{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# The Left Handed Sister Problem"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": [
     "remove-cell"
    ]
   },
   "source": [
    "Think Bayes, Second Edition\n",
    "\n",
    "Copyright 2021 Allen B. Downey\n",
    "\n",
    "License: [Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Suppose you meet someone who looks like the brother of your friend Mary. \n",
    "You ask if he has a sister named Mary, and he says \"Yes I do, but I don't think I know you.\"\n",
    "\n",
    "You remember that Mary has a sister who is left-handed, but you don't remember her name.\n",
    "So you ask your new friend if he has another sister who is left-handed.\n",
    "\n",
    "If he does, how much evidence does that provide that he is the brother of your friend, rather than a random person who coincidentally has a sister named Mary and another sister who is left-handed. In other words, what is the Bayes factor of the left-handed sister?\n",
    "\n",
    "Let's assume:\n",
    "\n",
    "* Out of 100 families with children, 20 have one child, 30 have two children, 40 have three children, and 10 have four children.\n",
    "\n",
    "* All children are either boys or girls with equal probability, one girl in 10 is left-handed, and one girl in 100 is named Mary.\n",
    "\n",
    "* Name, sex, and handedness are independent, so every child has the same probability of being a girl, left-handed, or named Mary.\n",
    "\n",
    "* If the person you met had more than one sister named Mary, he would have said so, but he could have more than one sister who is left handed."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Constructing the prior\n",
    "\n",
    "I'll make a Pandas `Series` that enumerates possible families with 2, 3, or 4 children."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "qs = [(2, 0),\n",
    "      (1, 1),\n",
    "      (0, 2),\n",
    "      (3, 0),\n",
    "      (2, 1),\n",
    "      (1, 2),\n",
    "      (0, 3),\n",
    "      (4, 0),\n",
    "      (3, 1),\n",
    "      (2, 2),\n",
    "      (1, 3),\n",
    "      (0, 4),\n",
    "    ]\n",
    "index = pd.MultiIndex.from_tuples(qs, names=['Boys', 'Girls'])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To compute the proportion of each type of family, I'll use Scipy to compute the binomial distribution."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from scipy.stats import binom\n",
    "\n",
    "boys = index.to_frame()['Boys']\n",
    "girls = index.to_frame()['Girls']\n",
    "ps = binom.pmf(girls, boys+girls, 0.5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "And put the results into a Pandas `Series`."
   ]
  },
  {
   "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>Prior</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Boys</th>\n",
       "      <th>Girls</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>0</th>\n",
       "      <td>0.2500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>1</th>\n",
       "      <td>0.5000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>2</th>\n",
       "      <td>0.2500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>0</th>\n",
       "      <td>0.1250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>1</th>\n",
       "      <td>0.3750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <td>0.3750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>3</th>\n",
       "      <td>0.1250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <th>0</th>\n",
       "      <td>0.0625</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>1</th>\n",
       "      <td>0.2500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>2</th>\n",
       "      <td>0.3750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>3</th>\n",
       "      <td>0.2500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>4</th>\n",
       "      <td>0.0625</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Prior\n",
       "Boys Girls        \n",
       "2    0      0.2500\n",
       "1    1      0.5000\n",
       "0    2      0.2500\n",
       "3    0      0.1250\n",
       "2    1      0.3750\n",
       "1    2      0.3750\n",
       "0    3      0.1250\n",
       "4    0      0.0625\n",
       "3    1      0.2500\n",
       "2    2      0.3750\n",
       "1    3      0.2500\n",
       "0    4      0.0625"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prior1 = pd.Series(ps, index, name='Prior')\n",
    "pd.DataFrame(prior1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "But we also have the information frequencies of these families are proportional to 30%, 40%, and 10%, so we can multiply through."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "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>Prior</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Boys</th>\n",
       "      <th>Girls</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>0</th>\n",
       "      <td>7.500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>1</th>\n",
       "      <td>15.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>2</th>\n",
       "      <td>7.500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>0</th>\n",
       "      <td>5.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>1</th>\n",
       "      <td>15.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <td>15.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>3</th>\n",
       "      <td>5.000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <th>0</th>\n",
       "      <td>0.625</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>1</th>\n",
       "      <td>2.500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>2</th>\n",
       "      <td>3.750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>3</th>\n",
       "      <td>2.500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>4</th>\n",
       "      <td>0.625</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Prior\n",
       "Boys Girls        \n",
       "2    0       7.500\n",
       "1    1      15.000\n",
       "0    2       7.500\n",
       "3    0       5.000\n",
       "2    1      15.000\n",
       "1    2      15.000\n",
       "0    3       5.000\n",
       "4    0       0.625\n",
       "3    1       2.500\n",
       "2    2       3.750\n",
       "1    3       2.500\n",
       "0    4       0.625"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ps = [30, 30, 30, 40, 40, 40, 40, 10, 10, 10, 10, 10]\n",
    "\n",
    "prior1 *= ps\n",
    "pd.DataFrame(prior1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "So that's the (unnormalized) prior.\n",
    "\n",
    "I'll use the following function to do Bayesian updates."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "def make_table(prior, likelihood):\n",
    "    \"\"\"Make a DataFrame representing a Bayesian update.\"\"\"\n",
    "    table = pd.DataFrame(prior)\n",
    "    table.columns = ['Prior']\n",
    "    table['Likelihood'] = likelihood\n",
    "    table['Product'] = (table['Prior'] * table['Likelihood'])\n",
    "    total = table['Product'].sum()\n",
    "    table['Posterior'] = table['Product'] / total\n",
    "    return table"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This function takes a prior and a likelihood and returns a `DataFrame`"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The first update\n",
    "\n",
    "Due to [length-biased sampling](https://towardsdatascience.com/the-inspection-paradox-is-everywhere-2ef1c2e9d709), the person you met is more likely to come from family with more boys.\n",
    "Specifically, the likelihood of meeting someone from a family with $n$ boys is proportional to $n$."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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>Prior</th>\n",
       "      <th>Likelihood</th>\n",
       "      <th>Product</th>\n",
       "      <th>Posterior</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Boys</th>\n",
       "      <th>Girls</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>0</th>\n",
       "      <td>7.500</td>\n",
       "      <td>2</td>\n",
       "      <td>15.0</td>\n",
       "      <td>0.136364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>1</th>\n",
       "      <td>15.000</td>\n",
       "      <td>1</td>\n",
       "      <td>15.0</td>\n",
       "      <td>0.136364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>2</th>\n",
       "      <td>7.500</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>0</th>\n",
       "      <td>5.000</td>\n",
       "      <td>3</td>\n",
       "      <td>15.0</td>\n",
       "      <td>0.136364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>1</th>\n",
       "      <td>15.000</td>\n",
       "      <td>2</td>\n",
       "      <td>30.0</td>\n",
       "      <td>0.272727</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <td>15.000</td>\n",
       "      <td>1</td>\n",
       "      <td>15.0</td>\n",
       "      <td>0.136364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>3</th>\n",
       "      <td>5.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <th>0</th>\n",
       "      <td>0.625</td>\n",
       "      <td>4</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.022727</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>1</th>\n",
       "      <td>2.500</td>\n",
       "      <td>3</td>\n",
       "      <td>7.5</td>\n",
       "      <td>0.068182</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>2</th>\n",
       "      <td>3.750</td>\n",
       "      <td>2</td>\n",
       "      <td>7.5</td>\n",
       "      <td>0.068182</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>3</th>\n",
       "      <td>2.500</td>\n",
       "      <td>1</td>\n",
       "      <td>2.5</td>\n",
       "      <td>0.022727</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>4</th>\n",
       "      <td>0.625</td>\n",
       "      <td>0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             Prior  Likelihood  Product  Posterior\n",
       "Boys Girls                                        \n",
       "2    0       7.500           2     15.0   0.136364\n",
       "1    1      15.000           1     15.0   0.136364\n",
       "0    2       7.500           0      0.0   0.000000\n",
       "3    0       5.000           3     15.0   0.136364\n",
       "2    1      15.000           2     30.0   0.272727\n",
       "1    2      15.000           1     15.0   0.136364\n",
       "0    3       5.000           0      0.0   0.000000\n",
       "4    0       0.625           4      2.5   0.022727\n",
       "3    1       2.500           3      7.5   0.068182\n",
       "2    2       3.750           2      7.5   0.068182\n",
       "1    3       2.500           1      2.5   0.022727\n",
       "0    4       0.625           0      0.0   0.000000"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "likelihood1 = prior1.index.to_frame()['Boys']\n",
    "table1 = make_table(prior1, likelihood1)\n",
    "table1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "So that's what we should believe about the family after the first update."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The second update\n",
    "\n",
    "The likelihood that a person has exactly one sister named Mary is given by the binomial distribution where `n` is the number of girls in the family and `p` is the probability that a girl is named Mary."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.        , 0.01      , 0.0198    , 0.        , 0.01      ,\n",
       "       0.0198    , 0.029403  , 0.        , 0.01      , 0.0198    ,\n",
       "       0.029403  , 0.03881196])"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from scipy.stats import binom\n",
    "\n",
    "ns = prior1.index.to_frame()['Girls']\n",
    "p = 1 / 100\n",
    "k = 1\n",
    "\n",
    "likelihood2 = binom.pmf(k, ns, p)\n",
    "likelihood2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here's the second update."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>Prior</th>\n",
       "      <th>Likelihood</th>\n",
       "      <th>Product</th>\n",
       "      <th>Posterior</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Boys</th>\n",
       "      <th>Girls</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>0</th>\n",
       "      <td>0.136364</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>1</th>\n",
       "      <td>0.136364</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>0.001364</td>\n",
       "      <td>0.143677</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>2</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.019800</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>0</th>\n",
       "      <td>0.136364</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>1</th>\n",
       "      <td>0.272727</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>0.002727</td>\n",
       "      <td>0.287354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <td>0.136364</td>\n",
       "      <td>0.019800</td>\n",
       "      <td>0.002700</td>\n",
       "      <td>0.284481</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>3</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.029403</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <th>0</th>\n",
       "      <td>0.022727</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>1</th>\n",
       "      <td>0.068182</td>\n",
       "      <td>0.010000</td>\n",
       "      <td>0.000682</td>\n",
       "      <td>0.071839</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>2</th>\n",
       "      <td>0.068182</td>\n",
       "      <td>0.019800</td>\n",
       "      <td>0.001350</td>\n",
       "      <td>0.142240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>3</th>\n",
       "      <td>0.022727</td>\n",
       "      <td>0.029403</td>\n",
       "      <td>0.000668</td>\n",
       "      <td>0.070409</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>4</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.038812</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               Prior  Likelihood   Product  Posterior\n",
       "Boys Girls                                           \n",
       "2    0      0.136364    0.000000  0.000000   0.000000\n",
       "1    1      0.136364    0.010000  0.001364   0.143677\n",
       "0    2      0.000000    0.019800  0.000000   0.000000\n",
       "3    0      0.136364    0.000000  0.000000   0.000000\n",
       "2    1      0.272727    0.010000  0.002727   0.287354\n",
       "1    2      0.136364    0.019800  0.002700   0.284481\n",
       "0    3      0.000000    0.029403  0.000000   0.000000\n",
       "4    0      0.022727    0.000000  0.000000   0.000000\n",
       "3    1      0.068182    0.010000  0.000682   0.071839\n",
       "2    2      0.068182    0.019800  0.001350   0.142240\n",
       "1    3      0.022727    0.029403  0.000668   0.070409\n",
       "0    4      0.000000    0.038812  0.000000   0.000000"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prior2 = table1['Posterior']\n",
    "table2 = make_table(prior2, likelihood2)\n",
    "table2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Based on the sister named Mary, we can rule out families with no girls, and families with more than one girls are more likely."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Probability of a left-handed sister\n",
    "\n",
    "Finally, we can compute the probability that he has at least one left-handed sister.\n",
    "The likelihood comes from the binomial distribution again, where `n` is the number of *additional* sisters, and we use the survival function to compute the probability that one or more are left-handed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "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>Additional sisters</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Boys</th>\n",
       "      <th>Girls</th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>2</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>3</th>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>4</th>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "            Additional sisters\n",
       "Boys Girls                    \n",
       "2    0                       0\n",
       "1    1                       0\n",
       "0    2                       1\n",
       "3    0                       0\n",
       "2    1                       0\n",
       "1    2                       1\n",
       "0    3                       2\n",
       "4    0                       0\n",
       "3    1                       0\n",
       "2    2                       1\n",
       "1    3                       2\n",
       "0    4                       3"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ns = prior1.index.to_frame()['Girls'] - 1\n",
    "ns.name = 'Additional sisters'\n",
    "neg = (ns < 0)\n",
    "ns[neg] = 0\n",
    "pd.DataFrame(ns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.   , 0.   , 0.1  , 0.   , 0.   , 0.1  , 0.19 , 0.   , 0.   ,\n",
       "       0.1  , 0.19 , 0.271])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "p = 1 / 10\n",
    "k = 1\n",
    "\n",
    "likelihood3 = binom.sf(k-1, ns, p)\n",
    "likelihood3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A convenient way to compute the total probability of an outcome is to do an update as if it happened, ignore the posterior probabilities, and compute the sum of the products. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>Prior</th>\n",
       "      <th>Likelihood</th>\n",
       "      <th>Product</th>\n",
       "      <th>Posterior</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Boys</th>\n",
       "      <th>Girls</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>0</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>1</th>\n",
       "      <td>0.143677</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>2</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.100</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>0</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>1</th>\n",
       "      <td>0.287354</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <td>0.284481</td>\n",
       "      <td>0.100</td>\n",
       "      <td>0.028448</td>\n",
       "      <td>0.507550</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>3</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.190</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <th>0</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <th>1</th>\n",
       "      <td>0.071839</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <th>2</th>\n",
       "      <td>0.142240</td>\n",
       "      <td>0.100</td>\n",
       "      <td>0.014224</td>\n",
       "      <td>0.253775</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <th>3</th>\n",
       "      <td>0.070409</td>\n",
       "      <td>0.190</td>\n",
       "      <td>0.013378</td>\n",
       "      <td>0.238675</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <th>4</th>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.271</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               Prior  Likelihood   Product  Posterior\n",
       "Boys Girls                                           \n",
       "2    0      0.000000       0.000  0.000000   0.000000\n",
       "1    1      0.143677       0.000  0.000000   0.000000\n",
       "0    2      0.000000       0.100  0.000000   0.000000\n",
       "3    0      0.000000       0.000  0.000000   0.000000\n",
       "2    1      0.287354       0.000  0.000000   0.000000\n",
       "1    2      0.284481       0.100  0.028448   0.507550\n",
       "0    3      0.000000       0.190  0.000000   0.000000\n",
       "4    0      0.000000       0.000  0.000000   0.000000\n",
       "3    1      0.071839       0.000  0.000000   0.000000\n",
       "2    2      0.142240       0.100  0.014224   0.253775\n",
       "1    3      0.070409       0.190  0.013378   0.238675\n",
       "0    4      0.000000       0.271  0.000000   0.000000"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "prior3 = table2['Posterior']\n",
    "table3 = make_table(prior3, likelihood3)\n",
    "table3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "At this point, there are only three family types left standing, (1,2), (2,2), and (1,3).\n",
    "\n",
    "Here's the total probability that your new friend has a left-handed sister."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0560498128605398"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "p = table3['Product'].sum()\n",
    "p"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## The Bayes factor\n",
    "\n",
    "If your interlocutor is the brother of your friend, the probability is 1 that he has a left-handed sister.\n",
    "If he is not the brother of your friend, the probability is `p`.\n",
    "So the Bayes factor is the ratio of these probabilities."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "17.841272770850235"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "1/p"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This might be the hardest Bayesian puzzle I've created.\n",
    "In fact, I got it wrong the first time, until [Aubrey Clayton convinced me](https://twitter.com/aubreyclayton/status/1420041376377475075) I needed to take into account the number of boys and girls in each family, not just the size.\n",
    "He solved the problem by enumerating the possible families in a giant spreadsheet!\n",
    "So the fact that we get the same answer gives me more confidence it is correct.\n",
    "\n",
    "Thanks to Aubrey and the other folks on Twitter who submitted answers, including \n",
    "[Corey Yanofsky](https://twitter.com/Corey_Yanofsky/status/1418627294256582664) and\n",
    "[Michal Haltuf](https://twitter.com/MichalHaltuf/status/1418685902717693952).\n",
    "\n",
    "If you like this puzzle, you might like the [new second edition of *Think Bayes*](https://thinkbayes.com)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "celltoolbar": "Tags",
  "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}