{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "\n",
    "from matplotlib import pyplot as plt\n",
    "from lifelines import CoxPHFitter\n",
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Testing the proportional hazard assumptions\n",
    "\n",
    "This Jupyter notebook is a small tutorial on how to test and fix proportional hazard problems. An important question to first ask is: [_do I need to care about the proportional hazard assumption?_](#Do-I-need-to-care-about-the-proportional-hazard-assumption?) - often the answer is no. \n",
    "\n",
    "The proportional hazard assumption is that _all_ individuals have the same hazard function, but a unique scaling factor infront. So the _shape_ of the hazard function is the same for all individuals, and only a scalar multiple changes per individual. \n",
    "\n",
    "$$h_i(t) = a_i h(t)$$\n",
    "\n",
    "At the core of the assumption is that $a_i$ is not time varying, that is, $a_i(t) = a_i$. Further more, if we take the ratio of this with another subject (called the hazard ratio): \n",
    "\n",
    "$$\\frac{h_i(t)}{h_j(t)} = \\frac{a_i h(t)}{a_j h(t)} = \\frac{a_i}{a_j}$$\n",
    "\n",
    "is constant for all $t$. In this tutorial we will test this non-time varying assumption, and look at ways to handle violations. \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<lifelines.CoxPHFitter: fitted with 432 total observations, 318 right-censored observations>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from lifelines.datasets import load_rossi\n",
    "rossi = load_rossi()\n",
    "cph = CoxPHFitter()\n",
    "\n",
    "cph.fit(rossi, 'week', 'arrest')"
   ]
  },
  {
   "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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>lifelines.CoxPHFitter</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>duration col</th>\n",
       "      <td>'week'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>event col</th>\n",
       "      <td>'arrest'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>baseline estimation</th>\n",
       "      <td>breslow</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of observations</th>\n",
       "      <td>432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of events observed</th>\n",
       "      <td>114</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>partial log-likelihood</th>\n",
       "      <td>-658.748</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>time fit was run</th>\n",
       "      <td>2020-03-23 15:17:18 UTC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>untransformed variables</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>coef</th>\n",
       "      <th>exp(coef)</th>\n",
       "      <th>se(coef)</th>\n",
       "      <th>coef lower 95%</th>\n",
       "      <th>coef upper 95%</th>\n",
       "      <th>exp(coef) lower 95%</th>\n",
       "      <th>exp(coef) upper 95%</th>\n",
       "      <th>z</th>\n",
       "      <th>p</th>\n",
       "      <th>-log2(p)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>fin</th>\n",
       "      <td>-0.379</td>\n",
       "      <td>0.684</td>\n",
       "      <td>0.191</td>\n",
       "      <td>-0.755</td>\n",
       "      <td>-0.004</td>\n",
       "      <td>0.470</td>\n",
       "      <td>0.996</td>\n",
       "      <td>-1.983</td>\n",
       "      <td>0.047</td>\n",
       "      <td>4.398</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>-0.057</td>\n",
       "      <td>0.944</td>\n",
       "      <td>0.022</td>\n",
       "      <td>-0.101</td>\n",
       "      <td>-0.014</td>\n",
       "      <td>0.904</td>\n",
       "      <td>0.986</td>\n",
       "      <td>-2.611</td>\n",
       "      <td>0.009</td>\n",
       "      <td>6.791</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>race</th>\n",
       "      <td>0.314</td>\n",
       "      <td>1.369</td>\n",
       "      <td>0.308</td>\n",
       "      <td>-0.290</td>\n",
       "      <td>0.918</td>\n",
       "      <td>0.748</td>\n",
       "      <td>2.503</td>\n",
       "      <td>1.019</td>\n",
       "      <td>0.308</td>\n",
       "      <td>1.698</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>wexp</th>\n",
       "      <td>-0.150</td>\n",
       "      <td>0.861</td>\n",
       "      <td>0.212</td>\n",
       "      <td>-0.566</td>\n",
       "      <td>0.266</td>\n",
       "      <td>0.568</td>\n",
       "      <td>1.305</td>\n",
       "      <td>-0.706</td>\n",
       "      <td>0.480</td>\n",
       "      <td>1.058</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mar</th>\n",
       "      <td>-0.434</td>\n",
       "      <td>0.648</td>\n",
       "      <td>0.382</td>\n",
       "      <td>-1.182</td>\n",
       "      <td>0.315</td>\n",
       "      <td>0.307</td>\n",
       "      <td>1.370</td>\n",
       "      <td>-1.136</td>\n",
       "      <td>0.256</td>\n",
       "      <td>1.965</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>paro</th>\n",
       "      <td>-0.085</td>\n",
       "      <td>0.919</td>\n",
       "      <td>0.196</td>\n",
       "      <td>-0.469</td>\n",
       "      <td>0.299</td>\n",
       "      <td>0.626</td>\n",
       "      <td>1.348</td>\n",
       "      <td>-0.434</td>\n",
       "      <td>0.665</td>\n",
       "      <td>0.589</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prio</th>\n",
       "      <td>0.091</td>\n",
       "      <td>1.096</td>\n",
       "      <td>0.029</td>\n",
       "      <td>0.035</td>\n",
       "      <td>0.148</td>\n",
       "      <td>1.036</td>\n",
       "      <td>1.159</td>\n",
       "      <td>3.194</td>\n",
       "      <td>0.001</td>\n",
       "      <td>9.476</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Concordance</th>\n",
       "      <td>0.640</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Log-likelihood ratio test</th>\n",
       "      <td>33.266 on 7 df</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>-log2(p) of ll-ratio test</th>\n",
       "      <td>15.370</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cph.print_summary(model=\"untransformed variables\", decimals=3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Checking assumptions with `check_assumptions`\n",
    "\n",
    "New to lifelines 0.16.0 is the `CoxPHFitter.check_assumptions` method. This method will compute statistics that check the proportional hazard assumption, produce plots to check assumptions, and more. Also included is an option to display advice to the console. Here's a breakdown of each information displayed:\n",
    "\n",
    " - Presented first are the results of a statistical test to test for any time-varying coefficients. A time-varying coefficient imply a covariate's influence _relative to the baseline_ changes over time. This implies a violation of the proportional hazard assumption. For each variable, we transform _time_ four times (these are common transformations of time to perform). If _lifelines_ rejects the null (that is, _lifelines_ rejects that the coefficient is not time-varying), we report this to the user.\n",
    " - Some advice is presented on how to correct the proportional hazard violation based on some summary statistics of the variable. \n",
    " - As a compliment to the above statistical test, for each variable that violates the PH assumption, visual plots of the the _scaled Schoenfeld residuals_ is presented against the four time transformations. A fitted lowess is also presented, along with 10 bootstrapped lowess lines (as an approximation to the confidence interval of the original lowess line). Ideally, this lowess line is constant (flat). Deviations away from the constant line are violations of the PH assumption. \n",
    " \n",
    "####  Why the _scaled Schoenfeld residuals_?\n",
    " \n",
    "This section can be skipped on first read. Let $s_{t,j}$ denote the scaled Schoenfeld residuals of variable $j$ at time $t$, $\\hat{\\beta_j}$ denote the maximum-likelihood estimate of the $j$th variable, and $\\beta_j(t)$ a time-varying coefficient in (fictional) alternative model that allows for time-varying coefficients. Therneau and Grambsch showed that. \n",
    "\n",
    "$$E[s_{t,j}] + \\hat{\\beta_j} = \\beta_j(t)$$\n",
    "\n",
    "The proportional hazard assumption implies that $\\hat{\\beta_j} = \\beta_j(t)$, hence $E[s_{t,j}] = 0$. This is what the above proportional hazard test is testing. Visually, plotting $s_{t,j}$ over time (or some transform of time), is a good way to see violations of $E[s_{t,j}] = 0$, along with the statisical test. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The ``p_value_threshold`` is set at 0.05. Even under the null hypothesis of no violations, some\n",
      "covariates will be below the threshold by chance. This is compounded when there are many covariates.\n",
      "Similarly, when there are lots of observations, even minor deviances from the proportional hazard\n",
      "assumption will be flagged.\n",
      "\n",
      "With that in mind, it's best to use a combination of statistical tests and visual tests to determine\n",
      "the most serious violations. Produce visual plots using ``check_assumptions(..., show_plots=True)``\n",
      "and looking for non-constant lines. See link [A] below for a full example.\n",
      "\n",
      "<lifelines.StatisticalResult>\n",
      "         test_name = proportional_hazard_test\n",
      " null_distribution = chi squared\n",
      "degrees_of_freedom = 1\n",
      "\n",
      "---\n",
      "           test_statistic      p  -log2(p)\n",
      "age  km             11.03 <0.005     10.12\n",
      "     rank           11.45 <0.005     10.45\n",
      "fin  km              0.02   0.89      0.17\n",
      "     rank            0.02   0.90      0.15\n",
      "mar  km              0.60   0.44      1.19\n",
      "     rank            0.71   0.40      1.32\n",
      "paro km              0.12   0.73      0.45\n",
      "     rank            0.13   0.71      0.49\n",
      "prio km              0.02   0.88      0.18\n",
      "     rank            0.02   0.89      0.17\n",
      "race km              1.44   0.23      2.12\n",
      "     rank            1.43   0.23      2.11\n",
      "wexp km              7.48   0.01      7.32\n",
      "     rank            7.31   0.01      7.19\n",
      "\n",
      "\n",
      "1. Variable 'age' failed the non-proportional test: p-value is 0.0007.\n",
      "\n",
      "   Advice 1: the functional form of the variable 'age' might be incorrect. That is, there may be\n",
      "non-linear terms missing. The proportional hazard test used is very sensitive to incorrect\n",
      "functional forms. See documentation in link [D] below on how to specify a functional form.\n",
      "\n",
      "   Advice 2: try binning the variable 'age' using pd.cut, and then specify it in `strata=['age',\n",
      "...]` in the call in `.fit`. See documentation in link [B] below.\n",
      "\n",
      "   Advice 3: try adding an interaction term with your time variable. See documentation in link [C]\n",
      "below.\n",
      "\n",
      "\n",
      "2. Variable 'wexp' failed the non-proportional test: p-value is 0.0063.\n",
      "\n",
      "   Advice: with so few unique values (only 2), you can include `strata=['wexp', ...]` in the call in\n",
      "`.fit`. See documentation in link [E] below.\n",
      "\n",
      "---\n",
      "[A]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html\n",
      "[B]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Bin-variable-and-stratify-on-it\n",
      "[C]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Introduce-time-varying-covariates\n",
      "[D]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Modify-the-functional-form\n",
      "[E]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Stratification\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 284,
       "width": 424
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 284,
       "width": 424
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "cph.check_assumptions(rossi, p_value_threshold=0.05, show_plots=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Alternatively, you can use the proportional hazard test outside of `check_assumptions`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<lifelines.StatisticalResult>\n",
      "         test_name = proportional_hazard_test\n",
      "    time_transform = rank\n",
      " null_distribution = chi squared\n",
      "degrees_of_freedom = 1\n",
      "             model = untransformed variables\n",
      "\n",
      "---\n",
      "      test_statistic     p  -log2(p)\n",
      "age           11.453 0.001    10.453\n",
      "fin            0.015 0.902     0.148\n",
      "mar            0.709 0.400     1.323\n",
      "paro           0.134 0.714     0.486\n",
      "prio           0.019 0.891     0.167\n",
      "race           1.426 0.232     2.106\n",
      "wexp           7.315 0.007     7.192\n"
     ]
    }
   ],
   "source": [
    "from lifelines.statistics import proportional_hazard_test\n",
    "\n",
    "results = proportional_hazard_test(cph, rossi, time_transform='rank')\n",
    "results.print_summary(decimals=3, model=\"untransformed variables\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Stratification\n",
    "\n",
    "\n",
    "In the advice above, we can see that `wexp` has small cardinality, so we can easily fix that by specifying it in the `strata`. What does the `strata` do? Let's go back to the proportional hazard assumption.\n",
    "\n",
    "In the introduction, we said that the proportional hazard assumption was that \n",
    "\n",
    "$$ h_i(t) = a_i h(t)$$\n",
    "\n",
    "In a simple case, it may be that there are two subgroups that have _very_ different baseline hazards. That is, we can split the dataset into subsamples based on some variable (we call this the stratifying variable), run the Cox model on all subsamples, and compare their baseline hazards. If these baseline hazards are _very_ different, then clearly the formula above is wrong - the $h(t)$ is some weighted average of the subgroups' baseline hazards. This ill fitting average baseline can cause $a_i$ to have time-dependent influence. A better model might be:\n",
    "\n",
    "$$ h_{i |i\\in G}(t) = a_i h_G(t)$$\n",
    "\n",
    "where now we have a unique baseline hazard _per_ subgroup $G$. Because of the way the Cox model is designed, inference of the coefficients is identical (expect now there are more baseline hazards, and no variation of the stratifying variable within a subgroup $G$). \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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>lifelines.CoxPHFitter</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>duration col</th>\n",
       "      <td>'week'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>event col</th>\n",
       "      <td>'arrest'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>strata</th>\n",
       "      <td>[wexp]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of observations</th>\n",
       "      <td>432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of events observed</th>\n",
       "      <td>114</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>partial log-likelihood</th>\n",
       "      <td>-580.89</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>time fit was run</th>\n",
       "      <td>2019-11-27 14:49:38 UTC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>wexp in strata</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>coef</th>\n",
       "      <th>exp(coef)</th>\n",
       "      <th>se(coef)</th>\n",
       "      <th>coef lower 95%</th>\n",
       "      <th>coef upper 95%</th>\n",
       "      <th>exp(coef) lower 95%</th>\n",
       "      <th>exp(coef) upper 95%</th>\n",
       "      <th>z</th>\n",
       "      <th>p</th>\n",
       "      <th>-log2(p)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>fin</th>\n",
       "      <td>-0.38</td>\n",
       "      <td>0.68</td>\n",
       "      <td>0.19</td>\n",
       "      <td>-0.76</td>\n",
       "      <td>-0.01</td>\n",
       "      <td>0.47</td>\n",
       "      <td>0.99</td>\n",
       "      <td>-1.99</td>\n",
       "      <td>0.05</td>\n",
       "      <td>4.42</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>-0.06</td>\n",
       "      <td>0.94</td>\n",
       "      <td>0.02</td>\n",
       "      <td>-0.10</td>\n",
       "      <td>-0.01</td>\n",
       "      <td>0.90</td>\n",
       "      <td>0.99</td>\n",
       "      <td>-2.64</td>\n",
       "      <td>0.01</td>\n",
       "      <td>6.91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>race</th>\n",
       "      <td>0.31</td>\n",
       "      <td>1.36</td>\n",
       "      <td>0.31</td>\n",
       "      <td>-0.30</td>\n",
       "      <td>0.91</td>\n",
       "      <td>0.74</td>\n",
       "      <td>2.49</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.32</td>\n",
       "      <td>1.65</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mar</th>\n",
       "      <td>-0.45</td>\n",
       "      <td>0.64</td>\n",
       "      <td>0.38</td>\n",
       "      <td>-1.20</td>\n",
       "      <td>0.29</td>\n",
       "      <td>0.30</td>\n",
       "      <td>1.34</td>\n",
       "      <td>-1.19</td>\n",
       "      <td>0.23</td>\n",
       "      <td>2.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>paro</th>\n",
       "      <td>-0.08</td>\n",
       "      <td>0.92</td>\n",
       "      <td>0.20</td>\n",
       "      <td>-0.47</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.63</td>\n",
       "      <td>1.35</td>\n",
       "      <td>-0.42</td>\n",
       "      <td>0.67</td>\n",
       "      <td>0.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prio</th>\n",
       "      <td>0.09</td>\n",
       "      <td>1.09</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.15</td>\n",
       "      <td>1.04</td>\n",
       "      <td>1.16</td>\n",
       "      <td>3.16</td>\n",
       "      <td>&lt;0.005</td>\n",
       "      <td>9.33</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Concordance</th>\n",
       "      <td>0.61</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Log-likelihood ratio test</th>\n",
       "      <td>23.77 on 6 df, -log2(p)=10.77</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "cph.fit(rossi, 'week', 'arrest', strata=['wexp'])\n",
    "cph.print_summary(model=\"wexp in strata\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The ``p_value_threshold`` is set at 0.01. Even under the null hypothesis of no violations, some\n",
      "covariates will be below the threshold by chance. This is compounded when there are many covariates.\n",
      "Similarly, when there are lots of observations, even minor deviances from the proportional hazard\n",
      "assumption will be flagged.\n",
      "\n",
      "With that in mind, it's best to use a combination of statistical tests and visual tests to determine\n",
      "the most serious violations. Produce visual plots using ``check_assumptions(..., show_plots=True)``\n",
      "and looking for non-constant lines. See link [A] below for a full example.\n",
      "\n",
      "<lifelines.StatisticalResult>\n",
      "         test_name = proportional_hazard_test\n",
      " null_distribution = chi squared\n",
      "degrees_of_freedom = 1\n",
      "\n",
      "---\n",
      "           test_statistic      p  -log2(p)\n",
      "age  km             11.29 <0.005     10.32\n",
      "     rank            4.62   0.03      4.99\n",
      "fin  km              0.02   0.90      0.16\n",
      "     rank            0.05   0.83      0.28\n",
      "mar  km              0.53   0.47      1.10\n",
      "     rank            1.31   0.25      1.99\n",
      "paro km              0.09   0.76      0.40\n",
      "     rank            0.00   0.97      0.05\n",
      "prio km              0.02   0.89      0.16\n",
      "     rank            0.02   0.90      0.16\n",
      "race km              1.47   0.23      2.15\n",
      "     rank            0.64   0.42      1.23\n",
      "\n",
      "\n",
      "1. Variable 'age' failed the non-proportional test: p-value is 0.0008.\n",
      "\n",
      "   Advice 1: the functional form of the variable 'age' might be incorrect. That is, there may be\n",
      "non-linear terms missing. The proportional hazard test used is very sensitive to incorrect\n",
      "functional forms. See documentation in link [D] below on how to specify a functional form.\n",
      "\n",
      "   Advice 2: try binning the variable 'age' using pd.cut, and then specify it in `strata=['age',\n",
      "...]` in the call in `.fit`. See documentation in link [B] below.\n",
      "\n",
      "   Advice 3: try adding an interaction term with your time variable. See documentation in link [C]\n",
      "below.\n",
      "\n",
      "\n",
      "---\n",
      "[A]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html\n",
      "[B]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Bin-variable-and-stratify-on-it\n",
      "[C]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Introduce-time-varying-covariates\n",
      "[D]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Modify-the-functional-form\n",
      "[E]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Stratification\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 284,
       "width": 424
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "cph.check_assumptions(rossi, show_plots=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Since `age` is still violating the proportional hazard assumption, we need to model it better.  From the residual plots above, we can see a the effect of age start to become negative over time. This will be relevant later. Below, we present three options to handle `age`. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Modify the functional form\n",
    "\n",
    "The proportional hazard test is very sensitive (i.e. lots of false positives) when the functional form of a variable is incorrect. For example, if the association between a covariate and the log-hazard is non-linear, but the model has only a linear term included, then the proportional hazard test can raise a false positive. \n",
    "\n",
    "The modeller can choose to add quadratic or cubic terms, i.e:\n",
    "```\n",
    "rossi['age**2'] = (rossi['age'] - rossi['age'].mean())**2\n",
    "rossi['age**3'] = (rossi['age'] - rossi['age'].mean())**3\n",
    "```\n",
    "\n",
    "but I think a more correct way to include non-linear terms is to use splines. Both Patsy and zEpid provide functionality for splines (tutorial incoming), but let's stick with the form above. \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "scrolled": false
   },
   "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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>lifelines.CoxPHFitter</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>duration col</th>\n",
       "      <td>'week'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>event col</th>\n",
       "      <td>'arrest'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>strata</th>\n",
       "      <td>[wexp]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of observations</th>\n",
       "      <td>432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of events observed</th>\n",
       "      <td>114</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>partial log-likelihood</th>\n",
       "      <td>-579.37</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>time fit was run</th>\n",
       "      <td>2019-11-27 14:49:39 UTC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>quad and cubic age terms</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>coef</th>\n",
       "      <th>exp(coef)</th>\n",
       "      <th>se(coef)</th>\n",
       "      <th>coef lower 95%</th>\n",
       "      <th>coef upper 95%</th>\n",
       "      <th>exp(coef) lower 95%</th>\n",
       "      <th>exp(coef) upper 95%</th>\n",
       "      <th>z</th>\n",
       "      <th>p</th>\n",
       "      <th>-log2(p)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>fin</th>\n",
       "      <td>-0.37</td>\n",
       "      <td>0.69</td>\n",
       "      <td>0.19</td>\n",
       "      <td>-0.75</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.47</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-1.93</td>\n",
       "      <td>0.05</td>\n",
       "      <td>4.24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>-0.06</td>\n",
       "      <td>0.94</td>\n",
       "      <td>0.03</td>\n",
       "      <td>-0.13</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.88</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-1.85</td>\n",
       "      <td>0.06</td>\n",
       "      <td>3.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>race</th>\n",
       "      <td>0.35</td>\n",
       "      <td>1.42</td>\n",
       "      <td>0.31</td>\n",
       "      <td>-0.26</td>\n",
       "      <td>0.95</td>\n",
       "      <td>0.77</td>\n",
       "      <td>2.60</td>\n",
       "      <td>1.13</td>\n",
       "      <td>0.26</td>\n",
       "      <td>1.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mar</th>\n",
       "      <td>-0.39</td>\n",
       "      <td>0.68</td>\n",
       "      <td>0.38</td>\n",
       "      <td>-1.15</td>\n",
       "      <td>0.36</td>\n",
       "      <td>0.32</td>\n",
       "      <td>1.43</td>\n",
       "      <td>-1.02</td>\n",
       "      <td>0.31</td>\n",
       "      <td>1.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>paro</th>\n",
       "      <td>-0.10</td>\n",
       "      <td>0.90</td>\n",
       "      <td>0.20</td>\n",
       "      <td>-0.49</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.61</td>\n",
       "      <td>1.33</td>\n",
       "      <td>-0.52</td>\n",
       "      <td>0.60</td>\n",
       "      <td>0.74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prio</th>\n",
       "      <td>0.09</td>\n",
       "      <td>1.10</td>\n",
       "      <td>0.03</td>\n",
       "      <td>0.04</td>\n",
       "      <td>0.15</td>\n",
       "      <td>1.04</td>\n",
       "      <td>1.16</td>\n",
       "      <td>3.22</td>\n",
       "      <td>&lt;0.005</td>\n",
       "      <td>9.59</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>age**2</th>\n",
       "      <td>0.01</td>\n",
       "      <td>1.01</td>\n",
       "      <td>0.00</td>\n",
       "      <td>-0.00</td>\n",
       "      <td>0.02</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.02</td>\n",
       "      <td>1.57</td>\n",
       "      <td>0.12</td>\n",
       "      <td>3.09</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>age**3</th>\n",
       "      <td>-0.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>-0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>1.00</td>\n",
       "      <td>-0.89</td>\n",
       "      <td>0.37</td>\n",
       "      <td>1.42</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Concordance</th>\n",
       "      <td>0.62</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Log-likelihood ratio test</th>\n",
       "      <td>26.81 on 8 df, -log2(p)=10.36</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "The ``p_value_threshold`` is set at 0.05. Even under the null hypothesis of no violations, some\n",
      "covariates will be below the threshold by chance. This is compounded when there are many covariates.\n",
      "Similarly, when there are lots of observations, even minor deviances from the proportional hazard\n",
      "assumption will be flagged.\n",
      "\n",
      "With that in mind, it's best to use a combination of statistical tests and visual tests to determine\n",
      "the most serious violations. Produce visual plots using ``check_assumptions(..., show_plots=True)``\n",
      "and looking for non-constant lines. See link [A] below for a full example.\n",
      "\n",
      "<lifelines.StatisticalResult>\n",
      "         test_name = proportional_hazard_test\n",
      " null_distribution = chi squared\n",
      "degrees_of_freedom = 1\n",
      "\n",
      "---\n",
      "             test_statistic    p  -log2(p)\n",
      "age    km              0.96 0.33      1.62\n",
      "       rank            4.09 0.04      4.54\n",
      "age**2 km              1.81 0.18      2.48\n",
      "       rank            0.79 0.37      1.42\n",
      "age**3 km              2.33 0.13      2.98\n",
      "       rank            0.03 0.87      0.19\n",
      "fin    km              0.03 0.87      0.20\n",
      "       rank            0.02 0.90      0.15\n",
      "mar    km              0.53 0.47      1.10\n",
      "       rank            0.94 0.33      1.59\n",
      "paro   km              0.20 0.66      0.60\n",
      "       rank            0.01 0.93      0.10\n",
      "prio   km              0.02 0.88      0.19\n",
      "       rank            0.01 0.90      0.15\n",
      "race   km              1.28 0.26      1.96\n",
      "       rank            0.47 0.49      1.02\n",
      "\n",
      "\n",
      "1. Variable 'age' failed the non-proportional test: p-value is 0.0431.\n",
      "\n",
      "   Advice 1: the functional form of the variable 'age' might be incorrect. That is, there may be\n",
      "non-linear terms missing. The proportional hazard test used is very sensitive to incorrect\n",
      "functional forms. See documentation in link [D] below on how to specify a functional form.\n",
      "\n",
      "   Advice 2: try binning the variable 'age' using pd.cut, and then specify it in `strata=['age',\n",
      "...]` in the call in `.fit`. See documentation in link [B] below.\n",
      "\n",
      "   Advice 3: try adding an interaction term with your time variable. See documentation in link [C]\n",
      "below.\n",
      "\n",
      "\n",
      "---\n",
      "[A]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html\n",
      "[B]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Bin-variable-and-stratify-on-it\n",
      "[C]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Introduce-time-varying-covariates\n",
      "[D]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Modify-the-functional-form\n",
      "[E]  https://lifelines.readthedocs.io/en/latest/jupyter_notebooks/Proportional%20hazard%20assumption.html#Stratification\n",
      "\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 284,
       "width": 424
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "rossi_higher_order_age = rossi.copy()\n",
    "rossi_higher_order_age['age'] = rossi_higher_order_age['age'] - rossi_higher_order_age['age'].mean()\n",
    "rossi_higher_order_age['age**2'] = (rossi_higher_order_age['age'] - rossi_higher_order_age['age'].mean())**2\n",
    "rossi_higher_order_age['age**3'] = (rossi_higher_order_age['age'] - rossi_higher_order_age['age'].mean())**3\n",
    "\n",
    "cph.fit(rossi_higher_order_age, 'week', 'arrest', strata=['wexp'])\n",
    "cph.print_summary(model=\"quad and cubic age terms\"); print()\n",
    "cph.check_assumptions(rossi_higher_order_age, show_plots=True, p_value_threshold=0.05)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We see we still have potentially _some_ violation, but it's a heck of a lot less. Also, interestingly, when we include these non-linear terms for `age`, the `wexp` proportionality violation disappears. It is not uncommon to see changing the functional form of one variable effects other's proportional tests, usually positively. So, we could remove the `strata=['wexp']` if we wished. \n",
    "\n",
    "#### Bin variable and stratify on it\n",
    "\n",
    "\n",
    "The second option proposed is to bin the variable into equal-sized bins, and stratify like we did with `wexp`. There is a trade off here between estimation and information-loss. If we have large bins, we will lose information (since different values are now binned together), but we need to estimate less new baseline hazards. On the other hand, with tiny bins, we allow the `age` data to have the most \"wiggle room\", but must compute many baseline hazards each of which has a smaller sample size. Like most things, the optimial value is somewhere inbetween."
   ]
  },
  {
   "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>age</th>\n",
       "      <th>age_strata</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>27</td>\n",
       "      <td>(24, 27]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>18</td>\n",
       "      <td>(15, 18]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>19</td>\n",
       "      <td>(18, 21]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>23</td>\n",
       "      <td>(21, 24]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>19</td>\n",
       "      <td>(18, 21]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   age age_strata\n",
       "0   27   (24, 27]\n",
       "1   18   (15, 18]\n",
       "2   19   (18, 21]\n",
       "3   23   (21, 24]\n",
       "4   19   (18, 21]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rossi_strata_age = rossi.copy()\n",
    "rossi_strata_age['age_strata'] = pd.cut(rossi_strata_age['age'], np.arange(0, 80, 3))\n",
    "\n",
    "rossi_strata_age[['age', 'age_strata']].head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<lifelines.CoxPHFitter: fitted with 432 total observations, 318 right-censored observations>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# drop the orignal, redundant, age column\n",
    "rossi_strata_age = rossi_strata_age.drop('age', axis=1)\n",
    "cph.fit(rossi_strata_age, 'week', 'arrest', strata=['age_strata', 'wexp'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "scrolled": false
   },
   "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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>lifelines.CoxPHFitter</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>duration col</th>\n",
       "      <td>'week'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>event col</th>\n",
       "      <td>'arrest'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>strata</th>\n",
       "      <td>[age_strata, wexp]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of observations</th>\n",
       "      <td>432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of events observed</th>\n",
       "      <td>114</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>partial log-likelihood</th>\n",
       "      <td>-392.443</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>time fit was run</th>\n",
       "      <td>2019-11-27 14:49:41 UTC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>stratified age and wexp</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>coef</th>\n",
       "      <th>exp(coef)</th>\n",
       "      <th>se(coef)</th>\n",
       "      <th>coef lower 95%</th>\n",
       "      <th>coef upper 95%</th>\n",
       "      <th>exp(coef) lower 95%</th>\n",
       "      <th>exp(coef) upper 95%</th>\n",
       "      <th>z</th>\n",
       "      <th>p</th>\n",
       "      <th>-log2(p)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>fin</th>\n",
       "      <td>-0.395</td>\n",
       "      <td>0.674</td>\n",
       "      <td>0.197</td>\n",
       "      <td>-0.781</td>\n",
       "      <td>-0.009</td>\n",
       "      <td>0.458</td>\n",
       "      <td>0.991</td>\n",
       "      <td>-2.004</td>\n",
       "      <td>0.045</td>\n",
       "      <td>4.472</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>race</th>\n",
       "      <td>0.280</td>\n",
       "      <td>1.324</td>\n",
       "      <td>0.313</td>\n",
       "      <td>-0.334</td>\n",
       "      <td>0.895</td>\n",
       "      <td>0.716</td>\n",
       "      <td>2.447</td>\n",
       "      <td>0.895</td>\n",
       "      <td>0.371</td>\n",
       "      <td>1.431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mar</th>\n",
       "      <td>-0.194</td>\n",
       "      <td>0.824</td>\n",
       "      <td>0.392</td>\n",
       "      <td>-0.961</td>\n",
       "      <td>0.574</td>\n",
       "      <td>0.382</td>\n",
       "      <td>1.776</td>\n",
       "      <td>-0.494</td>\n",
       "      <td>0.621</td>\n",
       "      <td>0.687</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>paro</th>\n",
       "      <td>-0.163</td>\n",
       "      <td>0.849</td>\n",
       "      <td>0.200</td>\n",
       "      <td>-0.555</td>\n",
       "      <td>0.228</td>\n",
       "      <td>0.574</td>\n",
       "      <td>1.256</td>\n",
       "      <td>-0.818</td>\n",
       "      <td>0.413</td>\n",
       "      <td>1.275</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prio</th>\n",
       "      <td>0.080</td>\n",
       "      <td>1.084</td>\n",
       "      <td>0.028</td>\n",
       "      <td>0.025</td>\n",
       "      <td>0.135</td>\n",
       "      <td>1.025</td>\n",
       "      <td>1.145</td>\n",
       "      <td>2.854</td>\n",
       "      <td>0.004</td>\n",
       "      <td>7.857</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Concordance</th>\n",
       "      <td>0.582</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Log-likelihood ratio test</th>\n",
       "      <td>13.247 on 5 df, -log2(p)=5.562</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x12544ed68>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 261,
       "width": 379
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "cph.print_summary(3, model=\"stratified age and wexp\")\n",
    "cph.plot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Proportional hazard assumption looks okay.\n"
     ]
    }
   ],
   "source": [
    "cph.check_assumptions(rossi_strata_age)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Introduce time-varying covariates\n",
    "\n",
    "Our second option to correct variables that violate the proportional hazard assumption is to model the time-varying component directly. This is done in two steps. The first is to transform your dataset into _episodic format_. This means that we split a subject from a single row into $n$ new rows, and each new row represents some time period for the subject. It's okay that the variables are static over this new time periods - we'll introduce some time-varying covariates later.\n",
    "\n",
    "See below for how to do this in _lifelines_:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "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>stop</th>\n",
       "      <th>start</th>\n",
       "      <th>arrest</th>\n",
       "      <th>age</th>\n",
       "      <th>fin</th>\n",
       "      <th>id</th>\n",
       "      <th>mar</th>\n",
       "      <th>paro</th>\n",
       "      <th>prio</th>\n",
       "      <th>race</th>\n",
       "      <th>wexp</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>7.0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>8.0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>9.0</td>\n",
       "      <td>8.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>10.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>11.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>12.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>13.0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>14.0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>15.0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>16.0</td>\n",
       "      <td>15.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>17.0</td>\n",
       "      <td>16.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>18.0</td>\n",
       "      <td>17.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>19.0</td>\n",
       "      <td>18.0</td>\n",
       "      <td>0</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>20.0</td>\n",
       "      <td>19.0</td>\n",
       "      <td>1</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>2.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>3.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>4.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>5.0</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>8</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    stop  start  arrest  age  fin  id  mar  paro  prio  race  wexp\n",
       "0    1.0    0.0       0   27    0   0    0     1     3     1     0\n",
       "1    2.0    1.0       0   27    0   0    0     1     3     1     0\n",
       "2    3.0    2.0       0   27    0   0    0     1     3     1     0\n",
       "3    4.0    3.0       0   27    0   0    0     1     3     1     0\n",
       "4    5.0    4.0       0   27    0   0    0     1     3     1     0\n",
       "5    6.0    5.0       0   27    0   0    0     1     3     1     0\n",
       "6    7.0    6.0       0   27    0   0    0     1     3     1     0\n",
       "7    8.0    7.0       0   27    0   0    0     1     3     1     0\n",
       "8    9.0    8.0       0   27    0   0    0     1     3     1     0\n",
       "9   10.0    9.0       0   27    0   0    0     1     3     1     0\n",
       "10  11.0   10.0       0   27    0   0    0     1     3     1     0\n",
       "11  12.0   11.0       0   27    0   0    0     1     3     1     0\n",
       "12  13.0   12.0       0   27    0   0    0     1     3     1     0\n",
       "13  14.0   13.0       0   27    0   0    0     1     3     1     0\n",
       "14  15.0   14.0       0   27    0   0    0     1     3     1     0\n",
       "15  16.0   15.0       0   27    0   0    0     1     3     1     0\n",
       "16  17.0   16.0       0   27    0   0    0     1     3     1     0\n",
       "17  18.0   17.0       0   27    0   0    0     1     3     1     0\n",
       "18  19.0   18.0       0   27    0   0    0     1     3     1     0\n",
       "19  20.0   19.0       1   27    0   0    0     1     3     1     0\n",
       "20   1.0    0.0       0   18    0   1    0     1     8     1     0\n",
       "21   2.0    1.0       0   18    0   1    0     1     8     1     0\n",
       "22   3.0    2.0       0   18    0   1    0     1     8     1     0\n",
       "23   4.0    3.0       0   18    0   1    0     1     8     1     0\n",
       "24   5.0    4.0       0   18    0   1    0     1     8     1     0"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from lifelines.utils import to_episodic_format\n",
    "\n",
    "# the time_gaps parameter specifies how large or small you want the periods to be. \n",
    "rossi_long = to_episodic_format(rossi, duration_col='week', event_col='arrest', time_gaps=1.)\n",
    "rossi_long.head(25)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Each subject is given a new id (but can be specified as well if already provided in the dataframe). This id is used to track subjects over time. Notice the `arrest` col is 0 for all periods prior to their (possible) event as well. \n",
    "\n",
    "Above I mentioned there were two steps to correct `age`. The first was to convert to a episodic format. The second is to create an interaction term between `age` and `stop`. This is a time-varying variable.\n",
    "\n",
    "Instead of `CoxPHFitter`, we must use `CoxTimeVaryingFitter` instead since we are working with a episodic dataset. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "rossi_long['time*age'] = rossi_long['age'] * rossi_long['stop']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<lifelines.CoxTimeVaryingFitter: fitted with 19809 periods, 432 subjects, 114 events>"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from lifelines import CoxTimeVaryingFitter\n",
    "ctv = CoxTimeVaryingFitter()\n",
    "\n",
    "ctv.fit(rossi_long, \n",
    "        id_col='id', \n",
    "        event_col='arrest', \n",
    "        start_col='start', \n",
    "        stop_col='stop', \n",
    "        strata=['wexp'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>lifelines.CoxTimeVaryingFitter</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>event col</th>\n",
       "      <td>'arrest'</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>strata</th>\n",
       "      <td>[wexp]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of subjects</th>\n",
       "      <td>432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of periods</th>\n",
       "      <td>19809</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>number of events</th>\n",
       "      <td>114</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>partial log-likelihood</th>\n",
       "      <td>-575.080</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>time fit was run</th>\n",
       "      <td>2019-11-27 14:49:44 UTC</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>model</th>\n",
       "      <td>age * time interaction</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div><table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>coef</th>\n",
       "      <th>exp(coef)</th>\n",
       "      <th>se(coef)</th>\n",
       "      <th>coef lower 95%</th>\n",
       "      <th>coef upper 95%</th>\n",
       "      <th>exp(coef) lower 95%</th>\n",
       "      <th>exp(coef) upper 95%</th>\n",
       "      <th>z</th>\n",
       "      <th>p</th>\n",
       "      <th>-log2(p)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>age</th>\n",
       "      <td>0.073</td>\n",
       "      <td>1.075</td>\n",
       "      <td>0.040</td>\n",
       "      <td>-0.005</td>\n",
       "      <td>0.151</td>\n",
       "      <td>0.995</td>\n",
       "      <td>1.163</td>\n",
       "      <td>1.830</td>\n",
       "      <td>0.067</td>\n",
       "      <td>3.893</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>fin</th>\n",
       "      <td>-0.386</td>\n",
       "      <td>0.680</td>\n",
       "      <td>0.191</td>\n",
       "      <td>-0.760</td>\n",
       "      <td>-0.011</td>\n",
       "      <td>0.468</td>\n",
       "      <td>0.989</td>\n",
       "      <td>-2.018</td>\n",
       "      <td>0.044</td>\n",
       "      <td>4.520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mar</th>\n",
       "      <td>-0.397</td>\n",
       "      <td>0.672</td>\n",
       "      <td>0.382</td>\n",
       "      <td>-1.147</td>\n",
       "      <td>0.352</td>\n",
       "      <td>0.318</td>\n",
       "      <td>1.422</td>\n",
       "      <td>-1.039</td>\n",
       "      <td>0.299</td>\n",
       "      <td>1.743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>paro</th>\n",
       "      <td>-0.098</td>\n",
       "      <td>0.907</td>\n",
       "      <td>0.196</td>\n",
       "      <td>-0.481</td>\n",
       "      <td>0.285</td>\n",
       "      <td>0.618</td>\n",
       "      <td>1.330</td>\n",
       "      <td>-0.501</td>\n",
       "      <td>0.616</td>\n",
       "      <td>0.698</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>prio</th>\n",
       "      <td>0.090</td>\n",
       "      <td>1.094</td>\n",
       "      <td>0.029</td>\n",
       "      <td>0.034</td>\n",
       "      <td>0.146</td>\n",
       "      <td>1.035</td>\n",
       "      <td>1.158</td>\n",
       "      <td>3.152</td>\n",
       "      <td>0.002</td>\n",
       "      <td>9.267</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>race</th>\n",
       "      <td>0.295</td>\n",
       "      <td>1.343</td>\n",
       "      <td>0.308</td>\n",
       "      <td>-0.310</td>\n",
       "      <td>0.899</td>\n",
       "      <td>0.733</td>\n",
       "      <td>2.458</td>\n",
       "      <td>0.955</td>\n",
       "      <td>0.340</td>\n",
       "      <td>1.558</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>time*age</th>\n",
       "      <td>-0.005</td>\n",
       "      <td>0.995</td>\n",
       "      <td>0.002</td>\n",
       "      <td>-0.008</td>\n",
       "      <td>-0.002</td>\n",
       "      <td>0.992</td>\n",
       "      <td>0.998</td>\n",
       "      <td>-3.337</td>\n",
       "      <td>0.001</td>\n",
       "      <td>10.203</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><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",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Log-likelihood ratio test</th>\n",
       "      <td>35.386 on 7 df, -log2(p)=16.689</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ctv.print_summary(3, model=\"age * time interaction\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x10e37b978>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 261,
       "width": 410
      },
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ctv.plot()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the above scaled Schoenfeld residual plots for `age`, we can see there is a slight negative effect for higher time values. This is confirmed in the output of the `CoxTimeVaryingFitter`: we see that the coefficient for `time*age` is -0.005.\n",
    "\n",
    "#### Conclusion\n",
    "\n",
    "The point estimates and the standard errors are very close to each other using either option, we can feel confident that either approach is okay to proceed. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Do I need to care about the proportional hazard assumption?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You may be surprised that often you don't need to care about the proportional hazard assumption. There are many reasons why not:\n",
    "\n",
    "1. If your goal is survival prediction, then you don't need to care about proportional hazards. Your goal is to maximize some score, irrelevant of how predictions are generated. \n",
    "\n",
    "2. Given a large enough sample size, even very small violations of proportional hazards will show up.  \n",
    "\n",
    "3. There are legitimate reasons to assume that all datasets will violate the proportional hazards assumption. This is detailed well in Stensrud & Hernán's \"Why Test for Proportional Hazards?\" [1]. \n",
    "\n",
    "4. > \"Even if the hazards were not proportional, altering the model to fit a set of assumptions fundamentally changes the scientific question. As Tukey said, \"Better an approximate answer to the exact question, rather than an exact answer to the approximate question.\" If you were to fit the Cox model in the presence of non-proportional hazards, what is the net effect? Slightly less power. In fact, you can recover most of that power with robust standard errors (specify `robust=True`). In this case the interpretation of the (exponentiated) model coefficient is a time-weighted average of the hazard ratio--I do this every single time.\" from AdamO, slightly modified to fit *lifelines* [2]\n",
    "\n",
    "Given the above considerations, the status quo is still to check for proportional hazards. So if you are avoiding testing for proportional hazards, be sure to understand and able to answer _why_ you are avoiding testing. \n",
    "\n",
    "#### References\n",
    "\n",
    "1.  Stensrud MJ, Hernán MA. Why Test for Proportional Hazards? JAMA. Published online March 13, 2020. doi:10.1001/jama.2020.1267\n",
    "2. AdamO (https://stats.stackexchange.com/users/8013/adamo), Checking the proportional hazard assumption, URL (version: 2019-04-05): https://stats.stackexchange.com/q/400981"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}