{ "cells": [ { "cell_type": "markdown", "metadata": { "pycharm": { "name": "#%% md\n" } }, "source": [ "## ARMA Modeling: Unit Root Testing\n", "\n", "**Functions**\n", "\n", "`sm.tsa.stattools.adfuller`, `arch.unitroot.ADF` \n", "\n", "### Exercise 72\n", "Download data on the AAA and BAA yields (Moodys) from FRED and construct the\n", "default premium as the difference between these two.\n", "\n", "1. Test the default premium for a unit root. \n", "2. If you find a unit root, test the change." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:48.615009Z", "iopub.status.busy": "2021-09-22T10:06:48.615009Z", "iopub.status.idle": "2021-09-22T10:06:50.694379Z", "shell.execute_reply": "2021-09-22T10:06:50.694379Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "outputs": [], "source": [ "import pandas as pd\n", "import pandas_datareader as pdr\n", "\n", "# Conservative start date to get all data\n", "aaa = pdr.get_data_fred(\"AAA\", start=\"1950\")\n", "baa = pdr.get_data_fred(\"BAA\", start=\"1950\")\n", "\n", "default = aaa[\"AAA\"] - baa[\"BAA\"]\n", "default.name = \"Default\"" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:50.699379Z", "iopub.status.busy": "2021-09-22T10:06:50.698379Z", "iopub.status.idle": "2021-09-22T10:06:51.868380Z", "shell.execute_reply": "2021-09-22T10:06:51.868380Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "%matplotlib inline\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "\n", "sns.set_style(\"darkgrid\")\n", "plt.rc(\"figure\", figsize=(16, 6))\n", "plt.rc(\"font\", size=14)\n", "\n", "default.plot.line()" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:51.871378Z", "iopub.status.busy": "2021-09-22T10:06:51.871378Z", "iopub.status.idle": "2021-09-22T10:06:52.421380Z", "shell.execute_reply": "2021-09-22T10:06:52.421380Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Augmented Dickey-Fuller Results
Test Statistic -3.713
P-value 0.022
Lags 17


Trend: Constant and Linear Time Trend
Critical Values: -3.97 (1%), -3.42 (5%), -3.13 (10%)
Null Hypothesis: The process contains a unit root.
Alternative Hypothesis: The process is weakly stationary." ], "text/plain": [ "\n", "\"\"\"\n", " Augmented Dickey-Fuller Results \n", "=====================================\n", "Test Statistic -3.713\n", "P-value 0.022\n", "Lags 17\n", "-------------------------------------\n", "\n", "Trend: Constant and Linear Time Trend\n", "Critical Values: -3.97 (1%), -3.42 (5%), -3.13 (10%)\n", "Null Hypothesis: The process contains a unit root.\n", "Alternative Hypothesis: The process is weakly stationary.\n", "\"\"\"" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from arch.unitroot import ADF\n", "\n", "adf = ADF(default, trend=\"ct\")\n", "adf.summary()" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:52.424377Z", "iopub.status.busy": "2021-09-22T10:06:52.424377Z", "iopub.status.idle": "2021-09-22T10:06:52.453379Z", "shell.execute_reply": "2021-09-22T10:06:52.453379Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "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", "
OLS Regression Results
Dep. Variable: y R-squared: 0.188
Model: OLS Adj. R-squared: 0.170
Method: Least Squares F-statistic: 10.03
Date: Wed, 22 Sep 2021 Prob (F-statistic): 6.71e-27
Time: 11:06:52 Log-Likelihood: 772.34
No. Observations: 842 AIC: -1505.
Df Residuals: 822 BIC: -1410.
Df Model: 19
Covariance Type: nonrobust
\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", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
coef std err t P>|t| [0.025 0.975]
Level.L1 -0.0362 0.010 -3.713 0.000 -0.055 -0.017
Diff.L1 0.3729 0.035 10.653 0.000 0.304 0.442
Diff.L2 -0.1339 0.037 -3.607 0.000 -0.207 -0.061
Diff.L3 0.0228 0.037 0.609 0.542 -0.051 0.096
Diff.L4 -0.0069 0.037 -0.186 0.853 -0.080 0.066
Diff.L5 0.1283 0.037 3.447 0.001 0.055 0.201
Diff.L6 -0.0417 0.037 -1.115 0.265 -0.115 0.032
Diff.L7 -0.0793 0.037 -2.119 0.034 -0.153 -0.006
Diff.L8 -0.0171 0.037 -0.459 0.647 -0.090 0.056
Diff.L9 0.0643 0.037 1.724 0.085 -0.009 0.138
Diff.L10 -0.0815 0.037 -2.182 0.029 -0.155 -0.008
Diff.L11 0.0497 0.037 1.335 0.182 -0.023 0.123
Diff.L12 -0.0386 0.037 -1.040 0.299 -0.112 0.034
Diff.L13 -0.0400 0.037 -1.079 0.281 -0.113 0.033
Diff.L14 0.0815 0.037 2.195 0.028 0.009 0.154
Diff.L15 -0.0342 0.037 -0.918 0.359 -0.107 0.039
Diff.L16 -0.0765 0.037 -2.063 0.039 -0.149 -0.004
Diff.L17 0.0507 0.036 1.421 0.156 -0.019 0.121
const -0.0304 0.010 -3.000 0.003 -0.050 -0.010
trend -1.128e-05 1.46e-05 -0.775 0.438 -3.98e-05 1.73e-05
\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Omnibus: 377.486 Durbin-Watson: 2.001
Prob(Omnibus): 0.000 Jarque-Bera (JB): 7936.768
Skew: -1.521 Prob(JB): 0.00
Kurtosis: 17.730 Cond. No. 8.28e+03


Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 8.28e+03. This might indicate that there are
strong multicollinearity or other numerical problems." ], "text/plain": [ "\n", "\"\"\"\n", " OLS Regression Results \n", "==============================================================================\n", "Dep. Variable: y R-squared: 0.188\n", "Model: OLS Adj. R-squared: 0.170\n", "Method: Least Squares F-statistic: 10.03\n", "Date: Wed, 22 Sep 2021 Prob (F-statistic): 6.71e-27\n", "Time: 11:06:52 Log-Likelihood: 772.34\n", "No. Observations: 842 AIC: -1505.\n", "Df Residuals: 822 BIC: -1410.\n", "Df Model: 19 \n", "Covariance Type: nonrobust \n", "==============================================================================\n", " coef std err t P>|t| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "Level.L1 -0.0362 0.010 -3.713 0.000 -0.055 -0.017\n", "Diff.L1 0.3729 0.035 10.653 0.000 0.304 0.442\n", "Diff.L2 -0.1339 0.037 -3.607 0.000 -0.207 -0.061\n", "Diff.L3 0.0228 0.037 0.609 0.542 -0.051 0.096\n", "Diff.L4 -0.0069 0.037 -0.186 0.853 -0.080 0.066\n", "Diff.L5 0.1283 0.037 3.447 0.001 0.055 0.201\n", "Diff.L6 -0.0417 0.037 -1.115 0.265 -0.115 0.032\n", "Diff.L7 -0.0793 0.037 -2.119 0.034 -0.153 -0.006\n", "Diff.L8 -0.0171 0.037 -0.459 0.647 -0.090 0.056\n", "Diff.L9 0.0643 0.037 1.724 0.085 -0.009 0.138\n", "Diff.L10 -0.0815 0.037 -2.182 0.029 -0.155 -0.008\n", "Diff.L11 0.0497 0.037 1.335 0.182 -0.023 0.123\n", "Diff.L12 -0.0386 0.037 -1.040 0.299 -0.112 0.034\n", "Diff.L13 -0.0400 0.037 -1.079 0.281 -0.113 0.033\n", "Diff.L14 0.0815 0.037 2.195 0.028 0.009 0.154\n", "Diff.L15 -0.0342 0.037 -0.918 0.359 -0.107 0.039\n", "Diff.L16 -0.0765 0.037 -2.063 0.039 -0.149 -0.004\n", "Diff.L17 0.0507 0.036 1.421 0.156 -0.019 0.121\n", "const -0.0304 0.010 -3.000 0.003 -0.050 -0.010\n", "trend -1.128e-05 1.46e-05 -0.775 0.438 -3.98e-05 1.73e-05\n", "==============================================================================\n", "Omnibus: 377.486 Durbin-Watson: 2.001\n", "Prob(Omnibus): 0.000 Jarque-Bera (JB): 7936.768\n", "Skew: -1.521 Prob(JB): 0.00\n", "Kurtosis: 17.730 Cond. No. 8.28e+03\n", "==============================================================================\n", "\n", "Notes:\n", "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", "[2] The condition number is large, 8.28e+03. This might indicate that there are\n", "strong multicollinearity or other numerical problems.\n", "\"\"\"" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "adf.regression.summary()" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:52.456378Z", "iopub.status.busy": "2021-09-22T10:06:52.456378Z", "iopub.status.idle": "2021-09-22T10:06:52.469380Z", "shell.execute_reply": "2021-09-22T10:06:52.469380Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Augmented Dickey-Fuller Results
Test Statistic -3.521
P-value 0.007
Lags 16


Trend: Constant
Critical Values: -3.44 (1%), -2.86 (5%), -2.57 (10%)
Null Hypothesis: The process contains a unit root.
Alternative Hypothesis: The process is weakly stationary." ], "text/plain": [ "\n", "\"\"\"\n", " Augmented Dickey-Fuller Results \n", "=====================================\n", "Test Statistic -3.521\n", "P-value 0.007\n", "Lags 16\n", "-------------------------------------\n", "\n", "Trend: Constant\n", "Critical Values: -3.44 (1%), -2.86 (5%), -2.57 (10%)\n", "Null Hypothesis: The process contains a unit root.\n", "Alternative Hypothesis: The process is weakly stationary.\n", "\"\"\"" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "adf = ADF(default, trend=\"c\")\n", "adf.summary()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:52.484378Z", "iopub.status.busy": "2021-09-22T10:06:52.472381Z", "iopub.status.idle": "2021-09-22T10:06:52.500883Z", "shell.execute_reply": "2021-09-22T10:06:52.500883Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "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", "
OLS Regression Results
Dep. Variable: y R-squared: 0.186
Model: OLS Adj. R-squared: 0.169
Method: Least Squares F-statistic: 11.08
Date: Wed, 22 Sep 2021 Prob (F-statistic): 1.66e-27
Time: 11:06:52 Log-Likelihood: 772.43
No. Observations: 843 AIC: -1509.
Df Residuals: 825 BIC: -1424.
Df Model: 17
Covariance Type: nonrobust
\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", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
coef std err t P>|t| [0.025 0.975]
Level.L1 -0.0325 0.009 -3.521 0.000 -0.051 -0.014
Diff.L1 0.3669 0.035 10.548 0.000 0.299 0.435
Diff.L2 -0.1392 0.037 -3.767 0.000 -0.212 -0.067
Diff.L3 0.0235 0.037 0.632 0.527 -0.050 0.097
Diff.L4 -0.0120 0.037 -0.324 0.746 -0.085 0.061
Diff.L5 0.1234 0.037 3.329 0.001 0.051 0.196
Diff.L6 -0.0425 0.037 -1.138 0.256 -0.116 0.031
Diff.L7 -0.0866 0.037 -2.332 0.020 -0.159 -0.014
Diff.L8 -0.0168 0.037 -0.451 0.652 -0.090 0.056
Diff.L9 0.0607 0.037 1.631 0.103 -0.012 0.134
Diff.L10 -0.0886 0.037 -2.391 0.017 -0.161 -0.016
Diff.L11 0.0448 0.037 1.208 0.228 -0.028 0.118
Diff.L12 -0.0354 0.037 -0.957 0.339 -0.108 0.037
Diff.L13 -0.0425 0.037 -1.146 0.252 -0.115 0.030
Diff.L14 0.0796 0.037 2.146 0.032 0.007 0.152
Diff.L15 -0.0431 0.037 -1.171 0.242 -0.115 0.029
Diff.L16 -0.0603 0.035 -1.720 0.086 -0.129 0.009
const -0.0316 0.009 -3.332 0.001 -0.050 -0.013
\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Omnibus: 379.647 Durbin-Watson: 1.994
Prob(Omnibus): 0.000 Jarque-Bera (JB): 8159.630
Skew: -1.524 Prob(JB): 0.00
Kurtosis: 17.934 Cond. No. 24.1


Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified." ], "text/plain": [ "\n", "\"\"\"\n", " OLS Regression Results \n", "==============================================================================\n", "Dep. Variable: y R-squared: 0.186\n", "Model: OLS Adj. R-squared: 0.169\n", "Method: Least Squares F-statistic: 11.08\n", "Date: Wed, 22 Sep 2021 Prob (F-statistic): 1.66e-27\n", "Time: 11:06:52 Log-Likelihood: 772.43\n", "No. Observations: 843 AIC: -1509.\n", "Df Residuals: 825 BIC: -1424.\n", "Df Model: 17 \n", "Covariance Type: nonrobust \n", "==============================================================================\n", " coef std err t P>|t| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "Level.L1 -0.0325 0.009 -3.521 0.000 -0.051 -0.014\n", "Diff.L1 0.3669 0.035 10.548 0.000 0.299 0.435\n", "Diff.L2 -0.1392 0.037 -3.767 0.000 -0.212 -0.067\n", "Diff.L3 0.0235 0.037 0.632 0.527 -0.050 0.097\n", "Diff.L4 -0.0120 0.037 -0.324 0.746 -0.085 0.061\n", "Diff.L5 0.1234 0.037 3.329 0.001 0.051 0.196\n", "Diff.L6 -0.0425 0.037 -1.138 0.256 -0.116 0.031\n", "Diff.L7 -0.0866 0.037 -2.332 0.020 -0.159 -0.014\n", "Diff.L8 -0.0168 0.037 -0.451 0.652 -0.090 0.056\n", "Diff.L9 0.0607 0.037 1.631 0.103 -0.012 0.134\n", "Diff.L10 -0.0886 0.037 -2.391 0.017 -0.161 -0.016\n", "Diff.L11 0.0448 0.037 1.208 0.228 -0.028 0.118\n", "Diff.L12 -0.0354 0.037 -0.957 0.339 -0.108 0.037\n", "Diff.L13 -0.0425 0.037 -1.146 0.252 -0.115 0.030\n", "Diff.L14 0.0796 0.037 2.146 0.032 0.007 0.152\n", "Diff.L15 -0.0431 0.037 -1.171 0.242 -0.115 0.029\n", "Diff.L16 -0.0603 0.035 -1.720 0.086 -0.129 0.009\n", "const -0.0316 0.009 -3.332 0.001 -0.050 -0.013\n", "==============================================================================\n", "Omnibus: 379.647 Durbin-Watson: 1.994\n", "Prob(Omnibus): 0.000 Jarque-Bera (JB): 8159.630\n", "Skew: -1.524 Prob(JB): 0.00\n", "Kurtosis: 17.934 Cond. No. 24.1\n", "==============================================================================\n", "\n", "Notes:\n", "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", "\"\"\"" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "adf.regression.summary()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Exercise 73\n", "\n", "Download data on consumer prices in the UK from the ONS.\n", "\n", "1. Test the log of CPI for a unit root. \n", "2. If you find a unit root, test inflation for one." ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:52.503883Z", "iopub.status.busy": "2021-09-22T10:06:52.503883Z", "iopub.status.idle": "2021-09-22T10:06:53.083886Z", "shell.execute_reply": "2021-09-22T10:06:53.083886Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import numpy as np\n", "\n", "cpi = pd.read_excel(\"data/uk-cpi-ons.xlsx\", index_col=\"DATE\")\n", "lncpi = np.log(cpi)\n", "plt.rc(\"figure\", figsize=(16, 6))\n", "plt.rc(\"font\", size=14)\n", "\n", "lncpi.plot.line()" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:53.086882Z", "iopub.status.busy": "2021-09-22T10:06:53.086882Z", "iopub.status.idle": "2021-09-22T10:06:53.099884Z", "shell.execute_reply": "2021-09-22T10:06:53.099884Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Augmented Dickey-Fuller Results
Test Statistic -3.972
P-value 0.010
Lags 14


Trend: Constant and Linear Time Trend
Critical Values: -3.98 (1%), -3.42 (5%), -3.13 (10%)
Null Hypothesis: The process contains a unit root.
Alternative Hypothesis: The process is weakly stationary." ], "text/plain": [ "\n", "\"\"\"\n", " Augmented Dickey-Fuller Results \n", "=====================================\n", "Test Statistic -3.972\n", "P-value 0.010\n", "Lags 14\n", "-------------------------------------\n", "\n", "Trend: Constant and Linear Time Trend\n", "Critical Values: -3.98 (1%), -3.42 (5%), -3.13 (10%)\n", "Null Hypothesis: The process contains a unit root.\n", "Alternative Hypothesis: The process is weakly stationary.\n", "\"\"\"" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "adf = ADF(lncpi, trend=\"ct\")\n", "adf.summary()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:53.114883Z", "iopub.status.busy": "2021-09-22T10:06:53.103882Z", "iopub.status.idle": "2021-09-22T10:06:53.131902Z", "shell.execute_reply": "2021-09-22T10:06:53.131902Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "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", "
OLS Regression Results
Dep. Variable: y R-squared: 0.619
Model: OLS Adj. R-squared: 0.601
Method: Least Squares F-statistic: 35.38
Date: Wed, 22 Sep 2021 Prob (F-statistic): 3.66e-63
Time: 11:06:53 Log-Likelihood: 1668.8
No. Observations: 366 AIC: -3304.
Df Residuals: 349 BIC: -3237.
Df Model: 16
Covariance Type: nonrobust
\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", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
coef std err t P>|t| [0.025 0.975]
Level.L1 -0.0200 0.005 -3.972 0.000 -0.030 -0.010
Diff.L1 0.0845 0.052 1.615 0.107 -0.018 0.187
Diff.L2 0.0731 0.052 1.406 0.161 -0.029 0.175
Diff.L3 -0.0121 0.037 -0.325 0.745 -0.085 0.061
Diff.L4 -0.0073 0.037 -0.196 0.845 -0.080 0.066
Diff.L5 -0.0623 0.037 -1.680 0.094 -0.135 0.011
Diff.L6 0.1141 0.037 3.063 0.002 0.041 0.187
Diff.L7 0.0251 0.038 0.666 0.506 -0.049 0.099
Diff.L8 0.0085 0.038 0.226 0.821 -0.066 0.083
Diff.L9 -0.0385 0.037 -1.030 0.304 -0.112 0.035
Diff.L10 -0.0200 0.037 -0.535 0.593 -0.093 0.054
Diff.L11 0.0230 0.037 0.614 0.539 -0.051 0.096
Diff.L12 0.6888 0.037 18.498 0.000 0.616 0.762
Diff.L13 -0.1277 0.052 -2.447 0.015 -0.230 -0.025
Diff.L14 -0.1137 0.052 -2.167 0.031 -0.217 -0.011
const 0.0819 0.020 4.009 0.000 0.042 0.122
trend 3.419e-05 9e-06 3.798 0.000 1.65e-05 5.19e-05
\n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "\n", " \n", "\n", "
Omnibus: 93.523 Durbin-Watson: 1.988
Prob(Omnibus): 0.000 Jarque-Bera (JB): 1069.844
Skew: 0.695 Prob(JB): 4.86e-233
Kurtosis: 11.260 Cond. No. 1.13e+05


Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.13e+05. This might indicate that there are
strong multicollinearity or other numerical problems." ], "text/plain": [ "\n", "\"\"\"\n", " OLS Regression Results \n", "==============================================================================\n", "Dep. Variable: y R-squared: 0.619\n", "Model: OLS Adj. R-squared: 0.601\n", "Method: Least Squares F-statistic: 35.38\n", "Date: Wed, 22 Sep 2021 Prob (F-statistic): 3.66e-63\n", "Time: 11:06:53 Log-Likelihood: 1668.8\n", "No. Observations: 366 AIC: -3304.\n", "Df Residuals: 349 BIC: -3237.\n", "Df Model: 16 \n", "Covariance Type: nonrobust \n", "==============================================================================\n", " coef std err t P>|t| [0.025 0.975]\n", "------------------------------------------------------------------------------\n", "Level.L1 -0.0200 0.005 -3.972 0.000 -0.030 -0.010\n", "Diff.L1 0.0845 0.052 1.615 0.107 -0.018 0.187\n", "Diff.L2 0.0731 0.052 1.406 0.161 -0.029 0.175\n", "Diff.L3 -0.0121 0.037 -0.325 0.745 -0.085 0.061\n", "Diff.L4 -0.0073 0.037 -0.196 0.845 -0.080 0.066\n", "Diff.L5 -0.0623 0.037 -1.680 0.094 -0.135 0.011\n", "Diff.L6 0.1141 0.037 3.063 0.002 0.041 0.187\n", "Diff.L7 0.0251 0.038 0.666 0.506 -0.049 0.099\n", "Diff.L8 0.0085 0.038 0.226 0.821 -0.066 0.083\n", "Diff.L9 -0.0385 0.037 -1.030 0.304 -0.112 0.035\n", "Diff.L10 -0.0200 0.037 -0.535 0.593 -0.093 0.054\n", "Diff.L11 0.0230 0.037 0.614 0.539 -0.051 0.096\n", "Diff.L12 0.6888 0.037 18.498 0.000 0.616 0.762\n", "Diff.L13 -0.1277 0.052 -2.447 0.015 -0.230 -0.025\n", "Diff.L14 -0.1137 0.052 -2.167 0.031 -0.217 -0.011\n", "const 0.0819 0.020 4.009 0.000 0.042 0.122\n", "trend 3.419e-05 9e-06 3.798 0.000 1.65e-05 5.19e-05\n", "==============================================================================\n", "Omnibus: 93.523 Durbin-Watson: 1.988\n", "Prob(Omnibus): 0.000 Jarque-Bera (JB): 1069.844\n", "Skew: 0.695 Prob(JB): 4.86e-233\n", "Kurtosis: 11.260 Cond. No. 1.13e+05\n", "==============================================================================\n", "\n", "Notes:\n", "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n", "[2] The condition number is large, 1.13e+05. This might indicate that there are\n", "strong multicollinearity or other numerical problems.\n", "\"\"\"" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "adf.regression.summary()" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:53.133899Z", "iopub.status.busy": "2021-09-22T10:06:53.133899Z", "iopub.status.idle": "2021-09-22T10:06:53.243900Z", "shell.execute_reply": "2021-09-22T10:06:53.242901Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" } }, "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", " \n", " \n", "
CPIconsttrend
DATE
1988-01-013.8793971.01.0
1988-02-013.8826151.02.0
1988-03-013.8860281.03.0
1988-04-013.8975181.04.0
1988-05-013.9025581.05.0
\n", "
" ], "text/plain": [ " CPI const trend\n", "DATE \n", "1988-01-01 3.879397 1.0 1.0\n", "1988-02-01 3.882615 1.0 2.0\n", "1988-03-01 3.886028 1.0 3.0\n", "1988-04-01 3.897518 1.0 4.0\n", "1988-05-01 3.902558 1.0 5.0" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "import statsmodels.tsa.api as tsa\n", "\n", "with_trend = tsa.add_trend(lncpi, trend=\"ct\")\n", "with_trend.head()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "execution": { "iopub.execute_input": "2021-09-22T10:06:53.247900Z", "iopub.status.busy": "2021-09-22T10:06:53.246903Z", "iopub.status.idle": "2021-09-22T10:06:53.805900Z", "shell.execute_reply": "2021-09-22T10:06:53.805900Z" }, "pycharm": { "is_executing": false, "name": "#%%\n" }, "tags": [] }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import statsmodels.api as sm\n", "\n", "res = sm.OLS(with_trend[\"CPI\"], with_trend[[\"const\", \"trend\"]]).fit()\n", "\n", "plt.rc(\"figure\", figsize=(16, 6))\n", "res.resid.plot.line()" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.9.6" }, "pycharm": { "stem_cell": { "cell_type": "raw", "metadata": { "collapsed": false }, "source": [] } } }, "nbformat": 4, "nbformat_minor": 4 }