examples/diagnostics_and_criticism/Bayes_factor.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Bayes Factors and Marginal Likelihood"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on PyMC3 v3.9.1\n"
     ]
    }
   ],
   "source": [
    "import arviz as az\n",
    "import numpy as np\n",
    "import pymc3 as pm\n",
    "\n",
    "from matplotlib import pyplot as plt\n",
    "from scipy.special import betaln\n",
    "from scipy.stats import beta\n",
    "\n",
    "print(f\"Running on PyMC3 v{pm.__version__}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "az.style.use(\"arviz-darkgrid\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The \"Bayesian way\" to compare models is to compute the _marginal likelihood_ of each model $p(y \\mid M_k)$, _i.e._ the probability of the observed data $y$ given the $M_k$ model. This quantity, the marginal likelihood, is just the normalizing constant of Bayes' theorem. We can see this if we write Bayes' theorem and make explicit the fact that all inferences are model-dependant. \n",
    "\n",
    "$$p (\\theta \\mid y, M_k ) = \\frac{p(y \\mid \\theta, M_k) p(\\theta \\mid M_k)}{p( y \\mid M_k)}$$\n",
    "\n",
    "where:\n",
    "\n",
    "* $y$ is the data\n",
    "* $\\theta$ the parameters\n",
    "* $M_k$ one model out of K competing models\n",
    "\n",
    "\n",
    "Usually when doing inference we do not need to compute this normalizing constant, so in practice we often compute the posterior up to a constant factor, that is:\n",
    "\n",
    "$$p (\\theta \\mid y, M_k ) \\propto p(y \\mid \\theta, M_k) p(\\theta \\mid M_k)$$\n",
    "\n",
    "However, for model comparison and model averaging the marginal likelihood is an important quantity. Although, it's not the only way to perform these tasks, you can read about model averaging and model selection using alternative methods [here](model_comparison.ipynb), [there](model_averaging.ipynb) and [elsewhere](GLM-model-selection.ipynb)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Bayesian model selection\n",
    "\n",
    "If our main objective is to choose only one model, the _best_ one, from a set of models we can just choose the one with the largest $p(y \\mid M_k)$. This is totally fine if **all models** are assumed to have the same _a priori_ probability. Otherwise, we have to take into account that not all models are equally likely _a priori_ and compute:\n",
    "\n",
    "$$p(M_k \\mid y) \\propto p(y \\mid M_k) p(M_k)$$\n",
    "\n",
    "Sometimes the main objective is not to just keep a single model but instead to compare models to determine which ones are more likely and by how much. This can be achieved using Bayes factors:\n",
    "\n",
    "$$BF =  \\frac{p(y \\mid M_0)}{p(y \\mid M_1)}$$\n",
    "\n",
    "that is, the ratio between the marginal likelihood of two models. The larger the BF the _better_ the model in the numerator ($M_0$ in this example). To ease the interpretation of BFs some authors have proposed tables with levels of *support* or *strength*, just a way to put numbers into words. \n",
    "\n",
    "* 1-3: anecdotal\n",
    "* 3-10: moderate\n",
    "* 10-30: strong\n",
    "* 30-100: very strong\n",
    "* $>$ 100: extreme\n",
    "\n",
    "Notice that if you get numbers below 1 then the support is for the model in the denominator, tables for those cases are also available. Of course, you can also just take the inverse of the values in the above table or take the inverse of the BF value and you will be OK.\n",
    "\n",
    "It is very important to remember that these rules are just conventions, simple guides at best. Results should always be put into context of our problems and should be accompanied with enough details so others could evaluate by themselves if they agree with our conclusions. The evidence necessary to make a claim is not the same in particle physics, or a court, or to evacuate a town to prevent hundreds of deaths."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Bayesian model averaging\n",
    "\n",
    "Instead of choosing one single model from a set of candidate models, model averaging is about getting one meta-model by averaging the candidate models. The Bayesian version of this weights each model by its marginal posterior probability.\n",
    "\n",
    "$$p(\\theta \\mid y) = \\sum_{k=1}^K p(\\theta \\mid y, M_k) \\; p(M_k \\mid y)$$\n",
    "\n",
    "This is the optimal way to average models if the prior is _correct_ and the _correct_ model is one of the $M_k$ models in our set. Otherwise, _bayesian model averaging_ will asymptotically select the one single model in the set of compared models that is closest in [Kullback-Leibler divergence](https://en.wikipedia.org/wiki/Kullback%E2%80%93Leibler_divergence).\n",
    "\n",
    "Check this [example](model_averaging.ipynb) as an alternative way to perform model averaging."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "##  Some remarks\n",
    "\n",
    "Now we will briefly discuss some key facts about the _marginal likelihood_\n",
    "\n",
    "* The good\n",
    "    * **Occam Razor included**: Models with more parameters have a larger penalization than models with fewer parameters. The intuitive reason is that the larger the number of parameters the more _spread_ the _prior_ with respect to the likelihood.\n",
    "\n",
    "\n",
    "* The bad\n",
    "    * Computing the marginal likelihood is, generally, a hard task because it’s an integral of a highly variable function over a high dimensional parameter space. In general this integral needs to be solved numerically using more or less sophisticated methods.\n",
    "    \n",
    "$$p(y \\mid M_k) = \\int_{\\theta_k} p(y \\mid \\theta_k, M_k) \\; p(\\theta_k | M_k) \\; d\\theta_k$$\n",
    "\n",
    "* The ugly\n",
    "    * The marginal likelihood depends **sensitively** on the specified prior for the parameters in each model $p(\\theta_k \\mid M_k)$.\n",
    "\n",
    "Notice that *the good* and *the ugly* are related. Using the marginal likelihood to compare models is a good idea because a penalization for complex models is already included (thus preventing us from overfitting) and, at the same time, a change in the prior will affect the computations of the marginal likelihood. At first this sounds a little bit silly; we already know that priors affect computations (otherwise we could simply avoid them), but the point here is the word **sensitively**. We are talking about changes in the prior that will keep inference of $\\theta$ more or less the same, but could have a big impact in the value of the marginal likelihood."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Computing Bayes factors\n",
    "\n",
    "The marginal likelihood is generally not available in closed-form except for some restricted models. For this reason many methods have been devised to compute the marginal likelihood and the derived Bayes factors, some of these methods are so simple and [naive](https://radfordneal.wordpress.com/2008/08/17/the-harmonic-mean-of-the-likelihood-worst-monte-carlo-method-ever/) that works very bad in practice. Most of the useful methods have been originally proposed in the field of Statistical Mechanics. This connection is explained because the marginal likelihood is analogous to a central quantity in statistical physics known as the _partition function_ which in turn is closely related to another very important quantity the _free-energy_. Many of the connections between Statistical Mechanics and Bayesian inference are summarized [here](https://arxiv.org/abs/1706.01428)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Using a hierarchical model\n",
    "\n",
    "Computation of Bayes factors can be framed as a hierarchical model, where the high-level parameter is an index assigned to each model and sampled from a categorical distribution. In other words, we perform inference for two (or more) competing models at the same time and we use a discrete _dummy_ variable that _jumps_ between models. How much time we spend sampling each model is proportional to $p(M_k \\mid y)$.\n",
    "\n",
    "Some common problems when computing Bayes factors this way is that if one model is better than the other, by definition, we will spend more time sampling from it than from the other model. And this could lead to inaccuracies because we will be undersampling the less likely model. Another problem is that the values of the parameters get updated even when the parameters are not used to fit that model. That is, when model 0 is chosen, parameters in model 1 are updated but since they are not used to explain the data, they only get restricted by the prior. If the prior is too vague, it is possible that when we choose model 1, the parameter values are too far away from the previous accepted values and hence the step is rejected. Therefore we end up having a problem with sampling.\n",
    "\n",
    "In case we find these problems, we can try to improve sampling by implementing two modifications to our model:\n",
    "\n",
    "* Ideally, we can get a better sampling of both models if they are visited equally, so we can adjust the prior for each model in such a way to favour the less favourable model and disfavour the most favourable one. This will not affect the computation of the Bayes factor because we have to include the priors in the computation.\n",
    "\n",
    "* Use pseudo priors, as suggested by Kruschke and others. The idea is simple: if the problem is that the parameters drift away unrestricted, when the model they belong to is not selected, then one solution is to try to restrict them artificially, but only when not used! You can find an example of using pseudo priors in a model used by Kruschke in his book and [ported](https://github.com/aloctavodia/Doing_bayesian_data_analysis) to Python/PyMC3.\n",
    "\n",
    "If you want to learn more about this approach to the computation of the marginal likelihood see [Chapter 12 of Doing Bayesian Data Analysis](http://www.sciencedirect.com/science/book/9780124058880). This chapter also discuss how to use Bayes Factors as a Bayesian alternative to classical hypothesis testing."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Analytically\n",
    "\n",
    "For some models, like the beta-binomial model (AKA the _coin-flipping_ model) we can compute the marginal likelihood analytically. If we write this model as:\n",
    "\n",
    "$$\\theta \\sim Beta(\\alpha, \\beta)$$\n",
    "$$y \\sim Bin(n=1, p=\\theta)$$\n",
    "\n",
    "the _marginal likelihood_ will be:\n",
    "\n",
    "$$p(y) = \\binom {n}{h}  \\frac{B(\\alpha + h,\\ \\beta + n - h)} {B(\\alpha, \\beta)}$$\n",
    "\n",
    "where:\n",
    "\n",
    "* $B$ is the [beta function](https://en.wikipedia.org/wiki/Beta_function) not to get confused with the $Beta$ distribution\n",
    "* $n$ is the number of trials\n",
    "* $h$ is the number of success\n",
    "\n",
    "Since we only care about the relative value of the _marginal likelihood_ under two different models (for the same data), we can omit the binomial coefficient $\\binom {n}{h}$, thus we can write:\n",
    "\n",
    "$$p(y) \\propto \\frac{B(\\alpha + h,\\ \\beta + n - h)} {B(\\alpha, \\beta)}$$\n",
    "\n",
    "This expression has been coded in the following cell, but with a twist. We will be using the `betaln` function instead of the `beta` function, this is done to prevent underflow."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def beta_binom(prior, y):\n",
    "    \"\"\"\n",
    "    Compute the marginal likelihood, analytically, for a beta-binomial model.\n",
    "\n",
    "    prior : tuple\n",
    "        tuple of alpha and beta parameter for the prior (beta distribution)\n",
    "    y : array\n",
    "        array with \"1\" and \"0\" corresponding to the success and fails respectively\n",
    "    \"\"\"\n",
    "    alpha, beta = prior\n",
    "    h = np.sum(y)\n",
    "    n = len(y)\n",
    "    p_y = np.exp(betaln(alpha + h, beta + n - h) - betaln(alpha, beta))\n",
    "    return p_y"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Our data for this example consist on 100 \"flips of a coin\" and the same number of observed \"heads\" and \"tails\". We will compare two models one with a uniform prior and one with a _more concentrated_ prior around $\\theta = 0.5$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "y = np.repeat([1, 0], [50, 50])  # 50 \"heads\" and 50 \"tails\"\n",
    "priors = ((1, 1), (30, 30))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "for a, b in priors:\n",
    "    distri = beta(a, b)\n",
    "    x = np.linspace(0, 1, 300)\n",
    "    x_pdf = distri.pdf(x)\n",
    "    plt.plot(x, x_pdf, label=fr\"$\\alpha$ = {a:d}, $\\beta$ = {b:d}\")\n",
    "    plt.yticks([])\n",
    "    plt.xlabel(\"$\\\\theta$\")\n",
    "    plt.legend()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The following cell returns the Bayes factor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5.0\n"
     ]
    }
   ],
   "source": [
    "BF = beta_binom(priors[1], y) / beta_binom(priors[0], y)\n",
    "print(round(BF))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We see that the model with the more concentrated prior $\\text{beta}(30, 30)$ has $\\approx 5$ times more support than the model with the more extended prior $\\text{beta}(1, 1)$. Besides the exact numerical value this should not be surprising since the prior for the most favoured model is concentrated around $\\theta = 0.5$ and the data $y$ has equal number of head and tails, consintent with a value of $\\theta$ around 0.5."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Sequential Monte Carlo\n",
    "\n",
    "The [Sequential Monte Carlo](SMC2_gaussians.ipynb) sampler is a method that basically progresses by a series of successive *annealed* sequences from the prior to the posterior. A nice by-product of this process is that we get an estimation of the marginal likelihood. Actually for numerical reasons the returned value is the log marginal likelihood (this helps to avoid underflow)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Initializing SMC sampler...\n",
      "Multiprocess sampling (2 chains in 2 jobs)\n",
      "Stage:   0 Beta: 0.107\n",
      "Stage:   1 Beta: 0.843\n",
      "Stage:   2 Beta: 1.000\n",
      "Initializing SMC sampler...\n",
      "Multiprocess sampling (2 chains in 2 jobs)\n",
      "Stage:   0 Beta: 1.000\n"
     ]
    }
   ],
   "source": [
    "models = []\n",
    "traces = []\n",
    "for alpha, beta in priors:\n",
    "    with pm.Model() as model:\n",
    "        a = pm.Beta(\"a\", alpha, beta)\n",
    "        yl = pm.Bernoulli(\"yl\", a, observed=y)\n",
    "        trace = pm.sample_smc(1000, random_seed=42, parallel=True)\n",
    "        models.append(model)\n",
    "        traces.append(trace)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([5., 5.])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "BF_smc = np.exp(traces[1].report.log_marginal_likelihood - traces[0].report.log_marginal_likelihood)\n",
    "np.round(BF_smc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As we can see from the previous cell, SMC gives essentially the same answer as the analytical calculation! \n",
    "\n",
    "We obtain an array with two values, one per SMC run. As with other samplers PyMC3 attempts to run the sampler more than one time. Having independent samples may help diagnose the performace of the sampler.\n",
    "\n",
    "The advantage of using SMC to compute the (log) marginal likelihood is that we can use it for a wider range of models as a closed-form expression is no longer needed. The cost we pay for this flexibility is a more expensive computation. Notice that SMC (with a metropolis kernel as implemented in PyMC3) is not as efficient or robust as gradient-based samplers like NUTS. As the dimensionality of the problem increases a more accurate estimation of the posterior and the _marginal likelihood_ will requiere a larger number of `draws`. Additionally, a larger number of `n_steps` may help, specially if after stage 1 we notice that SMC uses a number of steps that are close to `n_steps`, i.e. SMC is having trouble to automatically reduce this number.\n",
    "\n",
    "You can check the number of steps per stage by doing:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "([8, 9, 11], [8, 9, 11])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "traces[0].report.nsteps"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Bayes factors and inference\n",
    "\n",
    "In this example we have used Bayes factors to judge which model seems to be better at explaining the data, and we get that one of the models is $\\approx 5$ _better_ than the other. \n",
    "\n",
    "But what about the posterior we get from these models? How different they are?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/osvaldo/proyectos/00_BM/arviz/arviz/data/io_pymc3.py:89: FutureWarning: Using `from_pymc3` without the model will be deprecated in a future release. Not using the model will return less accurate and less useful results. Make sure you use the model argument or call from_pymc3 within a model context.\n",
      "  FutureWarning,\n"
     ]
    },
    {
     "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>mean</th>\n",
       "      <th>sd</th>\n",
       "      <th>hdi_3%</th>\n",
       "      <th>hdi_97%</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>0.5</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.41</td>\n",
       "      <td>0.59</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   mean    sd  hdi_3%  hdi_97%\n",
       "a   0.5  0.05    0.41     0.59"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "az.summary(traces[0], var_names=\"a\", kind=\"stats\").round(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/osvaldo/proyectos/00_BM/arviz/arviz/data/io_pymc3.py:89: FutureWarning: Using `from_pymc3` without the model will be deprecated in a future release. Not using the model will return less accurate and less useful results. Make sure you use the model argument or call from_pymc3 within a model context.\n",
      "  FutureWarning,\n"
     ]
    },
    {
     "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>mean</th>\n",
       "      <th>sd</th>\n",
       "      <th>hdi_3%</th>\n",
       "      <th>hdi_97%</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>a</th>\n",
       "      <td>0.5</td>\n",
       "      <td>0.04</td>\n",
       "      <td>0.43</td>\n",
       "      <td>0.57</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   mean    sd  hdi_3%  hdi_97%\n",
       "a   0.5  0.04    0.43     0.57"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "az.summary(traces[1], var_names=\"a\", kind=\"stats\").round(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We may argue that the results are pretty similar, we have the same mean value for $\\theta$, and a slightly wider posterior for `model_0`, as expected since this model has a wider prior. We can also check the posterior predictive distribution to see how similar they are."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<MultiTrace: 2 chains, 1000 iterations, 2 variables>"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "traces[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/osvaldo/proyectos/00_BM/pymc3/pymc3/sampling.py:1618: UserWarning: samples parameter is smaller than nchains times ndraws, some draws and/or chains may not be represented in the returned posterior predictive sample\n",
      "  \"samples parameter is smaller than nchains times ndraws, some draws \"\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "        <style>\n",
       "            /* Turns off some styling */\n",
       "            progress {\n",
       "                /* gets rid of default border in Firefox and Opera. */\n",
       "                border: none;\n",
       "                /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "                background-size: auto;\n",
       "            }\n",
       "            .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "                background: #F44336;\n",
       "            }\n",
       "        </style>\n",
       "      <progress value='100' class='' max='100', style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [100/100 00:00<00:00]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "        <style>\n",
       "            /* Turns off some styling */\n",
       "            progress {\n",
       "                /* gets rid of default border in Firefox and Opera. */\n",
       "                border: none;\n",
       "                /* Needs to be in here for Safari polyfill so background images work as expected. */\n",
       "                background-size: auto;\n",
       "            }\n",
       "            .progress-bar-interrupted, .progress-bar-interrupted::-webkit-progress-bar {\n",
       "                background: #F44336;\n",
       "            }\n",
       "        </style>\n",
       "      <progress value='100' class='' max='100', style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      100.00% [100/100 00:00<00:00]\n",
       "    </div>\n",
       "    "
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 900x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "_, ax = plt.subplots(figsize=(9, 6))\n",
    "ppc_0 = pm.sample_posterior_predictive(traces[0], 100, models[0], size=(len(y), 20))\n",
    "ppc_1 = pm.sample_posterior_predictive(traces[1], 100, models[1], size=(len(y), 20))\n",
    "for m_0, m_1 in zip(ppc_0[\"yl\"].T, ppc_1[\"yl\"].T):\n",
    "    az.plot_kde(np.mean(m_0, 0), ax=ax, plot_kwargs={\"color\": \"C0\"})\n",
    "    az.plot_kde(np.mean(m_1, 0), ax=ax, plot_kwargs={\"color\": \"C1\"})\n",
    "ax.plot([], label=\"model_0\")\n",
    "ax.plot([], label=\"model_1\")\n",
    "ax.legend()\n",
    "ax.set_xlabel(\"$\\\\theta$\")\n",
    "ax.set_yticks([]);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this example the observed data $y$ is more consistent with `model_1` (because the prior is concentrated around the correct value of $\\theta$) than `model_0` (which assigns equal probability to every possible value of $\\theta$), and this difference is captured by the Bayes factors. We could say Bayes factors are measuring which model, as a whole, is better, including details of the prior that may be irrelevant for parameter inference. In fact in this example we can also see that it is possible to have two different models, with different Bayes factors, but nevertheless get very similar predictions. The reason is that the data is informative enough to reduce the effect of the prior up to the point of inducing a very similar posterior. As predictions are computed from the posterior we also get very similar predictions. In most scenarios when comparing models what we really care is the predictive accuracy of the models, if two models have similar predictive accuracy we consider both models as similar. To estimate the predictive accuracy we can use tools like WAIC, LOO or cross-validation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "arviz    0.8.3\n",
      "json     2.0.9\n",
      "numpy    1.18.1\n",
      "pymc3    3.9.1\n",
      "autopep8 1.5\n",
      "last updated: Thu Jun 25 2020 \n",
      "\n",
      "CPython 3.7.6\n",
      "IPython 7.12.0\n",
      "watermark 2.0.2\n"
     ]
    }
   ],
   "source": [
    "%load_ext watermark\n",
    "%watermark -n -u -v -iv -w"
   ]
  }
 ],
 "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": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}