Skip to content

Instantly share code, notes, and snippets.

@cmrivers

cmrivers/vanessa

Last active August 29, 2015 14:22
Show Gist options
  • Save cmrivers/d3cf21631fb3b0a9e4cd to your computer and use it in GitHub Desktop.
Save cmrivers/d3cf21631fb3b0a9e4cd to your computer and use it in GitHub Desktop.
Download ZIP
Raw
vanessa
{
"cells": [
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Populating the interactive namespace from numpy and matplotlib\n"
]
}
],
"source": [
"import seaborn as sns\n",
"import pandas as pd\n",
"import epipy\n",
"%pylab inline"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"dat = pd.read_csv('vanessa.csv')\n",
"dat['exposure'] = dat.exposure.replace(['2.5 wk', '3 wk', '2 wk'], '2-3 wk')\n",
"dat['treatment'] = dat['treatment'].replace(0, 'control')\n",
"dat['treatment'] = dat['treatment'].replace(120, 'exposed')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**This is what your data looks like**"
]
},
{
"cell_type": "code",
"execution_count": 77,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>treatment</th>\n",
" <th>exposure</th>\n",
" <th>implantation sites</th>\n",
" <th>corpora lutea</th>\n",
" <th>implants</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>11</td>\n",
" <td>20</td>\n",
" <td>0.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>10</td>\n",
" <td>18</td>\n",
" <td>0.6</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>11</td>\n",
" <td>14</td>\n",
" <td>0.8</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>10</td>\n",
" <td>10</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>11</td>\n",
" <td>11</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" treatment exposure implantation sites corpora lutea implants\n",
"0 control 2-3 wk 11 20 0.6\n",
"1 control 2-3 wk 10 18 0.6\n",
"2 control 2-3 wk 11 14 0.8\n",
"3 control 2-3 wk 10 10 1.0\n",
"4 control 2-3 wk 11 11 1.0"
]
},
"execution_count": 77,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dat.head()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Summary statistics of each variable**"
]
},
{
"cell_type": "code",
"execution_count": 78,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"----------------------------------\n",
"treatment \n",
"\n",
" count freq\n",
"exposed 16 0.516129\n",
"control 15 0.483871\n",
"----------------------------------\n",
"exposure \n",
"\n",
" count freq\n",
"8 wk 19 0.612903\n",
"2-3 wk 12 0.387097\n",
"----------------------------------\n",
"implantation sites \n",
"\n",
"count 31.000000\n",
"missing 0.000000\n",
"min 0.000000\n",
"median 13.000000\n",
"mean 10.548387\n",
"std 5.117543\n",
"max 16.000000\n",
"dtype: float64\n",
"----------------------------------\n",
"corpora lutea \n",
"\n",
"count 31.000000\n",
"missing 0.000000\n",
"min 6.000000\n",
"median 15.000000\n",
"mean 15.387097\n",
"std 4.047035\n",
"max 25.000000\n",
"dtype: float64\n",
"----------------------------------\n",
"implants \n",
"\n",
"count 31.000000\n",
"missing 0.000000\n",
"min 0.000000\n",
"median 0.800000\n",
"mean 0.696774\n",
"std 0.339101\n",
"max 1.000000\n",
"dtype: float64\n"
]
}
],
"source": [
"epipy.summary(dat)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Cool. The fancy plot shortcut shows that treatment is significant, but only at 8 weeks. I'll go into the ### details below.**"
]
},
{
"cell_type": "code",
"execution_count": 104,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"<seaborn.axisgrid.FacetGrid at 0x111843f90>"
]
},
"execution_count": 104,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAacAAAFhCAYAAADUXmUxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nKsdwkiRVjuEkSaocw0mSVDmGkySpcv4/2A2pzy8d4akAAAAASUVORK5CYII=\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x112c18210>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"sns.factorplot('exposure', y='implantation sites', hue='treatment', data=dat, kind='point', ci=95)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Exposed groups clearly have lower number of implantations, but high variance.**"
]
},
{
"cell_type": "code",
"execution_count": 106,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"<seaborn.axisgrid.FacetGrid at 0x112c0e990>"
]
},
"execution_count": 106,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAacAAAFhCAYAAADUXmUxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x112f16810>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"sns.factorplot('exposure', y='implantation sites', hue='treatment', data=dat, kind='box')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Categorical analysis for failed implantations (value = 0) and successfull (value > 0)**"
]
},
{
"cell_type": "code",
"execution_count": 81,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/caitlin/anaconda/lib/python2.7/site-packages/IPython/kernel/__main__.py:2: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame\n",
"\n",
"See the the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
" from IPython.kernel.zmq import kernelapp as app\n"
]
},
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>treatment</th>\n",
" <th>exposure</th>\n",
" <th>implantation sites</th>\n",
" <th>corpora lutea</th>\n",
" <th>implants</th>\n",
" <th>failed</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>11</td>\n",
" <td>20</td>\n",
" <td>0.6</td>\n",
" <td>healthy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>10</td>\n",
" <td>18</td>\n",
" <td>0.6</td>\n",
" <td>healthy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>11</td>\n",
" <td>14</td>\n",
" <td>0.8</td>\n",
" <td>healthy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>10</td>\n",
" <td>10</td>\n",
" <td>1.0</td>\n",
" <td>healthy</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>control</td>\n",
" <td>2-3 wk</td>\n",
" <td>11</td>\n",
" <td>11</td>\n",
" <td>1.0</td>\n",
" <td>healthy</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" treatment exposure implantation sites corpora lutea implants failed\n",
"0 control 2-3 wk 11 20 0.6 healthy\n",
"1 control 2-3 wk 10 18 0.6 healthy\n",
"2 control 2-3 wk 11 14 0.8 healthy\n",
"3 control 2-3 wk 10 10 1.0 healthy\n",
"4 control 2-3 wk 11 11 1.0 healthy"
]
},
"execution_count": 81,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dat['failed'] = 'healthy'\n",
"dat['failed'][dat['implantation sites'] == 0] = 'sick'\n",
"dat.head()"
]
},
{
"cell_type": "code",
"execution_count": 113,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>sick</th>\n",
" <th>healthy</th>\n",
" <th>All</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>exposed</th>\n",
" <td>3.00</td>\n",
" <td>13</td>\n",
" <td>16</td>\n",
" </tr>\n",
" <tr>\n",
" <th>control</th>\n",
" <td>0.01</td>\n",
" <td>15</td>\n",
" <td>15</td>\n",
" </tr>\n",
" <tr>\n",
" <th>All</th>\n",
" <td>3.00</td>\n",
" <td>28</td>\n",
" <td>31</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" sick healthy All\n",
"exposed 3.00 13 16\n",
"control 0.01 15 15\n",
"All 3.00 28 31"
]
},
"execution_count": 113,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"table = epipy.create_2x2(dat, 'treatment', 'failed', ['exposed', 'control'], ['sick', 'healthy'])\n",
"table = table.replace(0, .01)\n",
"table"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Results of 2x2 not significant. This is almost certainly due to small N.**"
]
},
{
"cell_type": "code",
"execution_count": 114,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Odds ratio: 346.15 (95% CI: (0.0, 117954664177.25))\n",
"Relative risk: 281.44 (95% CI: (0.0, 93377184723.96))\n",
"\n",
"Attributable risk: 0.187 (95% CI: (-0.02, 0.4))\n",
"Attributable risk percent: 99.64% (95% CI: (98.53, 100.761))\n",
"Population attributable risk: 0.096\n",
"Population attributable risk percent: 99.31% \n",
"\n",
"Chi square: 3.08896186169\n",
"p value: 0.543049795904\n"
]
}
],
"source": [
"epipy.analyze_2x2(table)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Same thing but just doing 8 week exposures.**"
]
},
{
"cell_type": "code",
"execution_count": 115,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>sick</th>\n",
" <th>healthy</th>\n",
" <th>All</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>exposed</th>\n",
" <td>1.00</td>\n",
" <td>9</td>\n",
" <td>10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>control</th>\n",
" <td>0.01</td>\n",
" <td>9</td>\n",
" <td>9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>All</th>\n",
" <td>1.00</td>\n",
" <td>18</td>\n",
" <td>19</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" sick healthy All\n",
"exposed 1.00 9 10\n",
"control 0.01 9 9\n",
"All 1.00 18 19"
]
},
"execution_count": 115,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"table8 = epipy.create_2x2(dat[dat.exposure == '8 wk'], 'treatment', 'failed', ['exposed', 'control'], ['sick', 'healthy'])\n",
"table8 = table8.replace(0, .01)\n",
"table8"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Not significant. N is too small.**"
]
},
{
"cell_type": "code",
"execution_count": 116,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Odds ratio: 100.0 (95% CI: (0.0, 36646515867.84))\n",
"Relative risk: 90.1 (95% CI: (0.0, 31652767974.3))\n",
"\n",
"Attributable risk: 0.099 (95% CI: (-0.1, 0.3))\n",
"Attributable risk percent: 98.89% (95% CI: (96.85, 100.932))\n",
"Population attributable risk: 0.052\n",
"Population attributable risk percent: 97.91% \n",
"\n",
"Chi square: 0.925631790036\n",
"p value: 0.92085506544\n"
]
}
],
"source": [
"epipy.analyze_2x2(table8)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Ordinary least squares regression, used for categorical predictor with continuos outcome. This should be basically the same thing as the first plot shown above.**"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Control is coded 0, exposed is coded 1 (aka 120 in your data). Predictor is treatment, dependent is implantation sites.**"
]
},
{
"cell_type": "code",
"execution_count": 144,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>treatment</th>\n",
" <th>treatment_ord</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>control</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>exposed</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" treatment treatment_ord\n",
"5 control 0\n",
"6 exposed 1"
]
},
"execution_count": 144,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import statsmodels.formula.api as smf\n",
"import statsmodels.api as sm\n",
"\n",
"dat['implant'] = dat['implantation sites']\n",
"dat['treatment_ord'] = pd.Categorical(dat.treatment).labels\n",
"dat[['treatment', 'treatment_ord']][5:7]"
]
},
{
"cell_type": "code",
"execution_count": 130,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"est = smf.ols(formula=\"implant ~ treatment_ord\", data=dat).fit()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Boom. P < .05. Treatment negatively correlated with implantation sites**"
]
},
{
"cell_type": "code",
"execution_count": 131,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<table class=\"simpletable\">\n",
"<caption>OLS Regression Results</caption>\n",
"<tr>\n",
" <th>Dep. Variable:</th> <td>implant</td> <th> R-squared: </th> <td> 0.188</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Model:</th> <td>OLS</td> <th> Adj. R-squared: </th> <td> 0.160</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Method:</th> <td>Least Squares</td> <th> F-statistic: </th> <td> 6.694</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Date:</th> <td>Thu, 11 Jun 2015</td> <th> Prob (F-statistic):</th> <td>0.0150</td> \n",
"</tr>\n",
"<tr>\n",
" <th>Time:</th> <td>11:57:58</td> <th> Log-Likelihood: </th> <td> -90.873</td>\n",
"</tr>\n",
"<tr>\n",
" <th>No. Observations:</th> <td> 31</td> <th> AIC: </th> <td> 185.7</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Df Residuals:</th> <td> 29</td> <th> BIC: </th> <td> 188.6</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Df Model:</th> <td> 1</td> <th> </th> <td> </td> \n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <td></td> <th>coef</th> <th>std err</th> <th>t</th> <th>P>|t|</th> <th>[95.0% Conf. Int.]</th> \n",
"</tr>\n",
"<tr>\n",
" <th>Intercept</th> <td> 12.8000</td> <td> 1.211</td> <td> 10.566</td> <td> 0.000</td> <td> 10.322 15.278</td>\n",
"</tr>\n",
"<tr>\n",
" <th>treatment_ord</th> <td> -4.3625</td> <td> 1.686</td> <td> -2.587</td> <td> 0.015</td> <td> -7.811 -0.914</td>\n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <th>Omnibus:</th> <td> 3.573</td> <th> Durbin-Watson: </th> <td> 1.588</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Prob(Omnibus):</th> <td> 0.168</td> <th> Jarque-Bera (JB): </th> <td> 2.598</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Skew:</th> <td>-0.553</td> <th> Prob(JB): </th> <td> 0.273</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Kurtosis:</th> <td> 2.112</td> <th> Cond. No. </th> <td> 2.66</td>\n",
"</tr>\n",
"</table>"
],
"text/plain": [
"<class 'statsmodels.iolib.summary.Summary'>\n",
"\"\"\"\n",
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: implant R-squared: 0.188\n",
"Model: OLS Adj. R-squared: 0.160\n",
"Method: Least Squares F-statistic: 6.694\n",
"Date: Thu, 11 Jun 2015 Prob (F-statistic): 0.0150\n",
"Time: 11:57:58 Log-Likelihood: -90.873\n",
"No. Observations: 31 AIC: 185.7\n",
"Df Residuals: 29 BIC: 188.6\n",
"Df Model: 1 \n",
"=================================================================================\n",
" coef std err t P>|t| [95.0% Conf. Int.]\n",
"---------------------------------------------------------------------------------\n",
"Intercept 12.8000 1.211 10.566 0.000 10.322 15.278\n",
"treatment_ord -4.3625 1.686 -2.587 0.015 -7.811 -0.914\n",
"==============================================================================\n",
"Omnibus: 3.573 Durbin-Watson: 1.588\n",
"Prob(Omnibus): 0.168 Jarque-Bera (JB): 2.598\n",
"Skew: -0.553 Prob(JB): 0.273\n",
"Kurtosis: 2.112 Cond. No. 2.66\n",
"==============================================================================\n",
"\"\"\""
]
},
"execution_count": 131,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"est.summary()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Here's the plot of that. Again, control is 0 and treatment is 1.**"
]
},
{
"cell_type": "code",
"execution_count": 140,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAEZCAYAAAB1mUk3AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x11362b290>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig = sm.graphics.plot_fit(est, 'treatment_ord')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Repeating that analysis with just 8 week exposures. Fit improves (shown by higher R squared), but results remain consistent and significant.**"
]
},
{
"cell_type": "code",
"execution_count": 146,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/caitlin/anaconda/lib/python2.7/site-packages/scipy/stats/stats.py:1205: UserWarning: kurtosistest only valid for n>=20 ... continuing anyway, n=19\n",
" int(n))\n"
]
},
{
"data": {
"text/html": [
"<table class=\"simpletable\">\n",
"<caption>OLS Regression Results</caption>\n",
"<tr>\n",
" <th>Dep. Variable:</th> <td>implant</td> <th> R-squared: </th> <td> 0.298</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Model:</th> <td>OLS</td> <th> Adj. R-squared: </th> <td> 0.256</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Method:</th> <td>Least Squares</td> <th> F-statistic: </th> <td> 7.203</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Date:</th> <td>Thu, 11 Jun 2015</td> <th> Prob (F-statistic):</th> <td>0.0157</td> \n",
"</tr>\n",
"<tr>\n",
" <th>Time:</th> <td>12:05:47</td> <th> Log-Likelihood: </th> <td> -55.064</td>\n",
"</tr>\n",
"<tr>\n",
" <th>No. Observations:</th> <td> 19</td> <th> AIC: </th> <td> 114.1</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Df Residuals:</th> <td> 17</td> <th> BIC: </th> <td> 116.0</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Df Model:</th> <td> 1</td> <th> </th> <td> </td> \n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <td></td> <th>coef</th> <th>std err</th> <th>t</th> <th>P>|t|</th> <th>[95.0% Conf. Int.]</th> \n",
"</tr>\n",
"<tr>\n",
" <th>Intercept</th> <td> 14.2222</td> <td> 1.547</td> <td> 9.195</td> <td> 0.000</td> <td> 10.959 17.486</td>\n",
"</tr>\n",
"<tr>\n",
" <th>treatment_ord</th> <td> -5.7222</td> <td> 2.132</td> <td> -2.684</td> <td> 0.016</td> <td> -10.221 -1.224</td>\n",
"</tr>\n",
"</table>\n",
"<table class=\"simpletable\">\n",
"<tr>\n",
" <th>Omnibus:</th> <td> 2.194</td> <th> Durbin-Watson: </th> <td> 1.851</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Prob(Omnibus):</th> <td> 0.334</td> <th> Jarque-Bera (JB): </th> <td> 1.745</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Skew:</th> <td>-0.614</td> <th> Prob(JB): </th> <td> 0.418</td>\n",
"</tr>\n",
"<tr>\n",
" <th>Kurtosis:</th> <td> 2.166</td> <th> Cond. No. </th> <td> 2.68</td>\n",
"</tr>\n",
"</table>"
],
"text/plain": [
"<class 'statsmodels.iolib.summary.Summary'>\n",
"\"\"\"\n",
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: implant R-squared: 0.298\n",
"Model: OLS Adj. R-squared: 0.256\n",
"Method: Least Squares F-statistic: 7.203\n",
"Date: Thu, 11 Jun 2015 Prob (F-statistic): 0.0157\n",
"Time: 12:05:47 Log-Likelihood: -55.064\n",
"No. Observations: 19 AIC: 114.1\n",
"Df Residuals: 17 BIC: 116.0\n",
"Df Model: 1 \n",
"=================================================================================\n",
" coef std err t P>|t| [95.0% Conf. Int.]\n",
"---------------------------------------------------------------------------------\n",
"Intercept 14.2222 1.547 9.195 0.000 10.959 17.486\n",
"treatment_ord -5.7222 2.132 -2.684 0.016 -10.221 -1.224\n",
"==============================================================================\n",
"Omnibus: 2.194 Durbin-Watson: 1.851\n",
"Prob(Omnibus): 0.334 Jarque-Bera (JB): 1.745\n",
"Skew: -0.614 Prob(JB): 0.418\n",
"Kurtosis: 2.166 Cond. No. 2.68\n",
"==============================================================================\n",
"\"\"\""
]
},
"execution_count": 146,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"est2 = smf.ols(formula=\"implant ~ treatment_ord\", data=dat[dat.exposure == '8 wk']).fit()\n",
"est2.summary()"
]
},
{
"cell_type": "code",
"execution_count": 148,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAYMAAAEZCAYAAAB1mUk3AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nUREIpwAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x113947490>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig = sm.graphics.plot_fit(est2, 'treatment_ord')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.9"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment