{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Impatient Robinson"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Up to now, we have implicitly assumed Robinson to be forward-looking with respect to his intertemporal preferences, such that he maximizes the expected present value of utility over the remaining lifetime according to\n",
    "\n",
    "$$\n",
    "    U_t(u_t, u_{t+1}, ...) \\equiv \\sum^{T}_{t=0}\n",
    "            {\\delta^{t}u_t}\n",
    "$$\n",
    "\n",
    "where $\\delta \\in (0,1]$ is the usual standard discount factor representing time-consistent preferences. With **respy** you can solve a discrete choice dynamic programming model for a (completely naïve) agent with time-inconsistent preferences just as easily. \n",
    "\n",
    "We represent time-inconsistency with the popular formulation by O’Donoghue and Rabin (1999): ($\\beta$-$\\delta$) preferences, defined as\n",
    "\n",
    "\n",
    "$$\n",
    "    U_t(u_t, u_{t+1}, ...) \\equiv u_t + \\beta \\sum^{T}_{k=t+1}\n",
    "            {\\delta^{k-t}u_k}\n",
    "$$\n",
    "\n",
    "where $\\beta \\in (0, 1]$ is the present-bias factor that captures time-inconsistent discounting, or impatience; the tendency to prefer activities that are immediately rewarded while procrastinating those that require an immediate cost. If $\\beta = 1$ we are back to the time-consistent case.\n",
    "\n",
    "In this tutorial, we will see how to model the behavior of an impatient Robinson who is additionally completely naïve with respect to his own time preferences, that is, at each point in time believes he will act time-consistently in future periods."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib agg\n",
    "\n",
    "import io\n",
    "import yaml\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "import respy as rp\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Specifications"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To represent Robinson's impatience, we just need to add ``\"beta\"`` to the string containing the parameters and specifications of the model. ``\"beta\"`` is by default equal to 1 (time-consistent discounting). Here we set it to 0.4:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "params_beta = \"\"\"\n",
    "category,name,value\n",
    "beta,beta, 0.4\n",
    "delta,delta,0.95\n",
    "wage_fishing,exp_fishing,0.1\n",
    "nonpec_fishing,constant,-1\n",
    "nonpec_hammock,constant,2.5\n",
    "nonpec_hammock,not_fishing_last_period,-1\n",
    "shocks_sdcorr,sd_fishing,1\n",
    "shocks_sdcorr,sd_hammock,1\n",
    "shocks_sdcorr,corr_hammock_fishing,-0.2\n",
    "lagged_choice_1_hammock,constant,1\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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></th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>category</th>\n",
       "      <th>name</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>beta</th>\n",
       "      <th>beta</th>\n",
       "      <td>0.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>delta</th>\n",
       "      <th>delta</th>\n",
       "      <td>0.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>wage_fishing</th>\n",
       "      <th>exp_fishing</th>\n",
       "      <td>0.10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>nonpec_fishing</th>\n",
       "      <th>constant</th>\n",
       "      <td>-1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"2\" valign=\"top\">nonpec_hammock</th>\n",
       "      <th>constant</th>\n",
       "      <td>2.50</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>not_fishing_last_period</th>\n",
       "      <td>-1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">shocks_sdcorr</th>\n",
       "      <th>sd_fishing</th>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>sd_hammock</th>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>corr_hammock_fishing</th>\n",
       "      <td>-0.20</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>lagged_choice_1_hammock</th>\n",
       "      <th>constant</th>\n",
       "      <td>1.00</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                 value\n",
       "category                name                          \n",
       "beta                    beta                      0.40\n",
       "delta                   delta                     0.95\n",
       "wage_fishing            exp_fishing               0.10\n",
       "nonpec_fishing          constant                 -1.00\n",
       "nonpec_hammock          constant                  2.50\n",
       "                        not_fishing_last_period  -1.00\n",
       "shocks_sdcorr           sd_fishing                1.00\n",
       "                        sd_hammock                1.00\n",
       "                        corr_hammock_fishing     -0.20\n",
       "lagged_choice_1_hammock constant                  1.00"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "params_beta = pd.read_csv(io.StringIO(params_beta), index_col=[\"category\", \"name\"])\n",
    "params_beta"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this tutorial, we will compare the behavior of:\n",
    "\n",
    "1. A time-consistent Robinson (``\"beta\"``= 1)\n",
    "2. An impatient Robinson (``\"beta\"`` = 0.4)\n",
    "3. A very impatient Robinson (``\"beta\"`` = 0.05)\n",
    "\n",
    "Therefore, we will need two additional sets of ``params``."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set of parameters for time-consistent Robinson (as beta is read by default as 1)\n",
    "params = params_beta.drop(labels=\"beta\", level=\"category\")\n",
    "\n",
    "# Set of parameters for very impatient Robinson\n",
    "params_lowbeta = params_beta.copy()\n",
    "params_lowbeta.loc[(\"beta\", \"beta\"), \"value\"] = 0.05"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We complement ``\"params\"`` with the ``options`` specifications:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "options = \"\"\"n_periods: 10\n",
    "estimation_draws: 200\n",
    "estimation_seed: 500\n",
    "estimation_tau: 0.001\n",
    "interpolation_points: -1\n",
    "simulation_agents: 1_000\n",
    "simulation_seed: 132\n",
    "solution_draws: 500\n",
    "solution_seed: 456\n",
    "covariates:\n",
    "    constant: \"1\"\n",
    "    not_fishing_last_period: \"lagged_choice_1 != 'fishing'\"\n",
    "core_state_space_filters:\n",
    "  # If Robinson has always been fishing, the previous choice cannot be 'hammock'.\n",
    "  - period > 0 and exp_fishing == period and lagged_choice_1 == 'hammock'\n",
    "  # If experience in fishing is zero, previous choice cannot be fishing.\n",
    "  - exp_fishing == 0 and lagged_choice_1 == 'fishing'\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'n_periods': 10,\n",
       " 'estimation_draws': 200,\n",
       " 'estimation_seed': 500,\n",
       " 'estimation_tau': 0.001,\n",
       " 'interpolation_points': -1,\n",
       " 'simulation_agents': 1000,\n",
       " 'simulation_seed': 132,\n",
       " 'solution_draws': 500,\n",
       " 'solution_seed': 456,\n",
       " 'covariates': {'constant': '1',\n",
       "  'not_fishing_last_period': \"lagged_choice_1 != 'fishing'\"},\n",
       " 'core_state_space_filters': [\"period > 0 and exp_fishing == period and lagged_choice_1 == 'hammock'\",\n",
       "  \"exp_fishing == 0 and lagged_choice_1 == 'fishing'\"]}"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "options = yaml.safe_load(options)\n",
    "options"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simulation "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Basic Model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We start by simulating the basic model for our three Robinsons."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Simulation for time-consistent Robinson\n",
    "simulate = rp.get_simulate_func(params, options)\n",
    "df = simulate(params)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Simulation for impatient Robinson\n",
    "simulate = rp.get_simulate_func(params_beta, options)\n",
    "df_beta = simulate(params_beta)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Simulation for very impatient Robinson\n",
    "simulate = rp.get_simulate_func(params_lowbeta, options)\n",
    "df_lowbeta = simulate(params_lowbeta)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can then compare their decisions period by period. The grouped stacked bar chart below and all the other visualizations can be easily generated with the ``Matplotlib`` library."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig = plt.figure(figsize=(12, 4))\n",
    "ax = fig.add_subplot()\n",
    "\n",
    "x = np.arange(10)\n",
    "\n",
    "bar_width = 0.25\n",
    "\n",
    "colors = [[\"#1f77b4\", \"#ff7f0e\"], [\"#428dc1\", \"#ff9833\"], [\"#70a8d0\", \"#ffb369\"]]\n",
    "labels = [\"β=1\", \"β=0.4\", \"β=0.05\"]\n",
    "positions = [x, x + bar_width * 1.2, x + bar_width * 2.4]\n",
    "\n",
    "for i, series in enumerate([df, df_beta, df_lowbeta]):\n",
    "    hammock = series.groupby(\"Period\").Choice.value_counts().unstack().loc[:, \"hammock\"]\n",
    "    fishing = series.groupby(\"Period\").Choice.value_counts().unstack().loc[:, \"fishing\"]\n",
    "    ax.bar(positions[i], fishing, width=bar_width, color=colors[i][0], label=labels[i])\n",
    "    ax.bar(\n",
    "        positions[i],\n",
    "        hammock,\n",
    "        width=bar_width,\n",
    "        bottom=fishing,\n",
    "        color=colors[i][1],\n",
    "        label=labels[i],\n",
    "    )\n",
    "\n",
    "ax.set_xticks(x + 2 * bar_width / 2)\n",
    "ax.set_xticklabels(np.arange(10))\n",
    "ax.set_xlabel(\"Periods\")\n",
    "\n",
    "handles, _ = ax.get_legend_handles_labels()\n",
    "handles_positions = [[0, 2, 4], [1, 3, 5]]\n",
    "bbox_to_anchor = [(1.12, 0.5), (1.12, 0.8)]\n",
    "\n",
    "for i, title in enumerate([\"fishing\", \"hammock\"]):\n",
    "    legend = plt.legend(\n",
    "        handles=list(handles[j] for j in handles_positions[i]),\n",
    "        ncol=1,\n",
    "        bbox_to_anchor=bbox_to_anchor[i],\n",
    "        title=title,\n",
    "        frameon=False,\n",
    "    )\n",
    "    plt.gca().add_artist(legend)\n",
    "\n",
    "fig.suptitle(\"Robinson's choices\", y=0.95);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1200x400 with 1 Axes>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fig"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can see that the impatient Robinsons is less likely to go fishing than the time-consistent Robinson in each period, but even a very impatient Robinson will spend at least two periods fishing.\n",
    "\n",
    "We can also compare the behavior of the Robinsons for different returns to experience. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Specification of grid for evaluation\n",
    "n_points = 15\n",
    "grid_start = 0\n",
    "grid_stop = 0.3\n",
    "\n",
    "grid_points = np.linspace(grid_start, grid_stop, n_points)\n",
    "\n",
    "mean_max_exp_fishing_by_beta = []\n",
    "for par in [params, params_beta, params_lowbeta]:\n",
    "    p = par.copy()\n",
    "    mean_max_exp_fishing = []\n",
    "    for value in grid_points:\n",
    "        p.loc[\"wage_fishing\", \"exp_fishing\"] = value\n",
    "        df = simulate(p)\n",
    "        stat = df.groupby(\"Identifier\")[\"Experience_Fishing\"].max().mean()\n",
    "        mean_max_exp_fishing.append(stat)\n",
    "    mean_max_exp_fishing_by_beta.append(mean_max_exp_fishing)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, ax = plt.subplots(figsize=(8, 6))\n",
    "labels = [\"β=1\", \"β=0.4\", \"β=0.05\"]\n",
    "\n",
    "for mean_max_exp_fishing, label in zip(mean_max_exp_fishing_by_beta, labels):\n",
    "    plt.plot(grid_points, mean_max_exp_fishing, label=label)\n",
    "\n",
    "plt.ylim([0, 10])\n",
    "plt.xlabel(\"Return to experience\")\n",
    "plt.ylabel(\"Average final level of experience\")\n",
    "\n",
    "plt.legend();"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fig"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For the same return to experience, time-inconsistent Robinsons attain lower average level of final experience, with the behavior of the very impatient Robinson obviously being the least reactive to an increasing return of experience.\n",
    "\n",
    "We've seen that an impatient agent heavily discounts the stream of utility from future periods. A completely myopic agent, whose preferences are represented by a ``\"delta\"`` equal to 0, does not put any weight on his future utility. We may wonder whether having a very degree of impatience, represented by a very low ``\"beta\"``, may be equivalent to being completely myopic."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Set of parameters for myopic Robinson\n",
    "params_myopic = params.copy()\n",
    "params_myopic.loc[(\"delta\", \"delta\"), \"value\"] = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Simulation for myopic Robinson\n",
    "simulate = rp.get_simulate_func(params_myopic, options)\n",
    "df_myopic = simulate(params_myopic)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, axs = plt.subplots(1, 2, figsize=(12, 4))\n",
    "\n",
    "df_myopic.groupby(\"Period\").Choice.value_counts().unstack().plot.bar(\n",
    "    ax=axs[0], stacked=True, rot=0, legend=False, title=\"Completely myiopic\"\n",
    ")\n",
    "df_lowbeta.groupby(\"Period\").Choice.value_counts().unstack().plot.bar(\n",
    "    ax=axs[1], stacked=True, rot=0, title=\"With present bias (β=0.05)\"\n",
    ")\n",
    "\n",
    "handles, _ = axs[0].get_legend_handles_labels()\n",
    "axs[1].get_legend().remove()\n",
    "fig.legend(handles=handles, loc=\"lower center\", bbox_to_anchor=(0.5, 0), ncol=3)\n",
    "fig.suptitle(\"Robinson's choices\", fontsize=14, y=1.05)\n",
    "\n",
    "plt.tight_layout(rect=[0, 0.05, 1, 1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fig"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can see that the behavior of the two Robinsons appear to be identical, despite present-biased Robinson having a long-run discount factor close to 1."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Extended Model "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's see what happens in the extended model. Remember that the extended model includes the additional covariate ``\"contemplation_with_friday\"``, a choice available once, starting from the third period, and only if Robinson has been fishing before. Remember that choosing to interact with Friday enters Robinson's utility negatively, reflecting the effort costs of learning and the food penalty.\n",
    "\n",
    "This time we compare the behavior of a time-consistent Robinson with that of a time-inconsistent Robinson with ``\"beta\"`` = 0.4.\n",
    "First, we load the model's options and parameters:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "params_ext, options_ext = rp.get_example_model(\n",
    "    \"robinson_crusoe_extended\", with_data=False\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Then, we create another set of parameters for impatient Robinson, which differs from the previous one only in the value of ``\"beta\"``:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "index = pd.MultiIndex.from_tuples([(\"beta\", \"beta\")], names=[\"category\", \"name\"])\n",
    "beta = pd.DataFrame(0.4, index=index, columns=[\"value\"])\n",
    "params_beta_ext = beta.append(params_ext)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Again, we simulate the model for time-consistent and for impatient Robinson:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulate = rp.get_simulate_func(params_ext, options_ext)\n",
    "df_ext = simulate(params_ext)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "simulate = rp.get_simulate_func(params_beta_ext, options_ext)\n",
    "df_beta_ext = simulate(params_beta_ext)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We are now ready to compare Robinsons' choices period by period."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "fig, axs = plt.subplots(1, 2, figsize=(12, 4))\n",
    "\n",
    "df_ext.groupby(\"Period\").Choice.value_counts().unstack().plot.bar(\n",
    "    ax=axs[0],\n",
    "    stacked=True,\n",
    "    rot=0,\n",
    "    legend=False,\n",
    "    title=\"Without present bias\",\n",
    "    color=[\"C0\", \"C2\", \"C1\"],\n",
    ")\n",
    "df_beta_ext.groupby(\"Period\").Choice.value_counts().unstack().plot.bar(\n",
    "    ax=axs[1],\n",
    "    stacked=True,\n",
    "    rot=0,\n",
    "    title=\"With present bias (β=0.4)\",\n",
    "    color=[\"C0\", \"C2\", \"C1\"],\n",
    ")\n",
    "\n",
    "handles, _ = axs[0].get_legend_handles_labels()\n",
    "axs[1].get_legend().remove()\n",
    "fig.legend(handles=handles, loc=\"lower center\", bbox_to_anchor=(0.5, 0), ncol=3)\n",
    "fig.suptitle(\"Robinson's choices\", fontsize=14, y=1.05)\n",
    "\n",
    "plt.tight_layout(rect=[0, 0.05, 1, 1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fig"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Unsurprisingly, a Robinson who's a completely naïve, time-incosistent discounter is unlikely to interact with Friday, who would teach him how to fish but affect Robinson's utility negatively in that period. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## References\n",
    "\n",
    "> O'Donoghue, T. and and Rabin, M. (1999). [Doing It Now or Later](https://doi.org/10.1257/aer.89.1.103). *American Economic Review*, 89(1): 103-124."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}