       "      <td>34.26</td>\n",
       "      <td>0.54</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>80</td>\n",
       "      <td>74</td>\n",
       "      <td>49.62</td>\n",
       "      <td>0.64</td>\n",
       "      <td>7</td>\n",
       "      <td>43</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>control</td>\n",
       "      <td>84</td>\n",
       "      <td>72</td>\n",
       "      <td>41.87</td>\n",
       "      <td>0.66</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>85</td>\n",
       "      <td>70</td>\n",
       "      <td>33.26</td>\n",
       "      <td>0.19</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>-1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>28</td>\n",
       "      <td>concussed</td>\n",
       "      <td>93</td>\n",
       "      <td>74</td>\n",
       "      <td>36.08</td>\n",
       "      <td>0.65</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>59</td>\n",
       "      <td>69</td>\n",
       "      <td>35.68</td>\n",
       "      <td>0.70</td>\n",
       "      <td>11</td>\n",
       "      <td>31</td>\n",
       "      <td>34</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    subject  condition  verbal_memory_baseline  visual_memory_baseline  \\\n",
       "8         9    control                      93                      85   \n",
       "12       13    control                      79                      60   \n",
       "13       14    control                      86                      59   \n",
       "29       30  concussed                      97                      73   \n",
       "37       38  concussed                      95                      63   \n",
       "32       33  concussed                      84                      81   \n",
       "36       37  concussed                      97                      70   \n",
       "26       27  concussed                      84                      78   \n",
       "3         4    control                      84                      72   \n",
       "27       28  concussed                      93                      74   \n",
       "\n",
       "    visual-motor_speed_baseline  reaction_time_baseline  \\\n",
       "8                         39.59                    0.68   \n",
       "12                        40.39                    0.82   \n",
       "13                        32.88                    0.59   \n",
       "29                        28.89                    0.71   \n",
       "37                        35.06                    0.84   \n",
       "32                        34.46                    0.48   \n",
       "36                        39.01                    0.60   \n",
       "26                        34.26                    0.54   \n",
       "3                         41.87                    0.66   \n",
       "27                        36.08                    0.65   \n",
       "\n",
       "    impulse_control_baseline  total_symptom_baseline  verbal_memory_retest  \\\n",
       "8                          7                       0                    91   \n",
       "12                        12                       0                    84   \n",
       "13                         2                       0                    81   \n",
       "29                         7                       0                    90   \n",
       "37                         5                       0                    62   \n",
       "32                         7                       0                    72   \n",
       "36                        10                       0                    74   \n",
       "26                         6                       0                    80   \n",
       "3                          7                       0                    85   \n",
       "27                        10                       0                    59   \n",
       "\n",
       "    visual_memory_retest  visual-motor_speed_retest  reaction_time_retest  \\\n",
       "8                     83                      37.42                  0.65   \n",
       "12                    67                      43.70                  0.57   \n",
       "13                    71                      32.40                  0.69   \n",
       "29                    73                      25.70                  0.73   \n",
       "37                    54                      35.09                  1.24   \n",
       "32                    79                      37.46                  0.56   \n",
       "36                    62                      39.66                  0.74   \n",
       "26                    74                      49.62                  0.64   \n",
       "3                     70                      33.26                  0.19   \n",
       "27                    69                      35.68                  0.70   \n",
       "\n",
       "    impulse_control_retest  total_symptom_retest  vbm_diff  \n",
       "8                        8                     0         2  \n",
       "12                      10                     0        -5  \n",
       "13                       3                     0         5  \n",
       "29                       3                    25         7  \n",
       "37                       2                    15        33  \n",
       "32                       1                    14        12  \n",
       "36                       5                    27        23  \n",
       "26                       7                    43         4  \n",
       "3                        8                     0        -1  \n",
       "27                      11                    31        34  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Amostra aleatória de 10 entradas\n",
    "impact.sample(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Faremos o teste-t dependentes para a métrica de Memória visual, verificando se há diferença entre o controle e as pessoas com concussão na situação de reteste.\n",
    "\n",
    "Verifique a aderência dos dados à distribuição normal\n",
    "- apresente o histograma (com a linha de distribuição normal), o valor p < W e a análise para cada grupo: controle e concussão. O procedimento procedimento pode ser visto [aqui:]('https://youtu.be/dOWZkghcTkM')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Teste-t para amostras dependentes, métrica de Memória visual, verificando se há diferença entre o controle e as pessoas com concussão na situação de reteste.\n",
    "impact['vbm_diff'] = impact['visual_memory_baseline'] - impact['visual_memory_retest']\n",
    "sns.set_theme(style='darkgrid')\n",
    "sns.histplot(data=impact, x='vbm_diff', kde=True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "impact['vbm_diff'] = impact['visual_memory_baseline'] - impact['visual_memory_retest']\n",
    "sns.set_theme(style='darkgrid')\n",
    "sns.histplot(data=impact, x='vbm_diff', hue='condition',kde=True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Faça o Teste-t para a métrica 'visual_memory_retest' - apresente a análise e responda:\n",
    "- Qual a difença média?\n",
    "- Qual o valor t e o que isso significa?\n",
    "- Qual a significância do resultado (p-value) e o que isso significa?\n",
    "- Qual o intervalo de confiança da diferença média? \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.975\n"
     ]
    }
   ],
   "source": [
    "# Cálculo da média das diferenças\n",
    "xbar_diff = impact['vbm_diff'].mean()\n",
    "print(xbar_diff)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "n_diff:  40\n",
      "s_diff:  4.82773769814095\n",
      "degrees_of_freedom:  39\n",
      "p_value:  0.9974959655708271\n"
     ]
    }
   ],
   "source": [
    "# valor de n (tamanho da amostra)\n",
    "n_diff = len(impact)\n",
    "print('n_diff: ', n_diff)\n",
    "\n",
    "\n",
    "# desvio padrão da diferença (antes e depois)\n",
    "s_diff = impact['vbm_diff'].std()\n",
    "print('s_diff: ', s_diff)\n",
    "\n",
    "# t student\n",
    "t_stat = (xbar_diff-0 / np.sqrt(s_diff**2/n_diff))\n",
    "\n",
    "# graus de liberdade\n",
    "degrees_of_freedom = n_diff - 1\n",
    "print('degrees_of_freedom: ', degrees_of_freedom)\n",
    "\n",
    "# valor de p\n",
    "p_value = t.cdf(t_stat, df=n_diff-1)\n",
    "print('p_value: ', p_value)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "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>T</th>\n",
       "      <th>dof</th>\n",
       "      <th>alternative</th>\n",
       "      <th>p-val</th>\n",
       "      <th>CI95%</th>\n",
       "      <th>cohen-d</th>\n",
       "      <th>BF10</th>\n",
       "      <th>power</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>T-test</th>\n",
       "      <td>3.897385</td>\n",
       "      <td>39</td>\n",
       "      <td>greater</td>\n",
       "      <td>0.000186</td>\n",
       "      <td>[1.69, inf]</td>\n",
       "      <td>0.616231</td>\n",
       "      <td>148.131</td>\n",
       "      <td>0.985507</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               T  dof alternative     p-val        CI95%   cohen-d     BF10  \\\n",
       "T-test  3.897385   39     greater  0.000186  [1.69, inf]  0.616231  148.131   \n",
       "\n",
       "           power  \n",
       "T-test  0.985507  "
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Testar diferenças entre as médias usando teste t\n",
    "pingouin.ttest(x=impact['vbm_diff'], y=0, alternative='greater')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "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>T</th>\n",
       "      <th>dof</th>\n",
       "      <th>alternative</th>\n",
       "      <th>p-val</th>\n",
       "      <th>CI95%</th>\n",
       "      <th>cohen-d</th>\n",
       "      <th>BF10</th>\n",
       "      <th>power</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>T-test</th>\n",
       "      <td>4.184333</td>\n",
       "      <td>39</td>\n",
       "      <td>greater</td>\n",
       "      <td>0.000079</td>\n",
       "      <td>[4.63, inf]</td>\n",
       "      <td>0.858432</td>\n",
       "      <td>322.412</td>\n",
       "      <td>0.999887</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               T  dof alternative     p-val        CI95%   cohen-d     BF10  \\\n",
       "T-test  4.184333   39     greater  0.000079  [4.63, inf]  0.858432  322.412   \n",
       "\n",
       "           power  \n",
       "T-test  0.999887  "
      ]
     },
     "execution_count": 65,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Testar diferenças com amostras dependentes (paired=True)\n",
    "pingouin.ttest(x=impact['verbal_memory_baseline'], y=impact['verbal_memory_retest'], paired=True, alternative='greater')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "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>T</th>\n",
       "      <th>dof</th>\n",
       "      <th>alternative</th>\n",
       "      <th>p-val</th>\n",
       "      <th>CI95%</th>\n",
       "      <th>cohen-d</th>\n",
       "      <th>BF10</th>\n",
       "      <th>power</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>T-test</th>\n",
       "      <td>3.839024</td>\n",
       "      <td>78</td>\n",
       "      <td>greater</td>\n",
       "      <td>0.000125</td>\n",
       "      <td>[4.39, inf]</td>\n",
       "      <td>0.858432</td>\n",
       "      <td>199.918</td>\n",
       "      <td>0.984636</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               T  dof alternative     p-val        CI95%   cohen-d     BF10  \\\n",
       "T-test  3.839024   78     greater  0.000125  [4.39, inf]  0.858432  199.918   \n",
       "\n",
       "           power  \n",
       "T-test  0.984636  "
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Testar diferenças com amostras independentes\n",
    "pingouin.ttest(x=impact['verbal_memory_baseline'], y=impact['verbal_memory_retest'], paired=False, alternative='greater')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "control      20\n",
       "concussed    20\n",
       "Name: condition, dtype: int64"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Verificar numero de entradas nas condições control e concussed,\n",
    "impact['condition'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "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>count</th>\n",
       "      <th>mean</th>\n",
       "      <th>std</th>\n",
       "      <th>min</th>\n",
       "      <th>25%</th>\n",
       "      <th>50%</th>\n",
       "      <th>75%</th>\n",
       "      <th>max</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>condition</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>concussed</th>\n",
       "      <td>20.0</td>\n",
       "      <td>69.2</td>\n",
       "      <td>8.376659</td>\n",
       "      <td>54.0</td>\n",
       "      <td>62.75</td>\n",
       "      <td>69.5</td>\n",
       "      <td>76.0</td>\n",
       "      <td>80.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>control</th>\n",
       "      <td>20.0</td>\n",
       "      <td>74.6</td>\n",
       "      <td>7.755473</td>\n",
       "      <td>60.0</td>\n",
       "      <td>69.50</td>\n",
       "      <td>74.5</td>\n",
       "      <td>80.0</td>\n",
       "      <td>86.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           count  mean       std   min    25%   50%   75%   max\n",
       "condition                                                      \n",
       "concussed   20.0  69.2  8.376659  54.0  62.75  69.5  76.0  80.0\n",
       "control     20.0  74.6  7.755473  60.0  69.50  74.5  80.0  86.0"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Visualizar estatísticas de sumário por grupo\n",
    "impact.groupby('condition')['visual_memory_retest'].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualizar distribuições nas duas condições\n",
    "sns.boxplot(x='verbal_memory_retest', y='condition', data=impact)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Teste de homoscedasticidade (homogeneidade da variância) (Levene). Qual o F ratio (W) e o p-value? Qual o significado?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "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>W</th>\n",
       "      <th>pval</th>\n",
       "      <th>equal_var</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>levene</th>\n",
       "      <td>0.052246</td>\n",
       "      <td>0.820426</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               W      pval  equal_var\n",
       "levene  0.052246  0.820426       True"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pingouin.homoscedasticity(data=impact, dv='visual_memory_retest', group='condition', method='levene', alpha=0.05)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Não há violação da homogeneidade (teste não significativo)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Testes T independentes\n",
    "\n",
    "Utilizaremos os dados 'Atividade 07 - IQ - Threat + working memory'. Utilize a aba \"sheet 2\" que possui duas condições de ameaça de estereótipo.\n",
    "Faremos testes-t independentes para a métrica de QI, verificando se há diferença entre o controle e as duas condições de ameaça de estereótipo."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "iqthreats = pd.read_excel('../data/iq_threats.xlsx')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 150 entries, 0 to 149\n",
      "Data columns (total 7 columns):\n",
      " #   Column       Non-Null Count  Dtype  \n",
      "---  ------       --------------  -----  \n",
      " 0   subject      150 non-null    int64  \n",
      " 1   condition    150 non-null    object \n",
      " 2   IQ           150 non-null    int64  \n",
      " 3   WM           150 non-null    int64  \n",
      " 4   WM.centered  150 non-null    float64\n",
      " 5   D1           150 non-null    int64  \n",
      " 6   D2           150 non-null    int64  \n",
      "dtypes: float64(1), int64(5), object(1)\n",
      "memory usage: 8.3+ KB\n"
     ]
    }
   ],
   "source": [
    "iqthreats.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "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>subject</th>\n",
       "      <th>condition</th>\n",
       "      <th>IQ</th>\n",
       "      <th>WM</th>\n",
       "      <th>WM.centered</th>\n",
       "      <th>D1</th>\n",
       "      <th>D2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>92</th>\n",
       "      <td>93</td>\n",
       "      <td>threat1</td>\n",
       "      <td>68</td>\n",
       "      <td>108</td>\n",
       "      <td>8.92</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>25</td>\n",
       "      <td>control</td>\n",
       "      <td>46</td>\n",
       "      <td>90</td>\n",
       "      <td>-9.08</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>86</th>\n",
       "      <td>87</td>\n",
       "      <td>threat1</td>\n",
       "      <td>55</td>\n",
       "      <td>111</td>\n",
       "      <td>11.92</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7</td>\n",
       "      <td>control</td>\n",
       "      <td>100</td>\n",
       "      <td>99</td>\n",
       "      <td>-0.08</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20</td>\n",
       "      <td>control</td>\n",
       "      <td>106</td>\n",
       "      <td>71</td>\n",
       "      <td>-28.08</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72</th>\n",
       "      <td>73</td>\n",
       "      <td>threat1</td>\n",
       "      <td>37</td>\n",
       "      <td>92</td>\n",
       "      <td>-7.08</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>141</th>\n",
       "      <td>142</td>\n",
       "      <td>threat2</td>\n",
       "      <td>30</td>\n",
       "      <td>103</td>\n",
       "      <td>3.92</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>150</td>\n",
       "      <td>threat2</td>\n",
       "      <td>61</td>\n",
       "      <td>85</td>\n",
       "      <td>-14.08</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>101</th>\n",
       "      <td>102</td>\n",
       "      <td>threat2</td>\n",
       "      <td>59</td>\n",
       "      <td>86</td>\n",
       "      <td>-13.08</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>69</td>\n",
       "      <td>threat1</td>\n",
       "      <td>41</td>\n",
       "      <td>95</td>\n",
       "      <td>-4.08</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     subject condition   IQ   WM  WM.centered  D1  D2\n",
       "92        93   threat1   68  108         8.92   1   0\n",
       "24        25   control   46   90        -9.08   0   0\n",
       "86        87   threat1   55  111        11.92   1   0\n",
       "6          7   control  100   99        -0.08   0   0\n",
       "19        20   control  106   71       -28.08   0   0\n",
       "72        73   threat1   37   92        -7.08   1   0\n",
       "141      142   threat2   30  103         3.92   0   1\n",
       "149      150   threat2   61   85       -14.08   0   1\n",
       "101      102   threat2   59   86       -13.08   0   1\n",
       "68        69   threat1   41   95        -4.08   1   0"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iqthreats.sample(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "2.1 Verifique a aderência dos dados à distribuição normal - apresente o histograma (com a linha de distribuição normal), o valor p < W e a análise para cada um dos três grupos. Dica - peça o histograma de toda a coluna e utilize o 'local data filter'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.histplot(data=iqthreats, x='IQ', hue='condition', kde=True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Faça o Teste-t para a métrica 'QI' - apresente a análise e responda:\n",
    "- Quais grupos possuem diferença significativa? \n",
    "- Qual o valor-t e valor-p do para controle e ameaça 1? Qual o intervalo de Confiança?\n",
    "- Qual o valor-t e valor-p do para controle e ameaça 2? Qual o intervalo de Confiança?\n",
    "- Qual o valor-t e valor-p do para ameaça 1e ameaça 2? Qual o intervalo de Confiança?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "controle = iqthreats[iqthreats['condition'] == 'control']\n",
    "ameaca1 = iqthreats[iqthreats['condition'] == 'threat1']\n",
    "ameaca2 = iqthreats[iqthreats['condition'] == 'threat2']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "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>T</th>\n",
       "      <th>dof</th>\n",
       "      <th>alternative</th>\n",
       "      <th>p-val</th>\n",
       "      <th>CI95%</th>\n",
       "      <th>cohen-d</th>\n",
       "      <th>BF10</th>\n",
       "      <th>power</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>T-test</th>\n",
       "      <td>12.894779</td>\n",
       "      <td>98</td>\n",
       "      <td>greater</td>\n",
       "      <td>3.904659e-23</td>\n",
       "      <td>[39.83, inf]</td>\n",
       "      <td>2.578956</td>\n",
       "      <td>6.848e+19</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                T  dof alternative         p-val         CI95%   cohen-d  \\\n",
       "T-test  12.894779   98     greater  3.904659e-23  [39.83, inf]  2.578956   \n",
       "\n",
       "             BF10  power  \n",
       "T-test  6.848e+19    1.0  "
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Testar diferenças para controle e ameaça 1\n",
    "pingouin.ttest(x=controle['IQ'], y=ameaca1['IQ'], paired=False, alternative='greater')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "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>T</th>\n",
       "      <th>dof</th>\n",
       "      <th>alternative</th>\n",
       "      <th>p-val</th>\n",
       "      <th>CI95%</th>\n",
       "      <th>cohen-d</th>\n",
       "      <th>BF10</th>\n",
       "      <th>power</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>T-test</th>\n",
       "      <td>14.475241</td>\n",
       "      <td>98</td>\n",
       "      <td>greater</td>\n",
       "      <td>2.233117e-26</td>\n",
       "      <td>[44.14, inf]</td>\n",
       "      <td>2.895048</td>\n",
       "      <td>9.982e+22</td>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                T  dof alternative         p-val         CI95%   cohen-d  \\\n",
       "T-test  14.475241   98     greater  2.233117e-26  [44.14, inf]  2.895048   \n",
       "\n",
       "             BF10  power  \n",
       "T-test  9.982e+22    1.0  "
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Testar diferenças para controle e ameaça 2\n",
    "pingouin.ttest(x=controle['IQ'], y=ameaca2['IQ'], paired=False, alternative='greater')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "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>T</th>\n",
       "      <th>dof</th>\n",
       "      <th>alternative</th>\n",
       "      <th>p-val</th>\n",
       "      <th>CI95%</th>\n",
       "      <th>cohen-d</th>\n",
       "      <th>BF10</th>\n",
       "      <th>power</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>T-test</th>\n",
       "      <td>1.575479</td>\n",
       "      <td>98</td>\n",
       "      <td>greater</td>\n",
       "      <td>0.059184</td>\n",
       "      <td>[-0.22, inf]</td>\n",
       "      <td>0.315096</td>\n",
       "      <td>1.263</td>\n",
       "      <td>0.468015</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               T  dof alternative     p-val         CI95%   cohen-d   BF10  \\\n",
       "T-test  1.575479   98     greater  0.059184  [-0.22, inf]  0.315096  1.263   \n",
       "\n",
       "           power  \n",
       "T-test  0.468015  "
      ]
     },
     "execution_count": 81,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Testar diferenças para ameaça 1 e ameaça 2\n",
    "pingouin.ttest(x=ameaca1['IQ'], y=ameaca2['IQ'], paired=False, alternative='greater')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Faça um teste da homogeneidade da variância (Levene)\n",
    "- Qual o F ratio e o p-value? Qual o significado?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "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>W</th>\n",
       "      <th>pval</th>\n",
       "      <th>equal_var</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>levene</th>\n",
       "      <td>7.320103</td>\n",
       "      <td>0.000932</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               W      pval  equal_var\n",
       "levene  7.320103  0.000932      False"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pingouin.homoscedasticity(data=iqthreats, dv='IQ', group='condition', method='levene', alpha=0.05)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Visualizar distribuições nas três condições\n",
    "sns.boxplot(x='IQ', y='condition', data=iqthreats)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## ANOVA\n",
    "Utilizaremos os mesmos dados da 'Atividade 07 - IQ - Threat + working memory'. Utilize a aba \"sheet 2\" que possui duas condições de ameaça de estereótipo.\n",
    "Repetiremos a análise da parte 2, mas utilizando a ANOVA. Testaremos a métrica de QI, verificando se há efeito da ameaça de estereótipo e se há diferença os níveis de tratamento."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Faça uma ANOVA com a ameaça como preditor do IQ. (Fit Y by X). \n",
    "- Apresente o resultado e análise e responda: há efeito da ameaça? É significativo?\n",
    "- Quando da variância de IQ pode ser explicada pela ameaça neste modelo?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/pingouin/parametric.py:992: FutureWarning: Not prepending group keys to the result index of transform-like apply. In the future, the group keys will be included in the index, regardless of whether the applied function returns a like-indexed object.\n",
      "To preserve the previous behavior, use\n",
      "\n",
      "\t>>> .groupby(..., group_keys=False)\n",
      "\n",
      "To adopt the future behavior and silence this warning, use \n",
      "\n",
      "\t>>> .groupby(..., group_keys=True)\n",
      "  sserror = grp.apply(lambda x: (x - x.mean()) ** 2).sum()\n"
     ]
    },
    {
     "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>Source</th>\n",
       "      <th>ddof1</th>\n",
       "      <th>ddof2</th>\n",
       "      <th>F</th>\n",
       "      <th>p-unc</th>\n",
       "      <th>np2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>condition</td>\n",
       "      <td>2</td>\n",
       "      <td>147</td>\n",
       "      <td>146.563514</td>\n",
       "      <td>9.881849e-36</td>\n",
       "      <td>0.666006</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Source  ddof1  ddof2           F         p-unc       np2\n",
       "0  condition      2    147  146.563514  9.881849e-36  0.666006"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "alpha = 0.2\n",
    "pingouin.anova(data=iqthreats, dv='IQ', between='condition')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "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>Contrast</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>Paired</th>\n",
       "      <th>Parametric</th>\n",
       "      <th>T</th>\n",
       "      <th>dof</th>\n",
       "      <th>alternative</th>\n",
       "      <th>p-unc</th>\n",
       "      <th>BF10</th>\n",
       "      <th>hedges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>condition</td>\n",
       "      <td>control</td>\n",
       "      <td>threat1</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>12.894779</td>\n",
       "      <td>98.0</td>\n",
       "      <td>two-sided</td>\n",
       "      <td>7.809318e-23</td>\n",
       "      <td>3.424e+19</td>\n",
       "      <td>2.559168</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>condition</td>\n",
       "      <td>control</td>\n",
       "      <td>threat2</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>14.475241</td>\n",
       "      <td>98.0</td>\n",
       "      <td>two-sided</td>\n",
       "      <td>4.466234e-26</td>\n",
       "      <td>4.991e+22</td>\n",
       "      <td>2.872836</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>condition</td>\n",
       "      <td>threat1</td>\n",
       "      <td>threat2</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>1.575479</td>\n",
       "      <td>98.0</td>\n",
       "      <td>two-sided</td>\n",
       "      <td>1.183687e-01</td>\n",
       "      <td>0.632</td>\n",
       "      <td>0.312678</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Contrast        A        B  Paired  Parametric          T   dof  \\\n",
       "0  condition  control  threat1   False        True  12.894779  98.0   \n",
       "1  condition  control  threat2   False        True  14.475241  98.0   \n",
       "2  condition  threat1  threat2   False        True   1.575479  98.0   \n",
       "\n",
       "  alternative         p-unc       BF10    hedges  \n",
       "0   two-sided  7.809318e-23  3.424e+19  2.559168  \n",
       "1   two-sided  4.466234e-26  4.991e+22  2.872836  \n",
       "2   two-sided  1.183687e-01      0.632  0.312678  "
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Teste em pares\n",
    "pingouin.pairwise_tests(data=iqthreats, dv='IQ', between='condition', padjust='none')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "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>Contrast</th>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th>Paired</th>\n",
       "      <th>Parametric</th>\n",
       "      <th>T</th>\n",
       "      <th>dof</th>\n",
       "      <th>alternative</th>\n",
       "      <th>p-unc</th>\n",
       "      <th>p-corr</th>\n",
       "      <th>p-adjust</th>\n",
       "      <th>BF10</th>\n",
       "      <th>hedges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>condition</td>\n",
       "      <td>control</td>\n",
       "      <td>threat1</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>12.894779</td>\n",
       "      <td>98.0</td>\n",
       "      <td>two-sided</td>\n",
       "      <td>7.809318e-23</td>\n",
       "      <td>2.342795e-22</td>\n",
       "      <td>bonf</td>\n",
       "      <td>3.424e+19</td>\n",
       "      <td>2.559168</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>condition</td>\n",
       "      <td>control</td>\n",
       "      <td>threat2</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>14.475241</td>\n",
       "      <td>98.0</td>\n",
       "      <td>two-sided</td>\n",
       "      <td>4.466234e-26</td>\n",
       "      <td>1.339870e-25</td>\n",
       "      <td>bonf</td>\n",
       "      <td>4.991e+22</td>\n",
       "      <td>2.872836</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>condition</td>\n",
       "      <td>threat1</td>\n",
       "      <td>threat2</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>1.575479</td>\n",
       "      <td>98.0</td>\n",
       "      <td>two-sided</td>\n",
       "      <td>1.183687e-01</td>\n",
       "      <td>3.551060e-01</td>\n",
       "      <td>bonf</td>\n",
       "      <td>0.632</td>\n",
       "      <td>0.312678</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    Contrast        A        B  Paired  Parametric          T   dof  \\\n",
       "0  condition  control  threat1   False        True  12.894779  98.0   \n",
       "1  condition  control  threat2   False        True  14.475241  98.0   \n",
       "2  condition  threat1  threat2   False        True   1.575479  98.0   \n",
       "\n",
       "  alternative         p-unc        p-corr p-adjust       BF10    hedges  \n",
       "0   two-sided  7.809318e-23  2.342795e-22     bonf  3.424e+19  2.559168  \n",
       "1   two-sided  4.466234e-26  1.339870e-25     bonf  4.991e+22  2.872836  \n",
       "2   two-sided  1.183687e-01  3.551060e-01     bonf      0.632  0.312678  "
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Ajuste Bonferroni\n",
    "pingouin.pairwise_tests(data=iqthreats, dv='IQ', between='condition', padjust='bonf')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Faça o teste post-hoc Tukey para todos os pares.\n",
    "- Há efeito de todos os níveis? Explique."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/marianne/code/Analise_Estatistica/venv/lib/python3.10/site-packages/pingouin/parametric.py:992: FutureWarning: Not prepending group keys to the result index of transform-like apply. In the future, the group keys will be included in the index, regardless of whether the applied function returns a like-indexed object.\n",
      "To preserve the previous behavior, use\n",
      "\n",
      "\t>>> .groupby(..., group_keys=False)\n",
      "\n",
      "To adopt the future behavior and silence this warning, use \n",
      "\n",
      "\t>>> .groupby(..., group_keys=True)\n",
      "  sserror = grp.apply(lambda x: (x - x.mean()) ** 2).sum()\n"
     ]
    },
    {
     "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>A</th>\n",
       "      <th>B</th>\n",
       "      <th>mean(A)</th>\n",
       "      <th>mean(B)</th>\n",
       "      <th>diff</th>\n",
       "      <th>se</th>\n",
       "      <th>T</th>\n",
       "      <th>p-tukey</th>\n",
       "      <th>hedges</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>control</td>\n",
       "      <td>threat1</td>\n",
       "      <td>97.88</td>\n",
       "      <td>52.16</td>\n",
       "      <td>45.72</td>\n",
       "      <td>3.232193</td>\n",
       "      <td>14.145196</td>\n",
       "      <td>2.153833e-14</td>\n",
       "      <td>2.807333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>control</td>\n",
       "      <td>threat2</td>\n",
       "      <td>97.88</td>\n",
       "      <td>48.02</td>\n",
       "      <td>49.86</td>\n",
       "      <td>3.232193</td>\n",
       "      <td>15.426061</td>\n",
       "      <td>2.153833e-14</td>\n",
       "      <td>3.061540</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>threat1</td>\n",
       "      <td>threat2</td>\n",
       "      <td>52.16</td>\n",
       "      <td>48.02</td>\n",
       "      <td>4.14</td>\n",
       "      <td>3.232193</td>\n",
       "      <td>1.280864</td>\n",
       "      <td>4.082157e-01</td>\n",
       "      <td>0.254207</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         A        B  mean(A)  mean(B)   diff        se          T  \\\n",
       "0  control  threat1    97.88    52.16  45.72  3.232193  14.145196   \n",
       "1  control  threat2    97.88    48.02  49.86  3.232193  15.426061   \n",
       "2  threat1  threat2    52.16    48.02   4.14  3.232193   1.280864   \n",
       "\n",
       "        p-tukey    hedges  \n",
       "0  2.153833e-14  2.807333  \n",
       "1  2.153833e-14  3.061540  \n",
       "2  4.082157e-01  0.254207  "
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pingouin.pairwise_tukey(data=iqthreats, dv='IQ', between='condition')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3.10.6 ('venv': venv)",
   "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": "3.10.6"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "17a21100134af3592d09988eee871935e79466d45670c914d929fa5f969b25f9"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}