{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# HIDDEN\n", "from datascience import *\n", "%matplotlib inline\n", "import matplotlib.pyplot as plots\n", "plots.style.use('fivethirtyeight')\n", "import math\n", "import numpy as np\n", "from scipy import stats" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# HIDDEN\n", "\n", "colors = Table.read_table('roulette_wheel.csv').column('Color')\n", "pockets = make_array('0','00')\n", "for i in np.arange(1, 37):\n", " pockets = np.append(pockets, str(i)) \n", "\n", "wheel = Table().with_columns(\n", " 'Pocket', pockets,\n", " 'Color', colors\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### The Central Limit Theorem ###\n", "Very few of the data histograms that we have seen in this course have been bell shaped. When we have come across a bell shaped distribution, it has almost invariably been an empirical histogram of a statistic based on a random sample.\n", "\n", "The examples below show two very different situations in which an approximate bell shape appears in such histograms." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Net Gain in Roulette ###\n", "In an earlier section, the bell appeared as the rough shape of the total amount of money we would make if we placed the same bet repeatedly on different spins of a roulette wheel. " ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Pocket Color
0 green
00 green
1 red
2 black
3 red
4 black
5 red
6 black
7 red
8 black
\n", "

... (28 rows omitted)\n", " \n", " \n", " Pocket Color Winnings: Red\n", " \n", " \n", " \n", " \n", " 0 green -1 \n", " \n", " \n", " \n", " 00 green -1 \n", " \n", " \n", " \n", " 1 red 1 \n", " \n", " \n", " \n", " 2 black -1 \n", " \n", " \n", " \n", " 3 red 1 \n", " \n", " \n", " \n", " 4 black -1 \n", " \n", " \n", " \n", " 5 red 1 \n", " \n", " \n", " \n", " 6 black -1 \n", " \n", " \n", " \n", " 7 red 1 \n", " \n", " \n", " \n", " 8 black -1 \n", " \n", " \n", "\n", "

... (28 rows omitted)" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "red.select('Winnings: Red').hist(bins=np.arange(-1.5, 1.6, 1))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now suppose you bet many times on red. Your net winnings will be the sum of many draws made at random with replacement from the distribution above.\n", "\n", "It will take a bit of math to list all the possible values of your net winnings along with all of their chances. We won't do that; instead, we will approximate the probability distribution by simulation, as we have done all along in this course. \n", "\n", "The code below simulates your net gain if you bet \\$1 on red on 400 different spins of the roulette wheel. " ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": true }, "outputs": [], "source": [ "num_bets = 400\n", "repetitions = 10000\n", "\n", "net_gain_red = make_array()\n", "\n", "for i in np.arange(repetitions):\n", " spins = red.sample(num_bets)\n", " new_net_gain_red = spins.column('Winnings: Red').sum()\n", " net_gain_red = np.append(net_gain_red, new_net_gain_red)\n", "\n", "\n", "results = Table().with_column(\n", " 'Net Gain on Red', net_gain_red\n", " )" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAcAAAAEqCAYAAACC+oCXAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niYjIIDEAiYjIIDEAiYjIIP0/tNN7p0G1dJgAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "results.hist(bins=np.arange(-80, 50, 6))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "That's a roughly bell shaped histogram, even though the distribution we are drawing from is nowhere near bell shaped.\n", "\n", "**Center.** The distribution is centered near -\\$20, roughly. To see why, note that your winnings will be \\$1 on about 18/38 of the bets, and -\\$1 on the remaining 20/38. So your average winnings per dollar bet will be roughly -5.26 cents:" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "-0.05263157894736842" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "average_per_bet = 1*(18/38) + (-1)*(20/38)\n", "average_per_bet" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "So in 400 bets you expect that your net gain will be about -\\$21:" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "-21.052631578947366" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "400 * average_per_bet" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For confirmation, we can compute the mean of the 10,000 simulated net gains:" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "-20.8992" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.mean(results.column(0))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Spread.** Run your eye along the curve starting at the center and notice that the point of inflection is near 0. On a bell shaped curve, the SD is the distance from the center to a point of inflection. The center is roughly -\\$20, which means that the SD of the distribution is around \\$20.\n", "\n", "In the next section we will see where the \\$20 comes from. For now, let's confirm our observation by simply calculating the SD of the 10,000 simulated net gains:" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "20.043159415621083" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.std(results.column(0))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Summary.** The net gain in 400 bets is the sum of the 400 amounts won on each individual bet. The probability distribution of that sum is approximately normal, with an average and an SD that we can approximate." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Average Flight Delay ###\n", "The table `united` contains data on departure delays of 13,825 United Airlines domestic flights out of San Francisco airport in the summer of 2015. As we have seen before, the distribution of delays has a long right-hand tail." ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": true }, "outputs": [], "source": [ "united = Table.read_table('united_summer2015.csv')" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAcQAAAEqCAYAAACLESDtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nU6wAAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "united.select('Delay').hist(bins=np.arange(-20, 300, 10))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The mean delay was about 16.6 minutes and the SD was about 39.5 minutes. Notice how large the SD is, compared to the mean. Those large deviations on the right have an effect, even though they are a very small proportion of the data." ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "(16.658155515370705, 39.480199851609314)" ] }, "execution_count": 17, "metadata": {}, "output_type": "execute_result" } ], "source": [ "mean_delay = np.mean(united.column('Delay'))\n", "sd_delay = np.std(united.column('Delay'))\n", "\n", "mean_delay, sd_delay" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Now suppose we sampled 400 delays at random with replacement. You could sample without replacement if you like, but the results would be very similar to with-replacement sampling. If you sample a few hundred out of 13,825 without replacement, you hardly change the population each time you pull out a value.\n", "\n", "In the sample, what could the average delay be? We expect it to be around 16 or 17, because that's the population average; but it is likely to be somewhat off. Let's see what we get by sampling. We'll work with the table `delay` that only contains the column of delays." ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": true }, "outputs": [], "source": [ "delay = united.select('Delay')" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "16.68" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "np.mean(delay.sample(400).column('Delay'))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The sample average varies according to how the sample comes out, so we will simulate the sampling process repeatedly and draw the empirical histogram of the sample average. That will be an approximation to the probability histogram of the sample average." ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": true }, "outputs": [], "source": [ "sample_size = 400\n", "repetitions = 10000\n", "\n", "means = make_array()\n", "\n", "for i in np.arange(repetitions):\n", " sample = delay.sample(sample_size)\n", " new_mean = np.mean(sample.column('Delay'))\n", " means = np.append(means, new_mean)\n", "\n", "results = Table().with_column(\n", " 'Sample Mean', means\n", ")" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAbsAAAEqCAYAAACMU/74AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n2DEYMi5UAAAAAElFTkSuQmCC\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "results.hist(bins=np.arange(10, 25, 0.5))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Once again, we see a rough bell shape, even though we are drawing from a very skewed distribution. The bell is centered somewhere between 16 ad 17, as we expect." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Central Limit Theorem ###\n", "\n", "The reason why the bell shape appears in such settings is a remarkable result of probability theory called the **Central Limit Theorem**. \n", "\n", "**The Central Limit Theorem says that the probability distribution of the sum or average of a large random sample drawn with replacement will be roughly normal, *regardless of the distribution of the population from which the sample is drawn*.**\n", "\n", "As we noted when we were studying Chebychev's bounds, results that can be applied to random samples *regardless of the distribution of the population* are very powerful, because in data science we rarely know the distribution of the population.\n", "\n", "The Central Limit Theorem makes it possible to make inferences with very little knowledge about the population, provided we have a large random sample. That is why it is central to the field of statistical inference." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Proportion of Purple Flowers ###\n", "Recall Mendel's probability model for the colors of the flowers of a species of pea plant. The model says that the flower colors of the plants are like draws made at random with replacement from {Purple, Purple, Purple, White}.\n", "\n", "In a large sample of plants, about what proportion will have purple flowers? We would expect the answer to be about 0.75, the proportion purple in the model. And, because proportions are means, the Central Limit Theorem says that the distribution of the sample proportion of purple plants is roughly normal.\n", "\n", "We can confirm this by simulation. Let's simulate the proportion of purple-flowered plants in a sample of 200 plants." ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
Color
Purple
Purple
Purple
White
" ], "text/plain": [ "Color\n", "Purple\n", "Purple\n", "Purple\n", "White" ] }, "execution_count": 22, "metadata": {}, "output_type": "execute_result" } ], "source": [ "colors = make_array('Purple', 'Purple', 'Purple', 'White')\n", "\n", "model = Table().with_column('Color', colors)\n", "\n", "model" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "collapsed": false }, "outputs": [], "source": [ "props = make_array()\n", "\n", "num_plants = 200\n", "repetitions = 10000\n", "\n", "for i in np.arange(repetitions):\n", " sample = model.sample(num_plants)\n", " new_prop = np.count_nonzero(sample.column('Color') == 'Purple')/num_plants\n", " props = np.append(props, new_prop)\n", " \n", "results = Table().with_column('Sample Proportion: 200', props)" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAdQAAAEqCAYAAACsv6EFAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIiIiEbCgEhERieD/AdNcPCueI3GwAAAAAElFTkSuQmCC\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "results.hist(bins=np.arange(0.65, 0.85, 0.01))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "There's that normal curve again, as predicted by the Central Limit Theorem, centered at around 0.75 just as you would expect.\n", "\n", "How would this distribution change if we increased the sample size? Let's run the code again with a sample size of 800, and collect the results of simulations in the same table in which we collected simulations based on a sample size of 200. We will keep the number of `repetitions` the same as before so that the two columns have the same length." ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "collapsed": true }, "outputs": [], "source": [ "props2 = make_array()\n", "\n", "num_plants = 800\n", "\n", "for i in np.arange(repetitions):\n", " sample = model.sample(num_plants)\n", " new_prop = np.count_nonzero(sample.column('Color') == 'Purple')/num_plants\n", " props2 = np.append(props2, new_prop)\n", " \n", "results = results.with_column('Sample Proportion: 800', props2)" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAuIAAAEWCAYAAAAjCPKtAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAwAUEcAAAAMAFBHAAAADDB/wMrSsOM8nHk0QAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "results.hist(bins=np.arange(0.65, 0.85, 0.01))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Both distributions are approximately normal but one is narrower than the other. The proportions based on a sample size of 800 are more tightly clustered around 0.75 than those from a sample size of 200. Increasing the sample size has decreased the variability in the sample proportion.\n", "\n", "This should not be surprising. We have leaned many times on the intuition that a larger sample size generally reduces the variability of a statistic. However, in the case of a sample average, we can *quantify* the relationship between sample size and variability.\n", "\n", "Exactly how does the sample size affect the variability of a sample average or proportion? That is the question we will examine in the next section." ] } ], "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": "3.4.5" } }, "nbformat": 4, "nbformat_minor": 0 }