{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Quickstart"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Introduction \n",
    "\n",
    "`sensemakr` for Python (PySensemakr) implements a suite of sensitivity analysis tools that makes it easier to understand the impact of omitted variables in linear regression models, as discussed in [Cinelli, C. and Hazlett, C. (2020) “Making\n",
    "Sense of Sensitivity: Extending Omitted Variable Bias.” Journal of the\n",
    "Royal Statistical Society, Series B (Statistical\n",
    "Methodology).](https://doi.org/10.1111/rssb.12348) The Python version of the package closely mirrors the R version, which can be found [here](https://github.com/carloscinelli/sensemakr). \n",
    "\n",
    "In this quickstart, we demonstrate the basic usage of the package by reproducing  Section 5 of Cinelli and Hazlett (2020), which estimates the effects of exposure to violence on attitudes towards peace, in Darfur. Throughout this manual, we mainly focus on the code. For detailed explanations, please refer to the original paper."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Violence in Darfur"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In 2003 and 2004, the Darfurian government orchestrated a horrific campaign of violence against civilians, killing an estimated two hundred thousand people. In this application, we are interested in answering the following question: did being directly exposed to harm make individuals more \"angry,\" and thus more likely to ask for revenge, or did it make them more \"weary,\" and thus more likely to ask for peace?  \n",
    "\n",
    "`PySensemakr` comes with the Darfur dataset, which can be loaded with the command `data.load_darfur()`. More details about the data can be found in the documentation, as well as in Hazlett (2019) and Cinelli and Hazlett (2020)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-02-12T19:58:33.334302Z",
     "start_time": "2021-02-12T19:58:31.753594Z"
    }
   },
   "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>wouldvote</th>\n",
       "      <th>peacefactor</th>\n",
       "      <th>peace_formerenemies</th>\n",
       "      <th>peace_jjindiv</th>\n",
       "      <th>peace_jjtribes</th>\n",
       "      <th>gos_soldier_execute</th>\n",
       "      <th>directlyharmed</th>\n",
       "      <th>age</th>\n",
       "      <th>farmer_dar</th>\n",
       "      <th>herder_dar</th>\n",
       "      <th>pastvoted</th>\n",
       "      <th>hhsize_darfur</th>\n",
       "      <th>village</th>\n",
       "      <th>female</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>30</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>23</td>\n",
       "      <td>Abdel Khair</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0.706831</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>5</td>\n",
       "      <td>Abdi Dar</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>45</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>15</td>\n",
       "      <td>Abu Sorog</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>0.495178</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>55</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>Abu Dejaj</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>25</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>Abu Dejaj</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   wouldvote  peacefactor  peace_formerenemies  peace_jjindiv  peace_jjtribes  \\\n",
       "0          0     1.000000                    1              1               1   \n",
       "1          0     0.706831                    0              1               1   \n",
       "2          1     0.000000                    0              0               0   \n",
       "3          1     0.495178                    1              0               0   \n",
       "4          0     0.000000                    0              0               0   \n",
       "\n",
       "   gos_soldier_execute  directlyharmed  age  farmer_dar  herder_dar  \\\n",
       "0                    0               0   30           0           0   \n",
       "1                    0               0   20           1           0   \n",
       "2                    1               0   45           1           0   \n",
       "3                    0               1   55           0           0   \n",
       "4                    1               1   25           1           0   \n",
       "\n",
       "   pastvoted  hhsize_darfur      village  female  \n",
       "0          1             23  Abdel Khair       0  \n",
       "1          1              5     Abdi Dar       1  \n",
       "2          0             15    Abu Sorog       0  \n",
       "3          0              9    Abu Dejaj       0  \n",
       "4          1              7    Abu Dejaj       1  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# imports sensemakr\n",
    "import sensemakr as smkr\n",
    "\n",
    "# loads darfur data\n",
    "darfur = smkr.load_darfur()\n",
    "darfur.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A natural approach for such problem is to run the following linear regression model, where we regress `peacefactor` on `directlyharmed`, further adjusting for `village`, `female` as well as other covariates. Here we run this regression using `statsmodel`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-02-12T19:58:33.698211Z",
     "start_time": "2021-02-12T19:58:33.459347Z"
    }
   },
   "outputs": [],
   "source": [
    "# imports \n",
    "import statsmodels.formula.api as smf\n",
    "\n",
    "# runs regression model\n",
    "reg_model = smf.ols(formula='peacefactor ~ directlyharmed + age + farmer_dar + herder_dar + '\\\n",
    "                    'pastvoted + hhsize_darfur + female + village', data=darfur)\n",
    "darfur_model = reg_model.fit()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The above regression results in the following estimate and standard errors for the coefficient of `directlyharmed`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "         <td></td>        <th>peacefactor</th>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>directlyharmed</th>   <td>0.0973</td>   \n",
       "</tr>\n",
       "<tr>\n",
       "  <th></th>                <td>(0.0233)</td>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>R-squared</th>        <td>0.5115</td>   \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>R-squared Adj.</th>   <td>0.2046</td>   \n",
       "</tr>\n",
       "</table>"
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary2.Summary'>\n",
       "\"\"\"\n",
       "\n",
       "==========================\n",
       "               peacefactor\n",
       "--------------------------\n",
       "directlyharmed 0.0973     \n",
       "               (0.0233)   \n",
       "R-squared      0.5115     \n",
       "R-squared Adj. 0.2046     \n",
       "==========================\n",
       "Standard errors in\n",
       "parentheses.\n",
       "\"\"\""
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# imports statsmodels summary_col function\n",
    "from statsmodels.iolib.summary2 import summary_col\n",
    "\n",
    "# summary of regression results for directlyharmed\n",
    "summary_col(darfur_model, regressor_order=[\"directlyharmed\"], drop_omitted=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "According to this model, those individual who were directly exposed to harm became on average more “pro-peace,” not less."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Sensitivity Analysis\n",
    "The causal interpretation of the previous estimate, however, relies on the assumption that `village` and `gender` are sufficient for control of confounding---in other words, it requires the assumption of *no unobserved confounders*. What if is wrong? How strong would these unobserved variables have to be in order to change the original research conclusions? The goal of `sensemakr' is precisely that, i.e, to make it easier to understand the impact that omitted variables would have on a regression result.  "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The main function of the package is the function `Sensemakr`. The `Sensemakr` function defines an object of class `Sensemakr,`  performing the most commonly required sensitivity analyses which can then be further explored with the `summary` and `plot` methods of the object. This function is mainly a convenience wrapper for other sensitivity functions defined in the package, which can also be called directly, as we detail later in the documentation. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the code chunk below, we apply the function `Sensemakr` to our OLS model from `statsmodel`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-02-12T19:58:33.974876Z",
     "start_time": "2021-02-12T19:58:33.748565Z"
    }
   },
   "outputs": [],
   "source": [
    "# creates a Sensemakr object\n",
    "darfur_sense = smkr.Sensemakr(model = darfur_model, \n",
    "                              treatment = \"directlyharmed\", \n",
    "                              benchmark_covariates = [\"female\"], \n",
    "                              kd = [1,2,3],\n",
    "                              ky = [1,2,3],\n",
    "                              q = 1.0, \n",
    "                              alpha = 0.05, \n",
    "                              reduce = True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The main arguments of the call are:\n",
    "\n",
    "**model**: the OLS model with the outcome regression. In our case, `darfur_model`.\n",
    "\n",
    "\n",
    "**treatment**: the name of the treatment variable. In our case, \"directlyharmed\".\n",
    "\n",
    "\n",
    "**benchmark_covariates**: the names of covariates that will be used to bound the plausible strength of the unobserved confounders. Here, we put \"female\", which is arguably one of the main determinants of exposure to violence, and also a strong determinant of attitudes towards peace.\n",
    "\n",
    "\n",
    "**kd** and **ky**: these arguments parameterize how many times stronger the confounder is related to the treatment (kd) and to the outcome (ky) in comparison to the observed benchmark covariates (in this case, female). In our example, setting `kd = [1, 2, 3]` and `ky = [1,2,3]` means we want to investigate the maximum strength of a confounder once, twice, or three times as strong as female (in explaining treatment and outcome variation). If only `kd` is given, `ky` will be set equal to `kd`.\n",
    "\n",
    "\n",
    "**q**: fraction of the effect estimate that would have to be explained away to be problematic. Setting q = 1, means that a reduction of 100% of the current effect estimate, that is, a true effect of zero, would be deemed problematic. The default is 1.\n",
    "\n",
    "\n",
    "**alpha**: significance level of interest for statistical inference. The default is 0.05.\n",
    "\n",
    "\n",
    "**reduce**: should we consider confounders acting towards increasing or reducing the absolute value of the estimate? The default is `reduce = True`, which means we are considering confounders that pull the estimate towards (or through) zero.\n",
    "\n",
    "\n",
    "Using the default arguments, one can simplify the previous call to:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# creates a Sensemakr object\n",
    "darfur_sense = smkr.Sensemakr(model = darfur_model, \n",
    "                              treatment = \"directlyharmed\", \n",
    "                              benchmark_covariates = [\"female\"], \n",
    "                              kd = [1,2,3])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Once we run `Sensemakr`, we can now explore the sensitivity analysis results."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Minimal sensitivity reporting\n",
    "\n",
    "The print method of Sensemakr provides a quick review of the original (unadjusted) estimates along with three summary sensitivity statistics suited for routine reporting: the partial $R^2$ of the treatment with the outcome, the robustness value ($RV$) required to reduce the estimate entirely to zero (i.e. $q=1$), and the RV beyond which the estimate would no longer be statistically distinguishable from zero at the 0.05 level $(q=1, \\alpha = 0.05)$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sensitivity Analysis to Unobserved Confounding\n",
      "\n",
      "Model Formula: peacefactor ~ directlyharmed + age + farmer_dar + herder_dar + pastvoted + hhsize_darfur + female + village\n",
      "\n",
      "Null hypothesis: q = 1 and reduce = True \n",
      "\n",
      "Unadjusted Estimates of ' directlyharmed ':\n",
      "  Coef. estimate: 0.097\n",
      "  Standard Error: 0.023\n",
      "  t-value: 4.184 \n",
      "\n",
      "Sensitivity Statistics:\n",
      "  Partial R2 of treatment with outcome: 0.022\n",
      "  Robustness Value, q = 1 : 0.139\n",
      "  Robustness Value, q = 1 alpha = 0.05 : 0.076 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "# basic print\n",
    "darfur_sense.print()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The package also provides a function that outputs code for a latex or html table with these results. If used in an interactive environment, such as a Jupyter notebook, the table is also automatically displayed in the notebook."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table style='align:center'>\n",
       "<thead>\n",
       "<tr>\n",
       "\t<th style=\"text-align:left;border-bottom: 1px solid transparent;border-top: 1px solid black\"> </th>\n",
       "\t<th colspan = 6 style=\"text-align:center;border-bottom: 1px solid black;border-top: 1px solid black\"> Outcome: peacefactor</th>\n",
       "</tr>\n",
       "<tr>\n",
       "\t<th style=\"text-align:left;border-top: 1px solid black\"> Treatment </th>\n",
       "\t<th style=\"text-align:right;border-top: 1px solid black\"> Est. </th>\n",
       "\t<th style=\"text-align:right;border-top: 1px solid black\"> S.E. </th>\n",
       "\t<th style=\"text-align:right;border-top: 1px solid black\"> t-value </th>\n",
       "\t<th style=\"text-align:right;border-top: 1px solid black\"> R<sup>2</sup><sub>Y~D|X</sub> </th>\n",
       "\t<th style=\"text-align:right;border-top: 1px solid black\">  RV<sub>q = 1</sub> </th>\n",
       "\t<th style=\"text-align:right;border-top: 1px solid black\"> RV<sub>q = 1, &alpha; = 0.05</sub> </th>\n",
       "</tr>\n",
       "</thead>\n",
       "<tbody>\n",
       " <tr>\n",
       "\t<td style=\"text-align:left; border-bottom: 1px solid black\"><i>directlyharmed</i></td>\n",
       "\t<td style=\"text-align:right;border-bottom: 1px solid black\">0.097 </td>\n",
       "\t<td style=\"text-align:right;border-bottom: 1px solid black\">0.023 </td>\n",
       "\t<td style=\"text-align:right;border-bottom: 1px solid black\">4.2 </td>\n",
       "\t<td style=\"text-align:right;border-bottom: 1px solid black\">2.2% </td>\n",
       "\t<td style=\"text-align:right;border-bottom: 1px solid black\">13.9% </td>\n",
       "\t<td style=\"text-align:right;border-bottom: 1px solid black\">7.6% </td>\n",
       "</tr>\n",
       "</tbody>\n",
       "<tr>\n",
       "<td colspan = 7 style='text-align:right;border-top: 1px solid black;border-bottom: 1px solid transparent;font-size:11px'>Note: df = 783; Bound ( 1x female ):  R<sup>2</sup><sub>Y~Z|X,D</sub> =  12.5%, R<sup>2</sup><sub>D~Z|X</sub> =0.9%</td>\n",
       "</tr>\n",
       "</table>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# html code for minimal reporting table\n",
    "html_code = darfur_sense.ovb_minimal_reporting(format = \"html\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "These three sensitivity statistics provide a minimal reporting for sensitivity analysis. More precisely:\n",
    "\n",
    "The robustness value for bringing the point estimate of directlyharmed exactly to zero $(RV_{q=1})$ is 13.9% . This means that unobserved confounders that explain 13.9% of the residual variance both of the treatment and of the outcome are sufficiently strong to explain away all the observed effect. On the other hand, unobserved confounders that do not explain at least 13.9% of the residual variance both of the treatment and of the outcome are not sufficiently strong to do so.\n",
    "\n",
    "The robustness value for testing the null hypothesis that the coefficient of directlyharmed is zero $(RV_{q=1, \\alpha = 0.05})$ falls to 7.6%. This means that unobserved confounders that explain 7.6% of the residual variance both of the treatment and of the outcome are sufficiently strong to bring the lower bound of the confidence interval to zero (at the chosen significance level of 5%). On the other hand, unobserved confounders that do not explain at least 7.6% of the residual variance both of the treatment and of the outcome are not sufficiently strong to do so.\n",
    "\n",
    "Finally, the partial $R^2$ of directlyharmed with peacefactor means that, in an extreme scenario, in which we assume that unobserved confounders explain all of the left out variance of the outcome, these unobserved confounders would need to explain at least 2.2% of the residual variance of the treatment to fully explain away the observed effect.\n",
    "\n",
    "The lower corner of the table, further provides bounds on the strength of an unobserved confounder *as strong as* the observed covariate `female`, resulting in $R^2_{Y\\sim Z\\mid X, D} = 12.5\\%$  and $R^2_{D\\sim Z\\mid X} = .9\\%$ . Since both of those are below the RV of 13.9\\%, we conclude confounders as strong as female, in explaining treatment and outcome variations, are not sufficiently strong to explain away the observed estimate.\n",
    "\n",
    "Moreover, the bound of $R^2_{D\\sim Z\\mid X} = .9\\%$ is below the partial 𝑅2 of the treatment with the outcome, $R^2_{Y\\sim D\\mid X} = 2.2\\%$, this means that even an extreme confounder explaining *all* residual variation of the outcome, and as strongly associated with the treatment as female would not be able to overturn the research conclusions."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The summary method of Sensemakr produces verbose output similar to the text explanations above, so that researchers can directly cite or include such texts in their reports."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Sensitivity Analysis to Unobserved Confounding\n",
      "\n",
      "Model Formula: peacefactor ~ directlyharmed + age + farmer_dar + herder_dar + pastvoted + hhsize_darfur + female + village\n",
      "\n",
      "Null hypothesis: q = 1 and reduce = True \n",
      "\n",
      "-- This means we are considering biases that reduce the absolute value of the current estimate.\n",
      "-- The null hypothesis deemed problematic is H0:tau = 0.0 \n",
      "\n",
      "Unadjusted Estimates of ' directlyharmed ':\n",
      "  Coef. estimate: 0.097\n",
      "  Standard Error: 0.023\n",
      "  t-value: 4.184 \n",
      "\n",
      "Sensitivity Statistics:\n",
      "  Partial R2 of treatment with outcome: 0.022\n",
      "  Robustness Value, q = 1 : 0.139\n",
      "  Robustness Value, q = 1 alpha = 0.05 : 0.076 \n",
      "\n",
      "Verbal interpretation of sensitivity statistics:\n",
      "\n",
      "-- Partial R2 of the treatment with the outcome: an extreme confounder (orthogonal to the covariates)  that explains 100% of the residual variance of the outcome, would need to explain at least 2.187 % of the residual variance of the treatment to fully account for the observed estimated effect.\n",
      "\n",
      "-- Robustness Value, q = 1 : unobserved confounders (orthogonal to the covariates) that  explain more than 13.878 % of the residual variance of both the treatment and the outcome are strong enough to bring the point estimate to 0.0 (a bias of 100.0 % of the original estimate). Conversely, unobserved confounders that do not explain more than 13.878 % of the residual variance of both the treatment and the outcome are not strong enough to bring the point estimate to 0.0 .\n",
      "\n",
      "-- Robustness Value, q = 1 , alpha = 0.05 : unobserved confounders (orthogonal to the covariates) that explain more than 7.626 % of the residual variance of both the treatment and the outcome are strong enough to bring the estimate to a range where it is no longer 'statistically different' from 0.0 (a bias of 100.0 % of the original estimate), at the significance level of alpha = 0.05 . Conversely, unobserved confounders that do not explain more than 7.626 % of the residual variance of both the treatment and the outcome are not strong enough to bring the estimate to a range where it is no longer 'statistically different' from 0.0 , at the significance level of alpha = 0.05 .\n",
      "\n",
      "Bounds on omitted variable bias:\n",
      "--The table below shows the maximum strength of unobserved confounders with association with the treatment and the outcome bounded by a multiple of the observed explanatory power of the chosen benchmark covariate(s).\n",
      "\n",
      "  bound_label    r2dz_x   r2yz_dx       treatment  adjusted_estimate  \\\n",
      "0   1x female  0.009164  0.124641  directlyharmed           0.075220   \n",
      "1   2x female  0.018329  0.249324  directlyharmed           0.052915   \n",
      "2   3x female  0.027493  0.374050  directlyharmed           0.030396   \n",
      "\n",
      "   adjusted_se  adjusted_t  adjusted_lower_CI  adjusted_upper_CI  \n",
      "0     0.021873    3.438904           0.032283           0.118158  \n",
      "1     0.020350    2.600246           0.012968           0.092862  \n",
      "2     0.018670    1.628062          -0.006253           0.067045  \n"
     ]
    }
   ],
   "source": [
    "# extended summary\n",
    "darfur_sense.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sensitivity contour plots"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    " Using the plot method for `Sensemakr`, we can further refine our sensitivity analysis by *visually* exploring the whole range of possible estimates that confounders with different strengths could cause."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let us begin by examining contour plots for the point estimate.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# contour plot for the estimate\n",
    "darfur_sense.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The horizontal axis shows the hypothetical residual share of variation of the treatment that unobserved confounding explains, $R^2_{D\\sim Z| {\\bf X} }$. The vertical axis shows the hypothetical partial $R^2$ of unobserved confounding with the outcome, $R^2_{Y\\sim Z| {\\bf X}, D}$. The contours show what would be the estimate for `directlyharmed` that one would have obtained in the full regression model including unobserved confounders with such hypothetical strengths. Note the plot is parameterized in way that hurts our preferred hypothesis, by pulling the estimate towards zero---the direction of the bias was set in the argument `reduce = True` of `Sensemakr()`.\n",
    "\n",
    "The bounds on the strength of confounding, determined by the parameter `kd = [1,2,3]` in the call for `Sensemakr()`, are also shown in the plot. Note that the plot reveals that the direction of the effect (positive) is robust to confounding once, twice or even three times as strong as the observed covariate `female`, although in this last case the magnitude of the effect is reduced to a third of the original estimate.\n",
    "\n",
    "We now examine the sensitivity of the *t-value* for testing the null hypothesis of zero effect. For this, it suffices to change the option `sensitivity_of = \"t-value\"`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x576 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# contour plot for t-value\n",
    "darfur_sense.plot(sensitivity_of = 't-value')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The plot reveals that, at the 5% significance level, the null hypothesis of zero effect would still be rejected given confounders once or twice as strong as `female`. However, by contrast to the point-estimate, accounting for sampling uncertainty now means that the null hypothesis of zero effect *would not* be rejected with the inclusion of a confounder three times as strong as `female`. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sensitivity to extreme scenarios"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Sometimes researchers may be better equipped to make plausibility judgments about the strength of determinants of the treatment assignment mechanism, and have less knowledge about the determinants of the outcome. In those cases, sensitivity plots using *extreme scenarios* are a useful option. These are produced with the option `plot_type = extreme`. Here one assumes confounding explains **all** or some large fraction of the residual variance of the outcome, then vary how strongly such confounding is hypothetically related to the treatment, to see how this affects the resulting point estimate."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 768x460.8 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# extreme scenarios plot\n",
    "darfur_sense.plot(plot_type = 'extreme')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This extreme scenarios plot sets the association of confounders with the outcome to  $R^2_{Y\\sim Z| {\\bf X}, D}$=100%,  $R^2_{Y\\sim Z| {\\bf X}, D}$=75%  and  $R^2_{Y\\sim Z| {\\bf X}, D}$=50% (producing three separate curves). The bounds on the strength of association of a confounder once, twice or three times as strongly associated with the treatment as `female` are shown as red ticks in the horizontal axis.  As the plot shows, even in the most extreme case of $R^2_{Y\\sim Z| {\\bf X}, D}$=100%, confounders would need to be more than twice as strongly associated with the treatment to fully explain away the point estimate. Moving to  the scenarios $R^2_{Y\\sim Z| {\\bf X}, D}$=75%  and  $R^2_{Y\\sim Z| {\\bf X}, D}$=50%, confounders would need to be more than three times as strongly associated with the treatment as was female in order to fully explain away the point estimate."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Going further\n",
    "The basic functionality demonstrated here will likely suffice for most users, most of the time. Sometimes, however, more flexibility will be needed in a given project. When this happens, researchers may resort directly to the functions defined in the other modules of the package. Those functions can be found in the Modules documentation, and we also provide some examples of how they can be used in the next notebook."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## References\n",
    "Cinelli, C. Hazlett, C. (2020) “Making Sense of Sensitivity: Extending Omitted Variable Bias”. Journal of the Royal Statistical Society, Series B (Statistical Methodology).\n",
    "\n",
    "Hazlett, C. (2019). Angry or Weary? How Violence Impacts Attitudes toward Peace among Darfurian Refugees. Journal of Conflict Resolution."
   ]
  }
 ],
 "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": "3.9.7"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": true,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}