Skip to content

Instantly share code, notes, and snippets.

@ChadFulton
Created October 5, 2017 01:18
Show Gist options
  • Save ChadFulton/30dc02868b6ad35a6b439ac78eb932a5 to your computer and use it in GitHub Desktop.
Save ChadFulton/30dc02868b6ad35a6b439ac78eb932a5 to your computer and use it in GitHub Desktop.
DFM Nonstationary
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAXQAAAD8CAYAAABn919SAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngoQEuhBCBAkJdCGECBIS6EIIEST+P9O9iDm1XGJuAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x10dc780d0>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"%matplotlib inline\n",
"import numpy as np\n",
"import pandas as pd\n",
"import statsmodels.api as sm\n",
"\n",
"dta = sm.datasets.macrodata.load_pandas().data\n",
"dta.index = pd.PeriodIndex(start='1959Q1', end='2009Q3', freq='Q')\n",
"\n",
"endog = np.log(dta[['cpi', 'realcons', 'unemp']])\n",
"\n",
"endog.plot();"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1 factor, AR(2)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.998891285128\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/fulton/projects/statsmodels/statsmodels/base/model.py:511: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
" \"Check mle_retvals\", ConvergenceWarning)\n"
]
}
],
"source": [
"mod1 = sm.tsa.DynamicFactor(endog, k_factors=1, factor_order=2)\n",
"res1 = mod1.fit()\n",
"print(np.max(np.abs(np.linalg.eigvals(mod1['transition']))))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2 factors, VAR(2)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.998264772165\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/fulton/projects/statsmodels/statsmodels/base/model.py:511: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
" \"Check mle_retvals\", ConvergenceWarning)\n"
]
}
],
"source": [
"mod2 = sm.tsa.DynamicFactor(endog, k_factors=2, factor_order=2)\n",
"res2 = mod2.fit()\n",
"print(np.max(np.abs(np.linalg.eigvals(mod2['transition']))))"
]
}
],
"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": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment