{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Exercise: Checking the sum and product rules, and their consequences\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Goal: Check using a very simple example that the Bayesian rules are consistent with standard probabilities based on frequencies. Also check notation and vocabulary.\n", "\n", "Physicist-friendly references:\n", "\n", "* R. Trotta, [*Bayes in the sky: Bayesian inference and model selection in cosmology*](https://www.tandfonline.com/doi/abs/10.1080/00107510802066753) {cite}`Trotta:2008qt`\n", " \n", "* D.S. Sivia and J. Skilling, [*Data Analysis: A Bayesian Tutorial, 2nd edition*](https://www.amazon.com/Data-Analysis-Bayesian-Devinderjit-Sivia/dp/0198568320/ref=mt_paperback?_encoding=UTF8&me=&qid=) {cite}`Sivia2006`\n", " \n", "* P. Gregory,\n", " [*Bayesian Logical Data Analysis for the Physical Sciences: A Comparative Approach with Mathematica® Support*](https://www.amazon.com/Bayesian-Logical-Analysis-Physical-Sciences/dp/0521150124/ref=sr_1_1?s=books&ie=UTF8&qid=1538587731&sr=1-1&keywords=gregory+bayesian) {cite}`Gregory2005`\n", "\n", "$% Some LaTeX definitions we'll use.\n", "\\newcommand{\\pr}{\\textrm{p}}\n", "$" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Bayesian rules of probability as principles of logic \n", "\n", "Notation: $p(x \\mid I)$ is the probability (or pdf) of $x$ being true\n", "given information $I$\n", "\n", "1. **Sum rule:** If set $\\{x_i\\}$ is exhaustive and exclusive, \n", " \n", " $$ \n", " \\sum_i p(x_i \\mid I) = 1 \\quad \\longrightarrow \\quad \\color{red}{\\int\\!dx\\, p(x \\mid I) = 1} \n", " $$ \n", " \n", " * cf. complete and orthonormal \n", " * implies *marginalization* (cf. inserting complete set of states or integrating out variables - but be careful!)\n", " \n", " $$\n", " p(x \\mid I) = \\sum_j p(x,y_j \\mid I) \n", " \\quad \\longrightarrow \\quad\n", " \\color{red}{p(x \\mid I) = \\int\\!dy\\, p(x,y \\mid I)} \n", " $$\n", " \n", " \n", "2. **Product rule:** expanding a joint probability of $x$ and $y$ \n", "\n", " $$\n", " \\color{red}{ p(x,y \\mid I) = p(x \\mid y,I)\\,p(y \\mid I)\n", " = p(y \\mid x,I)\\,p(x \\mid I)}\n", " $$\n", "\n", " * If $x$ and $y$ are mutually independent: $p(x \\mid y,I) = p(x \\mid I)$, then \n", " \n", " $$\n", " p(x,y \\mid I) \\longrightarrow p(x \\mid I)\\,p(y \\mid I)\n", " $$\n", " \n", " * Rearranging the second equality yields Bayes' Rule (or Theorem)\n", " \n", " $$\n", " \\color{blue}{p(x \\mid y,I) = \\frac{p(y \\mid x,I)\\, \n", " p(x \\mid I)}{p(y \\mid I)}}\n", " $$\n", "\n", "See Cox for the proof." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Answer the questions in *italics*. Check answers with your neighbors. Ask for help if you get stuck or are unsure." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "| TABLE 1 | Blue | Brown | Total |\n", "| :-------------: | :----------: | :-----------: | :-----------: |\n", "| Tall | 1 | 17 | 18 |\n", "| Short | 37 | 20 | 57 |\n", "| Total | 38 | 37 | 75 |\n", "\n", "| TABLE 2 | Blue | Brown | Total |\n", "| :-------------: | :----------: | :-----------: | :-----------: |\n", "| Tall |   |   |   |\n", "| Short |   |   |   |\n", "| Total |   |   |   |" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "1. Table 1 shows the number of blue- or brown-eyed and tall or short individuals in a population of 75.\n", "*Fill in the blanks in Table 2 with probabilities (in decimals with three places, not fractions) based on the usual \"frequentist\" interpretations of probability* (which would say that the probability of randomly drawing an ace from a deck of cards is 4/52 = 1/13). *Add x's in the row and/or column that illustrates the sum rule.*\n", "
\n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "2. *What is $\\pr(short, blue)$? Is this a joint or conditional probability? What is $\\pr(blue)$? \n", "
From the product rule, what is $\\pr(short | blue)$? Can you read this result directly from the table?*\n", "
\n", "
\n", "
\n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "3. *Apply Bayes' theorem to find $\\pr(blue | short)$ from your answers to the last part.*\n", "
\n", "
\n", "
\n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "4. *What rule does the second row (the one starting with \"Short\") illustrate? Write it out in $\\pr(\\cdot)$ notation.* \n", "
\n", "
\n", "
" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "5. *Are the probabilities of being tall and having brown eyes mutually independent? Why or why not?*\n", "
\n", "
\n", "
\n", "\n" ] }, { "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": "3.7.10" } }, "nbformat": 4, "nbformat_minor": 2 }