{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "(BEST)=\n", "# Bayesian Estimation Supersedes the T-Test\n", "\n", ":::{post} Jan 07, 2022\n", ":tags: hypothesis testing, model comparison, \n", ":category: beginner\n", ":author: Andrew Straw, Thomas Wiecki, Chris Fonnesbeck, Andrés suárez\n", ":::" ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Running on PyMC v4.2.2\n" ] } ], "source": [ "import arviz as az\n", "import numpy as np\n", "import pandas as pd\n", "import pymc as pm\n", "import seaborn as sns\n", "\n", "print(f\"Running on PyMC v{pm.__version__}\")" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [], "source": [ "%config InlineBackend.figure_format = 'retina'\n", "az.style.use(\"arviz-darkgrid\")\n", "rng = np.random.default_rng(seed=42)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### The Problem\n", "\n", "This model replicates the example used in **Bayesian estimation supersedes the t-test** {cite:p}kruschke2013.\n", "\n", "Several statistical inference procedures involve the comparison of two groups. We may be interested in whether one group is larger than another, or simply different from the other. We require a statistical model for this because true differences are usually accompanied by measurement or stochastic noise that prevent us from drawing conclusions simply from differences calculated from the observed data. \n", "\n", "The *de facto* standard for statistically comparing two (or more) samples is to use a statistical test. This involves expressing a null hypothesis, which typically claims that there is no difference between the groups, and using a chosen test statistic to determine whether the distribution of the observed data is plausible under the hypothesis. This rejection occurs when the calculated test statistic is higher than some pre-specified threshold value.\n", "\n", "Unfortunately, it is not easy to conduct hypothesis tests correctly, and their results are very easy to misinterpret. Setting up a statistical test involves several subjective choices (*e.g.* statistical test to use, null hypothesis to test, significance level) by the user that are rarely justified based on the problem or decision at hand, but rather, are usually based on traditional choices that are entirely arbitrary {cite:p}johnson1999. The evidence that it provides to the user is indirect, incomplete, and typically overstates the evidence against the null hypothesis {cite:p}goodman1999. \n", "\n", "A more informative and effective approach for comparing groups is one based on **estimation** rather than **testing**, and is driven by Bayesian probability rather than frequentist. That is, rather than testing whether two groups are different, we instead pursue an estimate of how different they are, which is fundamentally more informative. Moreover, we include an estimate of uncertainty associated with that difference which includes uncertainty due to our lack of knowledge of the model parameters (epistemic uncertainty) and uncertainty due to the inherent stochasticity of the system (aleatory uncertainty)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Example: Drug trial evaluation\n", "\n", "To illustrate how this Bayesian estimation approach works in practice, we will use a fictitious example from {cite:t}kruschke2013 concerning the evaluation of a clinical trial for drug evaluation. The trial aims to evaluate the efficacy of a \"smart drug\" that is supposed to increase intelligence by comparing IQ scores of individuals in a treatment arm (those receiving the drug) to those in a control arm (those receiving a placebo). There are 47 individuals and 42 individuals in the treatment and control arms, respectively." ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "