{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "79b72c1a-5dc1-45eb-b9d3-4269b5e93311",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "source": [
    "### Checking assumptions and including interactions - Exercises & Answers"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c2110c14-8e45-4d4f-b993-b8a7e2bcde70",
   "metadata": {},
   "source": [
    "## 1. Fitting some models and checking our assumptions\n",
    "Before we begin, lets import most of the things that we'll need.\n",
    "\n",
    "### a. Imports\n",
    "Import `pandas`, `pingouin`, `statsmodels.formula.api` and `seaborn`, and also get the `eval_measures` module from `statsmodels` so we can access the RMSE function\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "03136304-2972-42c0-bf4d-50756320746a",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "# Your answer here\n",
    "import pandas as pd\n",
    "import pingouin as pg\n",
    "import statsmodels.formula.api as smf\n",
    "import seaborn as sns\n",
    "import statsmodels.tools.eval_measures as measures\n",
    "\n",
    "sns.set_style('whitegrid')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b66984b2-e3c0-4fdd-9d08-1b62a9bae6c3",
   "metadata": {},
   "source": [
    "### b. Loading up data\n",
    "This week we test our skills on a new dataset, called the 'Teaching Ratings' dataset. This dataset contains 463 teaching evaluations of a set of professors at the University of Austin, and the characteristics of their course - and also includes how attractive the professor is perceived to be! \n",
    "\n",
    "You can find more discussion of the dataset [here](https://vincentarelbundock.github.io/Rdatasets/doc/AER/TeachingRatings.html), but for our purposes, we will consider the following variables described briefly here:\n",
    "- `age`, the professors age\n",
    "- `minority`, whether the professor belongs to a non-Caucasian minority.\n",
    "- `gender`, indicating the professors gender\n",
    "- `beauty`, a standardised measure of the attractiveness of the professor.\n",
    "- `eval`, the course evaluation score that ranges from 1 to 5.\n",
    "- `native`, whether the instructor is a native English speaker or not.\n",
    "- `students`, number of students who provided evaluations of this professor.\n",
    "- `prof`, a simple number indicating the professor.\n",
    "\n",
    "You can find the dataset at this link:\n",
    "https://vincentarelbundock.github.io/Rdatasets/csv/AER/TeachingRatings.csv\n",
    "\n",
    "Read it into a dataframe called `profs` and show the top 5 rows."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "348ed377-2355-4fa7-96e0-51ce712a77cf",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "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>rownames</th>\n",
       "      <th>minority</th>\n",
       "      <th>age</th>\n",
       "      <th>gender</th>\n",
       "      <th>credits</th>\n",
       "      <th>beauty</th>\n",
       "      <th>eval</th>\n",
       "      <th>division</th>\n",
       "      <th>native</th>\n",
       "      <th>tenure</th>\n",
       "      <th>students</th>\n",
       "      <th>allstudents</th>\n",
       "      <th>prof</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>yes</td>\n",
       "      <td>36</td>\n",
       "      <td>female</td>\n",
       "      <td>more</td>\n",
       "      <td>0.289916</td>\n",
       "      <td>4.3</td>\n",
       "      <td>upper</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>24</td>\n",
       "      <td>43</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>no</td>\n",
       "      <td>59</td>\n",
       "      <td>male</td>\n",
       "      <td>more</td>\n",
       "      <td>-0.737732</td>\n",
       "      <td>4.5</td>\n",
       "      <td>upper</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>17</td>\n",
       "      <td>20</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>no</td>\n",
       "      <td>51</td>\n",
       "      <td>male</td>\n",
       "      <td>more</td>\n",
       "      <td>-0.571984</td>\n",
       "      <td>3.7</td>\n",
       "      <td>upper</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>55</td>\n",
       "      <td>55</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>no</td>\n",
       "      <td>40</td>\n",
       "      <td>female</td>\n",
       "      <td>more</td>\n",
       "      <td>-0.677963</td>\n",
       "      <td>4.3</td>\n",
       "      <td>upper</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>40</td>\n",
       "      <td>46</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>no</td>\n",
       "      <td>31</td>\n",
       "      <td>female</td>\n",
       "      <td>more</td>\n",
       "      <td>1.509794</td>\n",
       "      <td>4.4</td>\n",
       "      <td>upper</td>\n",
       "      <td>yes</td>\n",
       "      <td>yes</td>\n",
       "      <td>42</td>\n",
       "      <td>48</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   rownames minority  age  gender credits    beauty  eval division native  \\\n",
       "0         1      yes   36  female    more  0.289916   4.3    upper    yes   \n",
       "1         2       no   59    male    more -0.737732   4.5    upper    yes   \n",
       "2         3       no   51    male    more -0.571984   3.7    upper    yes   \n",
       "3         4       no   40  female    more -0.677963   4.3    upper    yes   \n",
       "4         5       no   31  female    more  1.509794   4.4    upper    yes   \n",
       "\n",
       "  tenure  students  allstudents  prof  \n",
       "0    yes        24           43     1  \n",
       "1    yes        17           20     2  \n",
       "2    yes        55           55     3  \n",
       "3    yes        40           46     4  \n",
       "4    yes        42           48     5  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your answer here\n",
    "# Read in the dataset\n",
    "profs = pd.read_csv('https://vincentarelbundock.github.io/Rdatasets/csv/AER/TeachingRatings.csv')\n",
    "profs.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3f161582-062d-4581-934e-3f85eaf18fdc",
   "metadata": {},
   "source": [
    "### c. Some graphic exploratory associations\n",
    "Teaching evaluations are studied in surprising depths, particularly in fields such as economics, marketing, and in some parts of psychology. Two constant findings are that a) females receive lower ratings, on average, and that b) more physically attractive individuals get higher ratings, an example of the 'halo effect'.\n",
    "\n",
    "We will examine these questions with a linear model that we will refine. We will aim to predict course evaluations from gender and beauty.\n",
    "\n",
    "First, let us check the assumption of linearity and additivity. Using `seaborn`, make a scatterplot that shows the association between course evaluations and beauty, first colouring each point by whether it belongs to a male or female, and then making a separate plot for each gender - this might require a quick look at last weeks notes, but repetition will solidify these concepts, and allow you to check your first assumptions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "42bc5d35-c515-41c4-abb2-28bc2e916c73",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='beauty', ylabel='eval'>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Scatterplot - your answer here\n",
    "sns.scatterplot(data=profs, x='beauty', y='eval', hue='gender')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "80971885-c951-4b93-935c-ebfd1d4e3692",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<seaborn.axisgrid.FacetGrid at 0x145fae810>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Separate plots - your answer here\n",
    "sns.relplot(data=profs, col='gender', x='beauty', y='eval')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bf419452-336a-4294-b2ec-11bb3eeff84d",
   "metadata": {},
   "source": [
    "Is the assumption of additivity/linearity OK here? Do you observe *relatively linear associations* between these variables?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8b50371-0820-4dce-bcbb-cfb3e5aaca19",
   "metadata": {},
   "source": [
    "### d. Fitting a model and interpreting outputs\n",
    "With that assumption in the bag, fit a model that predicts evaluations from beauty and gender. Make sure you scale beauty, but not gender, to make the interpretation a bit simpler. Store it in dataframe called `modelA` and inspect the summary."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "f2476e26-2dad-41c2-8f88-1a9befae27ee",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>      <td>eval</td>    <th>  R-squared:         </th> <td>   0.066</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>               <td>OLS</td>    <th>  Adj. R-squared:    </th> <td>   0.062</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>  <td>   463</td>   <th>  F-statistic:       </th> <td>   16.33</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>  <td>nonrobust</td> <th>  Prob (F-statistic):</th> <td>1.41e-07</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "         <td></td>           <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Intercept</th>      <td>    3.8838</td> <td>    0.039</td> <td>  100.468</td> <td> 0.000</td> <td>    3.808</td> <td>    3.960</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>gender[T.male]</th> <td>    0.1978</td> <td>    0.051</td> <td>    3.880</td> <td> 0.000</td> <td>    0.098</td> <td>    0.298</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(beauty)</th>  <td>    0.1171</td> <td>    0.025</td> <td>    4.650</td> <td> 0.000</td> <td>    0.068</td> <td>    0.167</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/latex": [
       "\\begin{center}\n",
       "\\begin{tabular}{lclc}\n",
       "\\toprule\n",
       "\\textbf{Dep. Variable:}    &      eval     & \\textbf{  R-squared:         } &     0.066   \\\\\n",
       "\\textbf{Model:}            &      OLS      & \\textbf{  Adj. R-squared:    } &     0.062   \\\\\n",
       "\\textbf{No. Observations:} &        463    & \\textbf{  F-statistic:       } &     16.33   \\\\\n",
       "\\textbf{Covariance Type:}  &   nonrobust   & \\textbf{  Prob (F-statistic):} &  1.41e-07   \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "\\begin{tabular}{lcccccc}\n",
       "                        & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
       "\\midrule\n",
       "\\textbf{Intercept}      &       3.8838  &        0.039     &   100.468  &         0.000        &        3.808    &        3.960     \\\\\n",
       "\\textbf{gender[T.male]} &       0.1978  &        0.051     &     3.880  &         0.000        &        0.098    &        0.298     \\\\\n",
       "\\textbf{scale(beauty)}  &       0.1171  &        0.025     &     4.650  &         0.000        &        0.068    &        0.167     \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "%\\caption{OLS Regression Results}\n",
       "\\end{center}\n",
       "\n",
       "Notes: \\newline\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                   eval   R-squared:                       0.066\n",
       "Model:                            OLS   Adj. R-squared:                  0.062\n",
       "No. Observations:                 463   F-statistic:                     16.33\n",
       "Covariance Type:            nonrobust   Prob (F-statistic):           1.41e-07\n",
       "==================================================================================\n",
       "                     coef    std err          t      P>|t|      [0.025      0.975]\n",
       "----------------------------------------------------------------------------------\n",
       "Intercept          3.8838      0.039    100.468      0.000       3.808       3.960\n",
       "gender[T.male]     0.1978      0.051      3.880      0.000       0.098       0.298\n",
       "scale(beauty)      0.1171      0.025      4.650      0.000       0.068       0.167\n",
       "==================================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your answer here\n",
    "# Fit model, show summary\n",
    "modelA = smf.ols('eval ~ gender + scale(beauty)', data=profs).fit()\n",
    "modelA.summary(slim=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b6870f92-ed75-475d-9e0e-04f0105f477a",
   "metadata": {},
   "source": [
    "From this, what is the mean difference in evaluations between female and male professors, if beauty is set to zero? The answer is in the coefficients."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "30644bda-8013-41e5-aa8b-291d22f1fa73",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "# Your answer here\n",
    "# Females = intercept, males = intercept + coefficient for gender"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "71648e79-3da2-4d4b-aee0-7ffece19d011",
   "metadata": {},
   "source": [
    "From a glance at the coefficients, a new professor who is *two* SDs above the mean would have an increase of how much in their teaching ratings?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "3df265e2-cfb3-4f67-aa77-604cb46a8604",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "# Your answer here\n",
    "# 2 * the coefficient of scaled beauty."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "80df2c71-bac2-4e33-84a9-26d5aabdb2aa",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": []
   },
   "source": [
    "### e. Evaluating the model and checking\n",
    "We've got some basic answers from our model about the influence of beauty and gender on teaching ratings. We also saw these relationships were relatively linear - so now lets see whether our model is any good. \n",
    "\n",
    "Produce a histogram and KDE plot of residuals, checking the normality of the errors. Can you also conduct a Shapiro-Wilk test on them to see if they come from a normal distribution?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b5155519-da9f-453e-9959-58a60543633f",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "ShapiroResult(statistic=0.9804073996638387, pvalue=6.764511194804067e-06)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Your answer here\n",
    "sns.histplot(modelA.resid, kde=True)\n",
    "\n",
    "from scipy.stats import shapiro\n",
    "shapiro(modelA.resid)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a0ddf2c-9eb9-4326-8513-20cc95d4890c",
   "metadata": {},
   "source": [
    "How do these look? Is the test significant?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "84e4125d-8b62-4bab-901d-ee842a88aec4",
   "metadata": {},
   "source": [
    "### d. Checking for homoscedasticity\n",
    "The residuals look mostly normal, though the test is once again suggesting a problem! Move on now to checking the assumption of homoscedasticity - is the variance in prediction consistent? You will need to make a scatterplot of the predictions and the errors here. Can you also add a line at zero to make the points clear?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "d8b25567-0293-46da-90d6-54069a4b16e4",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.lines.Line2D at 0x146a22fd0>"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "axis = sns.scatterplot(x=modelA.fittedvalues, \n",
    "                       y=modelA.resid, alpha=.5) # scatter is easy\n",
    "axis.set(xlabel='Predicted Values', ylabel='Residual') # Renaming \n",
    "axis.axhline(0) # Adding a horizontal line at zero"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d81fb866-13cd-4ff8-996b-1bac3f283d29",
   "metadata": {},
   "source": [
    "How does this look? Any issues here?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b6df8c2-a3d2-4cf8-9aed-ed9796cfd1fa",
   "metadata": {},
   "source": [
    "### f. Further assumptions and conceptual issues\n",
    "Have a look at the `prof` column of your `profs` dataset. This column tells you which rows of the dataset (courses, ratings, etc) belong to a single professor. For example, professor 34 has 13 rows associated with them, as they were evaluated 13 times across different courses. You can count the number of unique values in this column by using something called `value_counts()`, like so:\n",
    "\n",
    "`profs['prof'].value_counts()`\n",
    "\n",
    "Run this line of code. What does this tell you about the *assumption of independence of errors*?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "1faefdbb-18ba-4486-8ed0-a4ed32fd73a8",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "prof\n",
       "34    13\n",
       "50    13\n",
       "82    11\n",
       "71    10\n",
       "58    10\n",
       "      ..\n",
       "22     1\n",
       "47     1\n",
       "69     1\n",
       "30     1\n",
       "62     1\n",
       "Name: count, Length: 94, dtype: int64"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your code here\n",
    "# How many rows belong to individual professors\n",
    "profs['prof'].value_counts()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f232549d-a4ee-4417-9436-1ba6a974f984",
   "metadata": {},
   "source": [
    "While we've done well so far, we've absolutely failed this assumption! Each row of the dataset is **not** independent, with some rows all concerning the same professor. As such we should not trust these results too much - its OK for learning for now, but this would be a bigger issue - and one we will solve later in the course."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af6d23f6-d9c7-4758-80ed-e308b8274f5b",
   "metadata": {},
   "source": [
    "It looks as though beauty has an association with course evaluations. If you check the link\n",
    "[here](https://vincentarelbundock.github.io/Rdatasets/doc/AER/TeachingRatings.html) for a description of the dataset, how much do you trust the `beauty` variable - what's wrong with it? How does this affect our validity and representativeness assumptions?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "9fa89882-b6c9-4292-a0e2-17d948482b96",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "# Your answer here\n",
    "# Its based on just six people! Is that good?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "558bb719-985a-4991-8298-db3fe82060b2",
   "metadata": {},
   "source": [
    "### g. Checking prediction errors\n",
    "Finally for the assumptions of this model, can you check the prediction error using RMSE? How 'off' on average is this model in terms of course evaluations? Is this good?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ba0b3baf-6dda-425e-8989-c5fc41f76ea9",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5355783806218819"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your answer here\n",
    "measures.rmse(profs['eval'], modelA.fittedvalues)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0081c795-7fbd-4e33-9cb6-59ec359d05de",
   "metadata": {},
   "source": [
    "## 2. Expanding the model to improve inferences\n",
    "We can now expand the model to answer a more complex, but more realistic question. The initial model examines whether both males and females differ in their evaluations, *controlling* for attractiveness - remember the coefficient of gender tests the mean difference when other predictors are zero. We also saw that attractiveness is associated with higher course evaluations, altogether.\n",
    "\n",
    "### a. An interaction\n",
    "Perhaps we should consider whether the effect of attractiveness on evaluations is *different* for men and women. To do this, we need an interaction. Fit a model with an interaction between gender and (scaled) beauty; call it `modelB`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "b4438fe0-9138-444c-add9-182890c37e5d",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>      <td>eval</td>    <th>  R-squared:         </th> <td>   0.073</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>               <td>OLS</td>    <th>  Adj. R-squared:    </th> <td>   0.066</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>  <td>   463</td>   <th>  F-statistic:       </th> <td>   11.97</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>  <td>nonrobust</td> <th>  Prob (F-statistic):</th> <td>1.47e-07</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "                <td></td>                  <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Intercept</th>                    <td>    3.8909</td> <td>    0.039</td> <td>  100.337</td> <td> 0.000</td> <td>    3.815</td> <td>    3.967</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>gender[T.male]</th>               <td>    0.1951</td> <td>    0.051</td> <td>    3.834</td> <td> 0.000</td> <td>    0.095</td> <td>    0.295</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(beauty)</th>                <td>    0.0690</td> <td>    0.037</td> <td>    1.862</td> <td> 0.063</td> <td>   -0.004</td> <td>    0.142</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(beauty):gender[T.male]</th> <td>    0.0888</td> <td>    0.050</td> <td>    1.761</td> <td> 0.079</td> <td>   -0.010</td> <td>    0.188</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/latex": [
       "\\begin{center}\n",
       "\\begin{tabular}{lclc}\n",
       "\\toprule\n",
       "\\textbf{Dep. Variable:}               &      eval     & \\textbf{  R-squared:         } &     0.073   \\\\\n",
       "\\textbf{Model:}                       &      OLS      & \\textbf{  Adj. R-squared:    } &     0.066   \\\\\n",
       "\\textbf{No. Observations:}            &        463    & \\textbf{  F-statistic:       } &     11.97   \\\\\n",
       "\\textbf{Covariance Type:}             &   nonrobust   & \\textbf{  Prob (F-statistic):} &  1.47e-07   \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "\\begin{tabular}{lcccccc}\n",
       "                                      & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
       "\\midrule\n",
       "\\textbf{Intercept}                    &       3.8909  &        0.039     &   100.337  &         0.000        &        3.815    &        3.967     \\\\\n",
       "\\textbf{gender[T.male]}               &       0.1951  &        0.051     &     3.834  &         0.000        &        0.095    &        0.295     \\\\\n",
       "\\textbf{scale(beauty)}                &       0.0690  &        0.037     &     1.862  &         0.063        &       -0.004    &        0.142     \\\\\n",
       "\\textbf{scale(beauty):gender[T.male]} &       0.0888  &        0.050     &     1.761  &         0.079        &       -0.010    &        0.188     \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "%\\caption{OLS Regression Results}\n",
       "\\end{center}\n",
       "\n",
       "Notes: \\newline\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                   eval   R-squared:                       0.073\n",
       "Model:                            OLS   Adj. R-squared:                  0.066\n",
       "No. Observations:                 463   F-statistic:                     11.97\n",
       "Covariance Type:            nonrobust   Prob (F-statistic):           1.47e-07\n",
       "================================================================================================\n",
       "                                   coef    std err          t      P>|t|      [0.025      0.975]\n",
       "------------------------------------------------------------------------------------------------\n",
       "Intercept                        3.8909      0.039    100.337      0.000       3.815       3.967\n",
       "gender[T.male]                   0.1951      0.051      3.834      0.000       0.095       0.295\n",
       "scale(beauty)                    0.0690      0.037      1.862      0.063      -0.004       0.142\n",
       "scale(beauty):gender[T.male]     0.0888      0.050      1.761      0.079      -0.010       0.188\n",
       "================================================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your answer here\n",
    "# Interaction model\n",
    "modelB = smf.ols('eval ~ scale(beauty) + gender + scale(beauty):gender', data=profs).fit()\n",
    "modelB.summary(slim=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15c3b968-6f2f-4677-8ba7-377b704ab351",
   "metadata": {},
   "source": [
    "First, can you conduct an F-test to see whether the interaction significantly raises the $R^2$ compared to `modelA`?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "92adccde-d5f0-4c66-ab0e-da11a55d84e4",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(3.1010028248372294, 0.07890991920658393, 1.0)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your answer here\n",
    "modelB.compare_f_test(modelA)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1ae6597c-140f-491f-aa92-656c9b776c40",
   "metadata": {},
   "source": [
    "Can you calculate the RMSE and see whether it has improved as a consequence of including the interaction?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "a68eb6d2-0cae-4772-8bfb-8570aca728a5",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5337783133573137"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your answer here\n",
    "measures.rmse(profs['eval'], modelB.fittedvalues)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5b59e5c-b295-4c3f-a42a-e8e3a318ea01",
   "metadata": {},
   "source": [
    "Does this model suggest evidence of beauty influence teaching evaluations? Note the differences between the conclusions of modelA and modelB, and consider which model is more representative of the real process of teaching evalutions."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "ee2fb04b-d2a9-40dc-b9c3-4dbe2f422c3c",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "# Your answer here\n",
    "# No, no clear evidence in B, but some in A, but A is less realistic."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f580ab60-554f-415e-9ad4-f2e8b341684e",
   "metadata": {},
   "source": [
    "### b. Additional controls\n",
    "When building models, it is necessary to think carefully about the process you are studying, and remember the mantra that 'all models are wrong, but some are useful'.\n",
    "\n",
    "Suppose our initial question is to see how beauty affects teaching evaluations separately for men and women. The interaction certainly allows us to answer that, but the dataset contains many other variables that likely impact teaching evaluations. For example:\n",
    "- `minority` codes whether the professor belongs to an ethnic minority. There is a long history suggesting things like accents affect teaching evaluations (sadly).\n",
    "- `age` may affect beauty, since younger people are more attractive, on average.\n",
    "- `tenure` codes whether a professor has achieved tenure, generally granted after around 7 years of teaching and research experience. In principle, these individuals should be better teachers.\n",
    "\n",
    "Let us now expand our model to include these predictors. We will scale age since it is a continuous variable, but we will just include minority and tenure. Including these will allow to see if our hypothesised interaction between sex and beauty exists once we account (i.e., set to zero) these other important predictors of teaching ability. Call this `modelC`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "c957d806-d52d-439f-99de-7080beb7086f",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>      <td>eval</td>    <th>  R-squared:         </th> <td>   0.094</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>               <td>OLS</td>    <th>  Adj. R-squared:    </th> <td>   0.082</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>  <td>   463</td>   <th>  F-statistic:       </th> <td>   7.892</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>  <td>nonrobust</td> <th>  Prob (F-statistic):</th> <td>4.18e-08</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "                <td></td>                  <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Intercept</th>                    <td>    4.0276</td> <td>    0.060</td> <td>   67.262</td> <td> 0.000</td> <td>    3.910</td> <td>    4.145</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>minority[T.yes]</th>              <td>   -0.0837</td> <td>    0.074</td> <td>   -1.138</td> <td> 0.256</td> <td>   -0.228</td> <td>    0.061</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>tenure[T.yes]</th>                <td>   -0.1825</td> <td>    0.062</td> <td>   -2.958</td> <td> 0.003</td> <td>   -0.304</td> <td>   -0.061</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>gender[T.male]</th>               <td>    0.2197</td> <td>    0.053</td> <td>    4.154</td> <td> 0.000</td> <td>    0.116</td> <td>    0.324</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(age)</th>                   <td>   -0.0364</td> <td>    0.027</td> <td>   -1.331</td> <td> 0.184</td> <td>   -0.090</td> <td>    0.017</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(beauty)</th>                <td>    0.0842</td> <td>    0.038</td> <td>    2.238</td> <td> 0.026</td> <td>    0.010</td> <td>    0.158</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(beauty):gender[T.male]</th> <td>    0.0424</td> <td>    0.052</td> <td>    0.813</td> <td> 0.416</td> <td>   -0.060</td> <td>    0.145</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/latex": [
       "\\begin{center}\n",
       "\\begin{tabular}{lclc}\n",
       "\\toprule\n",
       "\\textbf{Dep. Variable:}               &      eval     & \\textbf{  R-squared:         } &     0.094   \\\\\n",
       "\\textbf{Model:}                       &      OLS      & \\textbf{  Adj. R-squared:    } &     0.082   \\\\\n",
       "\\textbf{No. Observations:}            &        463    & \\textbf{  F-statistic:       } &     7.892   \\\\\n",
       "\\textbf{Covariance Type:}             &   nonrobust   & \\textbf{  Prob (F-statistic):} &  4.18e-08   \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "\\begin{tabular}{lcccccc}\n",
       "                                      & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
       "\\midrule\n",
       "\\textbf{Intercept}                    &       4.0276  &        0.060     &    67.262  &         0.000        &        3.910    &        4.145     \\\\\n",
       "\\textbf{minority[T.yes]}              &      -0.0837  &        0.074     &    -1.138  &         0.256        &       -0.228    &        0.061     \\\\\n",
       "\\textbf{tenure[T.yes]}                &      -0.1825  &        0.062     &    -2.958  &         0.003        &       -0.304    &       -0.061     \\\\\n",
       "\\textbf{gender[T.male]}               &       0.2197  &        0.053     &     4.154  &         0.000        &        0.116    &        0.324     \\\\\n",
       "\\textbf{scale(age)}                   &      -0.0364  &        0.027     &    -1.331  &         0.184        &       -0.090    &        0.017     \\\\\n",
       "\\textbf{scale(beauty)}                &       0.0842  &        0.038     &     2.238  &         0.026        &        0.010    &        0.158     \\\\\n",
       "\\textbf{scale(beauty):gender[T.male]} &       0.0424  &        0.052     &     0.813  &         0.416        &       -0.060    &        0.145     \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "%\\caption{OLS Regression Results}\n",
       "\\end{center}\n",
       "\n",
       "Notes: \\newline\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                   eval   R-squared:                       0.094\n",
       "Model:                            OLS   Adj. R-squared:                  0.082\n",
       "No. Observations:                 463   F-statistic:                     7.892\n",
       "Covariance Type:            nonrobust   Prob (F-statistic):           4.18e-08\n",
       "================================================================================================\n",
       "                                   coef    std err          t      P>|t|      [0.025      0.975]\n",
       "------------------------------------------------------------------------------------------------\n",
       "Intercept                        4.0276      0.060     67.262      0.000       3.910       4.145\n",
       "minority[T.yes]                 -0.0837      0.074     -1.138      0.256      -0.228       0.061\n",
       "tenure[T.yes]                   -0.1825      0.062     -2.958      0.003      -0.304      -0.061\n",
       "gender[T.male]                   0.2197      0.053      4.154      0.000       0.116       0.324\n",
       "scale(age)                      -0.0364      0.027     -1.331      0.184      -0.090       0.017\n",
       "scale(beauty)                    0.0842      0.038      2.238      0.026       0.010       0.158\n",
       "scale(beauty):gender[T.male]     0.0424      0.052      0.813      0.416      -0.060       0.145\n",
       "================================================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your answer here\n",
    "modelC = smf.ols('eval ~ minority + tenure + scale(age) + gender + scale(beauty) + scale(beauty):gender', \n",
    "                 data=profs).fit()\n",
    "modelC.summary(slim=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9b8217ee-0ff8-4d29-ac53-a1c1cf9361b3",
   "metadata": {},
   "source": [
    "Now check whether *this* model is 'significantly' better than modelB, and then check the RMSE. What does the statistical significance of the test tell you in comparison to the RMSE?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "51b0efaf-5da7-4225-be74-e7b091bddc38",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(3.6090171263130095, 0.013388316523354751, 3.0)\n",
      "0.5275520794476387\n"
     ]
    }
   ],
   "source": [
    "# Your answer here\n",
    "print(modelC.compare_f_test(modelB))\n",
    "print(measures.rmse(profs['eval'], modelC.fittedvalues))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de868126-5faa-417b-9e23-931f87301939",
   "metadata": {},
   "source": [
    "What does the model indicate about the effects of beauty now, and the difference between males and females? What about the effects of having tenure and being in a minority?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "f3126cc5-82d5-4dca-9e81-0c97332a2063",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [],
   "source": [
    "# Your answer here\n",
    "# No effect of minority, tenured reduces evaluation, \n",
    "# males are still higher then females, \n",
    "# beauty weakly increases evaluations, and no difference in that between sexes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "229539bb-c831-4a51-ab4b-6095952e040f",
   "metadata": {},
   "source": [
    "### c. A final challenge in interactions\n",
    "The interaction we have examined so far (with additional controls) is an interaction between two variables, one a categorical variable and one a continuous. This is sometimes known as a 'two-way' interaction. We can expand this further into an interaction between *three* variables, just to show you that the GLM is very flexible.\n",
    "\n",
    "Perhaps we think that rather than just controlling for how old a professor is, we should let age interact with gender and beauty. That is, we hypothesise that the effect of beauty on evaluations depends on both your gender, and your age. In order to know how your beauty affects your evaluations, we need to know your age and gender.\n",
    "\n",
    "Fitting an interaction with three variables is slightly more complex as you must include what's called the 'lower level' interactions, of which there are three!\n",
    "- beauty:gender (as we've targeted)\n",
    "- beauty:age\n",
    "- gender:age\n",
    "\n",
    "and then you can include the interaction between all three - e.g., beauty:age:gender.\n",
    "\n",
    "Writing that out would be a lot of work. `statsmodels` simplifies things a bit for us here. So far we've specified interactions with ':', but if we want to include all the lower-level ones in a single go, we can just use '*'. So, to make clear, these two things are identical:\n",
    "\n",
    "`eval ~ gender + beauty + gender:beauty`\n",
    "and\n",
    "`eval ~ gender*beauty`\n",
    "\n",
    "Being able to write out the full formula is a bonus, but it can slow you down, and this version just makes it easier for us. With that in mind, fit a model below that includes minority and tenure as controls, but lets age, gender, and beauty all interact together. Call this `modelD`, and remember to scale age and beauty.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "6487260a-2647-48f3-96f7-edfdabfc873e",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>      <td>eval</td>    <th>  R-squared:         </th> <td>   0.158</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>               <td>OLS</td>    <th>  Adj. R-squared:    </th> <td>   0.141</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>  <td>   463</td>   <th>  F-statistic:       </th> <td>   9.427</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>  <td>nonrobust</td> <th>  Prob (F-statistic):</th> <td>3.42e-13</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "                     <td></td>                        <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Intercept</th>                               <td>    3.9615</td> <td>    0.060</td> <td>   66.202</td> <td> 0.000</td> <td>    3.844</td> <td>    4.079</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>tenure[T.yes]</th>                           <td>   -0.1355</td> <td>    0.062</td> <td>   -2.170</td> <td> 0.031</td> <td>   -0.258</td> <td>   -0.013</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>minority[T.yes]</th>                         <td>   -0.1045</td> <td>    0.072</td> <td>   -1.442</td> <td> 0.150</td> <td>   -0.247</td> <td>    0.038</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>gender[T.male]</th>                          <td>    0.2893</td> <td>    0.053</td> <td>    5.499</td> <td> 0.000</td> <td>    0.186</td> <td>    0.393</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(age)</th>                              <td>   -0.1339</td> <td>    0.045</td> <td>   -3.003</td> <td> 0.003</td> <td>   -0.222</td> <td>   -0.046</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(age):gender[T.male]</th>               <td>    0.1601</td> <td>    0.055</td> <td>    2.906</td> <td> 0.004</td> <td>    0.052</td> <td>    0.268</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(beauty)</th>                           <td>    0.0358</td> <td>    0.049</td> <td>    0.731</td> <td> 0.465</td> <td>   -0.060</td> <td>    0.132</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(beauty):gender[T.male]</th>            <td>    0.0690</td> <td>    0.062</td> <td>    1.108</td> <td> 0.268</td> <td>   -0.053</td> <td>    0.191</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(age):scale(beauty)</th>                <td>   -0.0414</td> <td>    0.044</td> <td>   -0.934</td> <td> 0.351</td> <td>   -0.129</td> <td>    0.046</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>scale(age):scale(beauty):gender[T.male]</th> <td>    0.2052</td> <td>    0.056</td> <td>    3.655</td> <td> 0.000</td> <td>    0.095</td> <td>    0.316</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/latex": [
       "\\begin{center}\n",
       "\\begin{tabular}{lclc}\n",
       "\\toprule\n",
       "\\textbf{Dep. Variable:}                          &      eval     & \\textbf{  R-squared:         } &     0.158   \\\\\n",
       "\\textbf{Model:}                                  &      OLS      & \\textbf{  Adj. R-squared:    } &     0.141   \\\\\n",
       "\\textbf{No. Observations:}                       &        463    & \\textbf{  F-statistic:       } &     9.427   \\\\\n",
       "\\textbf{Covariance Type:}                        &   nonrobust   & \\textbf{  Prob (F-statistic):} &  3.42e-13   \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "\\begin{tabular}{lcccccc}\n",
       "                                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
       "\\midrule\n",
       "\\textbf{Intercept}                               &       3.9615  &        0.060     &    66.202  &         0.000        &        3.844    &        4.079     \\\\\n",
       "\\textbf{tenure[T.yes]}                           &      -0.1355  &        0.062     &    -2.170  &         0.031        &       -0.258    &       -0.013     \\\\\n",
       "\\textbf{minority[T.yes]}                         &      -0.1045  &        0.072     &    -1.442  &         0.150        &       -0.247    &        0.038     \\\\\n",
       "\\textbf{gender[T.male]}                          &       0.2893  &        0.053     &     5.499  &         0.000        &        0.186    &        0.393     \\\\\n",
       "\\textbf{scale(age)}                              &      -0.1339  &        0.045     &    -3.003  &         0.003        &       -0.222    &       -0.046     \\\\\n",
       "\\textbf{scale(age):gender[T.male]}               &       0.1601  &        0.055     &     2.906  &         0.004        &        0.052    &        0.268     \\\\\n",
       "\\textbf{scale(beauty)}                           &       0.0358  &        0.049     &     0.731  &         0.465        &       -0.060    &        0.132     \\\\\n",
       "\\textbf{scale(beauty):gender[T.male]}            &       0.0690  &        0.062     &     1.108  &         0.268        &       -0.053    &        0.191     \\\\\n",
       "\\textbf{scale(age):scale(beauty)}                &      -0.0414  &        0.044     &    -0.934  &         0.351        &       -0.129    &        0.046     \\\\\n",
       "\\textbf{scale(age):scale(beauty):gender[T.male]} &       0.2052  &        0.056     &     3.655  &         0.000        &        0.095    &        0.316     \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "%\\caption{OLS Regression Results}\n",
       "\\end{center}\n",
       "\n",
       "Notes: \\newline\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                   eval   R-squared:                       0.158\n",
       "Model:                            OLS   Adj. R-squared:                  0.141\n",
       "No. Observations:                 463   F-statistic:                     9.427\n",
       "Covariance Type:            nonrobust   Prob (F-statistic):           3.42e-13\n",
       "===========================================================================================================\n",
       "                                              coef    std err          t      P>|t|      [0.025      0.975]\n",
       "-----------------------------------------------------------------------------------------------------------\n",
       "Intercept                                   3.9615      0.060     66.202      0.000       3.844       4.079\n",
       "tenure[T.yes]                              -0.1355      0.062     -2.170      0.031      -0.258      -0.013\n",
       "minority[T.yes]                            -0.1045      0.072     -1.442      0.150      -0.247       0.038\n",
       "gender[T.male]                              0.2893      0.053      5.499      0.000       0.186       0.393\n",
       "scale(age)                                 -0.1339      0.045     -3.003      0.003      -0.222      -0.046\n",
       "scale(age):gender[T.male]                   0.1601      0.055      2.906      0.004       0.052       0.268\n",
       "scale(beauty)                               0.0358      0.049      0.731      0.465      -0.060       0.132\n",
       "scale(beauty):gender[T.male]                0.0690      0.062      1.108      0.268      -0.053       0.191\n",
       "scale(age):scale(beauty)                   -0.0414      0.044     -0.934      0.351      -0.129       0.046\n",
       "scale(age):scale(beauty):gender[T.male]     0.2052      0.056      3.655      0.000       0.095       0.316\n",
       "===========================================================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Your answer here\n",
    "modelD = smf.ols('eval ~ tenure + minority + scale(age)*scale(beauty)*gender', data=profs).fit()\n",
    "modelD.summary(slim=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd877e1a-d2c0-48e8-9db9-f23ad6824ad6",
   "metadata": {},
   "source": [
    "What does this model say about effect of beauty on evaluations considering age and gender? Can you compare this model to model C, and also assess its RMSE?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "6a3b2523-d634-46c4-b4da-e9c309c34cd2",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(11.416009424414138, 3.1413335349546134e-07, 3.0)\n",
      "0.5086738302618814\n"
     ]
    }
   ],
   "source": [
    "# Your answer here\n",
    "print(modelD.compare_f_test(modelC))\n",
    "print(measures.rmse(profs['eval'], modelD.fittedvalues))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fcc06f2b-4090-49b7-9592-83a11336d4ef",
   "metadata": {},
   "source": [
    "Notice how the F-test suggests a very significant increase in variance explained, while RMSE decreases only a little. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "71523f61-53f0-40bb-97eb-9e972cf1558c",
   "metadata": {},
   "source": [
    "### d. Interpreting this interaction\n",
    "You can see that the interaction between all three variables (age, gender, beauty) is statistically significant. But what does it *mean*? You absolutely cannot tell by looking at the coefficients, and this is why in general looking at them is folly. Run the code below to see a plot and see if graphically interpreting the predictions helps."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "5c585ccd-a629-45b1-bfcd-2370b33cf998",
   "metadata": {
    "editable": true,
    "slideshow": {
     "slide_type": ""
    },
    "tags": [
     "hide-input"
    ]
   },
   "outputs": [
    {
     "data": {
      "image/png": "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"
     },
     "metadata": {
      "image/png": {
       "height": 480,
       "width": 640
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Try this code for your modelD\n",
    "import marginaleffects as me\n",
    "me.plot_predictions(model=modelD, condition=['beauty', 'age', 'gender'])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c1805dad-8de0-4a76-9635-94bdd025710a",
   "metadata": {},
   "source": [
    "What does the interaction show you?"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}