Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
BDA/BDA 5.9.6.ipynb
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
144 lines (144 sloc)
20.5 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"# Problem 5.9.6. Exchangeable Models\n", | |
"\n", | |
"1. In the divorce rate example of Section 5.2, set up a prior distribution for the values $y_1 \\ldots, y_8$ that allows for one low value (Utah) and one high value (Nevada), with independent and identical distributions for the other six values. This prior distribution should be exchangeable, because it is not known which of the eight states correspond to Utah and Nevada. \n", | |
"\n", | |
"2. Determine the posterior distribution for $y_8$ under this model given the observed values of $y_1, \\ldots, y_7$ given in the example. This posterior distribution should probably have two or three modes, corresponding to the possibilities that the missing state is Utah, Nevada, or one of the other six. \n", | |
"\n", | |
"3. Now consider the entire set of eight data points, including the value for $y_8$ given at the end of the example. Are these data consistent with the prior distribution you gave in part (1) above? In particular, did your prior distribution allow for the possibility that the actual data have an outlier (Nevada) at the high end, but no outlier at the low end?\n", | |
"\n", | |
"The states are Arizona, Colorado, Idaho, Montana, Nevada, New Mexico, Utah, and Wyoming.\n", | |
"\n", | |
"The rates from seven of these states are 5.8, 6.6,7.8,5.6,7.0,7.1,5.4 divorces per 1000 population per year. \n", | |
"\n", | |
"Gelman, Andrew; Carlin, John B.; Stern, Hal S.; Dunson, David B.; Vehtari, Aki; Rubin, Donald B.. Bayesian Data Analysis, Third Edition (Chapman & Hall/CRC Texts in Statistical Science) (Page 135). CRC Press. Kindle Edition. " | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 73, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"name": "stdout", | |
"output_type": "stream", | |
"text": [ | |
"mean: 6.471428571428571 variance: 0.6877551020408161\n" | |
] | |
} | |
], | |
"source": [ | |
"from scipy.stats import norm\n", | |
"from itertools import permutations\n", | |
"import matplotlib.pyplot as plt\n", | |
"\n", | |
"rates=np.array([5.8,6.6,7.8,5.6,7.0,7.1,5.4])\n", | |
"print('mean:',rates.mean(),'variance:',rates.var())\n" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 74, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"s=range(8)\n", | |
"def prior(x):\n", | |
" L=0\n", | |
" for i,j in permutations(s,2):\n", | |
" L0=1\n", | |
" L0=L0*norm.pdf(x[i],loc=8.7,scale=.8)\n", | |
" L0=L0*norm.pdf(x[j],loc=4.3,scale=.8)\n", | |
" for k in s:\n", | |
" if k!=i and k!=j:\n", | |
" L0=L0*norm.pdf(x[k],loc=6.5,scale=.8)\n", | |
" L=L+L0\n", | |
" return(L)\n", | |
"\n", | |
"def like(x):\n", | |
" return prior(np.append(x,rates))" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 77, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"x=np.linspace(0.0,15.0,1000)\n", | |
"y=np.array([like(i) for i in x])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": 78, | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"data": { | |
"text/plain": [ | |
"[<matplotlib.lines.Line2D at 0x1a1977e748>]" | |
] | |
}, | |
"execution_count": 78, | |
"metadata": {}, | |
"output_type": "execute_result" | |
}, | |
{ | |
"data": { | |
"image/png": "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\n", | |
"text/plain": [ | |
"<Figure size 432x288 with 1 Axes>" | |
] | |
}, | |
"metadata": {}, | |
"output_type": "display_data" | |
} | |
], | |
"source": [ | |
"plt.plot(x,y)" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"I have a lot of questions about this problem, starting with: have I computed the right thing? I am not sure.\n", | |
"As far as the last part, No, my prior distribution did not allow for a high value without a low value; it expected one of each." | |
] | |
}, | |
{ | |
"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": "3.6.4" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |