{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0a500c14",
   "metadata": {},
   "source": [
    "# Skater Regression"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1847d3c6",
   "metadata": {},
   "source": [
    "### This notebook shows the use of the Skater Regression funcion (Skater_reg), introduced by Anselin & Amaral (2021). For more information on the method, check:\n",
    "https://www.researchgate.net/publication/353411566_Endogenous_Spatial_Regimes"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e4afc8e0",
   "metadata": {},
   "source": [
    "In this example, in addition to the required packages, we will use geopandas to load the data and matplotlib to plot the results. Alternatively, PySAL's own IO could also be used to load the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a7a0de53",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Required imports\n",
    "import libpysal as ps\n",
    "import numpy as np\n",
    "import spreg\n",
    "from spreg.skater_reg import Skater_reg\n",
    "\n",
    "# Optional imports\n",
    "import matplotlib.pyplot as plt\n",
    "import geopandas as gpd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c01ad58d",
   "metadata": {},
   "source": [
    "We use Messner et al. (2000) data on homicides and selected socio-economic characteristics for continental U.S. counties to exemplify the use of Skater_reg. It can be downloaded from PySAL's examples repository."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "52f82039",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load the example from PySAL\n",
    "ps.examples.load_example(\"NCOVR\")\n",
    "data = gpd.read_file(ps.examples.get_path('NAT.shp')).set_index('FIPS')\n",
    "\n",
    "# Set depedent and independent variables and the W matrix.\n",
    "y = data['HR90'].to_numpy()\n",
    "x = data[['RD90','PS90','UE90']].to_numpy()\n",
    "w = ps.weights.Queen.from_dataframe(data, use_index=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25be6fcf",
   "metadata": {},
   "source": [
    "Skater_reg by default uses Euclidean distance to compute the Minimum Spanning Tree (MST). Therefore, we standardize the variables that will be used to compute the MST before calling the main Skater_reg function. Here, we use the X variables to compute the MST. Alternative specifications can be used.\n",
    "\n",
    "We set the number of clusters to 20 and minimum quorum to 100."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ae2bd006",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 1min 16s, sys: 31.6 s, total: 1min 48s\n",
      "Wall time: 25.3 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "# Standardize the variables to be used to compute the minimum spanning tree (could add/remove any variable)\n",
    "x_std = (x - np.mean(x,axis=0)) / np.std(x,axis=0)\n",
    "\n",
    "# Call the Skater_reg method based on OLS\n",
    "results = Skater_reg().fit(20, w, x_std, {'reg':spreg.OLS,'y':y,'x':x}, quorum=100)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "53218349",
   "metadata": {},
   "source": [
    "The intermediate steps are stored in the attibute \\_trace. We can use this information to plot the decrease in the total sum of squared residuals by number of clusters. This information can be helpful to select the number of desired clusters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4e862e49",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "trace = [results._trace[i][1][2] for i in range(1,len(results._trace))]\n",
    "fig, ax = plt.subplots()\n",
    "ax.plot(list(range(2,len(trace)+2)), trace, '-o', color='black', linewidth=2)\n",
    "\n",
    "ax.set(xlabel='Number of clusters', ylabel='Total sum of squared residuals')\n",
    "ax.grid()\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3c6cf08",
   "metadata": {},
   "source": [
    "Let's say we choose 12 clusters. We can plot the results using geopandas and matplotlib."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ff616fb3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(-127.6195011138916, -64.0817699432373, 23.735178565979005, 50.59252300262451)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "data[\"cl_regions\"] = results._trace[11][0]\n",
    "data.plot(column=\"cl_regions\", categorical=True, legend=True, cmap='Paired').axis(\"off\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9bef8f61",
   "metadata": {},
   "source": [
    "With the cluster allocations and selected number of clusters, we can call the Regimes methods in Spreg to get the full regression results and Chow tests on the stability of the coefficients accross the 12 different clusters."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b13e7942",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "REGRESSION\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 0\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  0_['HR90']                Number of Observations:         604\n",
      "Mean dependent var  :      2.4577                Number of Variables   :           4\n",
      "S.D. dependent var  :      3.9266                Degrees of Freedom    :         600\n",
      "R-squared           :      0.3305\n",
      "Adjusted R-squared  :      0.3271\n",
      "Sum squared residual:    6224.952                F-statistic           :     98.7116\n",
      "Sigma-square        :      10.375                Prob(F-statistic)     :   6.109e-52\n",
      "S.E. of regression  :       3.221                Log likelihood        :   -1561.528\n",
      "Sigma-square ML     :      10.306                Akaike info criterion :    3131.057\n",
      "S.E of regression ML:      3.2103                Schwarz criterion     :    3148.671\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          0_CONSTANT       4.0851876       0.4756999       8.5877407       0.0000000\n",
      "              0_RD90       3.1288181       0.2856649      10.9527571       0.0000000\n",
      "              0_PS90       1.4553321       0.1760078       8.2685645       0.0000000\n",
      "              0_UE90       0.0530250       0.0612926       0.8651115       0.3873233\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER            7.255\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2       20184.603           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3          69.424           0.0000\n",
      "Koenker-Bassett test              3           4.695           0.1956\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 1\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  1_['HR90']                Number of Observations:         180\n",
      "Mean dependent var  :      2.6269                Number of Variables   :           4\n",
      "S.D. dependent var  :      4.5592                Degrees of Freedom    :         176\n",
      "R-squared           :      0.1473\n",
      "Adjusted R-squared  :      0.1328\n",
      "Sum squared residual:    3172.661                F-statistic           :     10.1339\n",
      "Sigma-square        :      18.026                Prob(F-statistic)     :   3.424e-06\n",
      "S.E. of regression  :       4.246                Log likelihood        :    -513.652\n",
      "Sigma-square ML     :      17.626                Akaike info criterion :    1035.304\n",
      "S.E of regression ML:      4.1983                Schwarz criterion     :    1048.076\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          1_CONSTANT       1.6802968       1.0041720       1.6733157       0.0960416\n",
      "              1_RD90       0.9214816       0.7386502       1.2475210       0.2138639\n",
      "              1_PS90       0.5520464       0.3817853       1.4459601       0.1499668\n",
      "              1_UE90       0.3793060       0.1012117       3.7476508       0.0002418\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER            6.525\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2        4249.029           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3           6.927           0.0743\n",
      "Koenker-Bassett test              3           0.565           0.9044\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 2\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  2_['HR90']                Number of Observations:         105\n",
      "Mean dependent var  :      5.4586                Number of Variables   :           4\n",
      "S.D. dependent var  :      3.9328                Degrees of Freedom    :         101\n",
      "R-squared           :      0.6004\n",
      "Adjusted R-squared  :      0.5885\n",
      "Sum squared residual:     642.756                F-statistic           :     50.5868\n",
      "Sigma-square        :       6.364                Prob(F-statistic)     :   4.794e-20\n",
      "S.E. of regression  :       2.523                Log likelihood        :    -244.108\n",
      "Sigma-square ML     :       6.121                Akaike info criterion :     496.217\n",
      "S.E of regression ML:      2.4742                Schwarz criterion     :     506.832\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          2_CONSTANT       2.9279569       1.6500241       1.7744934       0.0789946\n",
      "              2_RD90       3.8978472       0.8119511       4.8005936       0.0000055\n",
      "              2_PS90       2.5952604       0.2458875      10.5546660       0.0000000\n",
      "              2_UE90       0.3236171       0.1945793       1.6631633       0.0993799\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER           15.160\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2           6.807           0.0333\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3          15.329           0.0016\n",
      "Koenker-Bassett test              3          14.809           0.0020\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 3\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  3_['HR90']                Number of Observations:         157\n",
      "Mean dependent var  :      3.2521                Number of Variables   :           4\n",
      "S.D. dependent var  :      3.4925                Degrees of Freedom    :         153\n",
      "R-squared           :      0.3735\n",
      "Adjusted R-squared  :      0.3612\n",
      "Sum squared residual:    1192.118                F-statistic           :     30.4049\n",
      "Sigma-square        :       7.792                Prob(F-statistic)     :   1.785e-15\n",
      "S.E. of regression  :       2.791                Log likelihood        :    -381.912\n",
      "Sigma-square ML     :       7.593                Akaike info criterion :     771.824\n",
      "S.E of regression ML:      2.7556                Schwarz criterion     :     784.049\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          3_CONSTANT       1.6648327       1.6499048       1.0090477       0.3145449\n",
      "              3_RD90       2.5911850       0.5446873       4.7571975       0.0000045\n",
      "              3_PS90       1.7951113       0.2645028       6.7867381       0.0000000\n",
      "              3_UE90       0.2831519       0.1896309       1.4931734       0.1374511\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER           17.037\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2         700.804           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3         128.095           0.0000\n",
      "Koenker-Bassett test              3          23.069           0.0000\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 4\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  4_['HR90']                Number of Observations:         157\n",
      "Mean dependent var  :      5.2565                Number of Variables   :           4\n",
      "S.D. dependent var  :      7.5670                Degrees of Freedom    :         153\n",
      "R-squared           :      0.0718\n",
      "Adjusted R-squared  :      0.0536\n",
      "Sum squared residual:    8291.273                F-statistic           :      3.9445\n",
      "Sigma-square        :      54.191                Prob(F-statistic)     :    0.009592\n",
      "S.E. of regression  :       7.361                Log likelihood        :    -534.160\n",
      "Sigma-square ML     :      52.811                Akaike info criterion :    1076.321\n",
      "S.E of regression ML:      7.2671                Schwarz criterion     :    1088.546\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          4_CONSTANT       6.5333323       2.4673414       2.6479239       0.0089474\n",
      "              4_RD90       2.7602351       1.0586310       2.6073627       0.0100275\n",
      "              4_PS90      -0.6252142       0.6065058      -1.0308463       0.3042397\n",
      "              4_UE90      -0.0983422       0.2825469      -0.3480561       0.7282764\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER            9.215\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2       10522.321           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3         397.444           0.0000\n",
      "Koenker-Bassett test              3          19.450           0.0002\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 5\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  5_['HR90']                Number of Observations:         416\n",
      "Mean dependent var  :      3.5350                Number of Variables   :           4\n",
      "S.D. dependent var  :      3.5289                Degrees of Freedom    :         412\n",
      "R-squared           :      0.2384\n",
      "Adjusted R-squared  :      0.2328\n",
      "Sum squared residual:    3936.025                F-statistic           :     42.9870\n",
      "Sigma-square        :       9.553                Prob(F-statistic)     :   3.458e-24\n",
      "S.E. of regression  :       3.091                Log likelihood        :   -1057.705\n",
      "Sigma-square ML     :       9.462                Akaike info criterion :    2123.409\n",
      "S.E of regression ML:      3.0760                Schwarz criterion     :    2139.532\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          5_CONSTANT       3.6580644       0.7883611       4.6400874       0.0000047\n",
      "              5_RD90       2.1705064       0.3732128       5.8157339       0.0000000\n",
      "              5_PS90       1.6485127       0.2143249       7.6916535       0.0000000\n",
      "              5_UE90      -0.0049898       0.0843801      -0.0591343       0.9528738\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER           11.124\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2        2163.820           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3         295.778           0.0000\n",
      "Koenker-Bassett test              3          48.598           0.0000\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 6\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  6_['HR90']                Number of Observations:         105\n",
      "Mean dependent var  :      6.9902                Number of Variables   :           4\n",
      "S.D. dependent var  :      7.7137                Degrees of Freedom    :         101\n",
      "R-squared           :      0.5133\n",
      "Adjusted R-squared  :      0.4989\n",
      "Sum squared residual:    3011.570                F-statistic           :     35.5107\n",
      "Sigma-square        :      29.818                Prob(F-statistic)     :   9.373e-16\n",
      "S.E. of regression  :       5.461                Log likelihood        :    -325.192\n",
      "Sigma-square ML     :      28.682                Akaike info criterion :     658.384\n",
      "S.E of regression ML:      5.3555                Schwarz criterion     :     669.000\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          6_CONSTANT      12.6762323       2.3973782       5.2875396       0.0000007\n",
      "              6_RD90       7.2357749       0.8959392       8.0761894       0.0000000\n",
      "              6_PS90       3.0087836       0.5687185       5.2904618       0.0000007\n",
      "              6_UE90      -0.9087647       0.4285148      -2.1207310       0.0363931\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER           10.336\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2        1082.543           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3          69.868           0.0000\n",
      "Koenker-Bassett test              3           8.330           0.0397\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 7\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  7_['HR90']                Number of Observations:         212\n",
      "Mean dependent var  :      6.7045                Number of Variables   :           4\n",
      "S.D. dependent var  :      7.5062                Degrees of Freedom    :         208\n",
      "R-squared           :      0.6513\n",
      "Adjusted R-squared  :      0.6463\n",
      "Sum squared residual:    4145.470                F-statistic           :    129.5007\n",
      "Sigma-square        :      19.930                Prob(F-statistic)     :   2.429e-47\n",
      "S.E. of regression  :       4.464                Log likelihood        :    -615.973\n",
      "Sigma-square ML     :      19.554                Akaike info criterion :    1239.945\n",
      "S.E of regression ML:      4.4220                Schwarz criterion     :    1253.372\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          7_CONSTANT       6.8749278       1.4815715       4.6402943       0.0000062\n",
      "              7_RD90       5.0735729       0.4720012      10.7490683       0.0000000\n",
      "              7_PS90       4.3257745       0.4290443      10.0823502       0.0000000\n",
      "              7_UE90      -0.1901823       0.2136345      -0.8902227       0.3743748\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER           10.840\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2          23.086           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3          68.023           0.0000\n",
      "Koenker-Bassett test              3          50.360           0.0000\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 8\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  8_['HR90']                Number of Observations:         142\n",
      "Mean dependent var  :      6.9674                Number of Variables   :           4\n",
      "S.D. dependent var  :      7.7639                Degrees of Freedom    :         138\n",
      "R-squared           :      0.0816\n",
      "Adjusted R-squared  :      0.0616\n",
      "Sum squared residual:    7805.895                F-statistic           :      4.0858\n",
      "Sigma-square        :      56.564                Prob(F-statistic)     :    0.008156\n",
      "S.E. of regression  :       7.521                Log likelihood        :    -485.973\n",
      "Sigma-square ML     :      54.971                Akaike info criterion :     979.945\n",
      "S.E of regression ML:      7.4142                Schwarz criterion     :     991.769\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          8_CONSTANT       8.9134518       2.2205952       4.0139922       0.0000975\n",
      "              8_RD90       3.1669956       1.0249618       3.0898670       0.0024224\n",
      "              8_PS90       0.9219418       0.7333370       1.2571872       0.2108094\n",
      "              8_UE90      -0.2902235       0.3083686      -0.9411576       0.3482687\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER            7.818\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2         211.413           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3          16.332           0.0010\n",
      "Koenker-Bassett test              3           4.771           0.1893\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 9\n",
      "---------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  :  9_['HR90']                Number of Observations:         494\n",
      "Mean dependent var  :      9.4357                Number of Variables   :           4\n",
      "S.D. dependent var  :      6.1868                Degrees of Freedom    :         490\n",
      "R-squared           :      0.3161\n",
      "Adjusted R-squared  :      0.3120\n",
      "Sum squared residual:   12904.325                F-statistic           :     75.5098\n",
      "Sigma-square        :      26.335                Prob(F-statistic)     :   3.675e-40\n",
      "S.E. of regression  :       5.132                Log likelihood        :   -1506.863\n",
      "Sigma-square ML     :      26.122                Akaike info criterion :    3021.726\n",
      "S.E of regression ML:      5.1110                Schwarz criterion     :    3038.536\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "          9_CONSTANT      10.2257744       0.7060239      14.4836089       0.0000000\n",
      "              9_RD90       4.9173048       0.3601681      13.6528046       0.0000000\n",
      "              9_PS90       2.7435413       0.3773269       7.2709932       0.0000000\n",
      "              9_UE90      -0.5158999       0.1027098      -5.0228862       0.0000007\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER            7.112\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2         164.804           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3          93.891           0.0000\n",
      "Koenker-Bassett test              3          45.305           0.0000\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 10\n",
      "----------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  : 10_['HR90']                Number of Observations:         322\n",
      "Mean dependent var  :     10.9368                Number of Variables   :           4\n",
      "S.D. dependent var  :      7.1069                Degrees of Freedom    :         318\n",
      "R-squared           :      0.1980\n",
      "Adjusted R-squared  :      0.1904\n",
      "Sum squared residual:   13003.178                F-statistic           :     26.1676\n",
      "Sigma-square        :      40.890                Prob(F-statistic)     :   3.738e-15\n",
      "S.E. of regression  :       6.395                Log likelihood        :   -1052.340\n",
      "Sigma-square ML     :      40.383                Akaike info criterion :    2112.680\n",
      "S.E of regression ML:      6.3547                Schwarz criterion     :    2127.779\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "         10_CONSTANT       8.9613419       1.1548606       7.7596741       0.0000000\n",
      "             10_RD90       3.1036861       0.4676112       6.6373221       0.0000000\n",
      "             10_PS90       2.0054035       0.4775095       4.1997143       0.0000347\n",
      "             10_UE90      -0.1659300       0.1618652      -1.0251118       0.3060896\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER            8.728\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2         805.242           0.0000\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3         271.848           0.0000\n",
      "Koenker-Bassett test              3          60.502           0.0000\n",
      "----------\n",
      "\n",
      "SUMMARY OF OUTPUT: ORDINARY LEAST SQUARES ESTIMATION - REGIME 11\n",
      "----------------------------------------------------------------\n",
      "Data set            :     unknown\n",
      "Weights matrix      :     unknown\n",
      "Dependent Variable  : 11_['HR90']                Number of Observations:         191\n",
      "Mean dependent var  :     12.6163                Number of Variables   :           4\n",
      "S.D. dependent var  :      6.4910                Degrees of Freedom    :         187\n",
      "R-squared           :      0.2010\n",
      "Adjusted R-squared  :      0.1882\n",
      "Sum squared residual:    6396.303                F-statistic           :     15.6792\n",
      "Sigma-square        :      34.205                Prob(F-statistic)     :   3.882e-09\n",
      "S.E. of regression  :       5.848                Log likelihood        :    -606.337\n",
      "Sigma-square ML     :      33.488                Akaike info criterion :    1220.674\n",
      "S.E of regression ML:      5.7869                Schwarz criterion     :    1233.683\n",
      "\n",
      "------------------------------------------------------------------------------------\n",
      "            Variable     Coefficient       Std.Error     t-Statistic     Probability\n",
      "------------------------------------------------------------------------------------\n",
      "         11_CONSTANT      10.6523809       1.8667675       5.7063244       0.0000000\n",
      "             11_RD90       2.8884391       0.5972275       4.8364133       0.0000028\n",
      "             11_PS90       0.2205890       0.5966193       0.3697316       0.7120008\n",
      "             11_UE90      -0.0296635       0.3154386      -0.0940388       0.9251790\n",
      "------------------------------------------------------------------------------------\n",
      "Regimes variable: skater_reg\n",
      "\n",
      "REGRESSION DIAGNOSTICS\n",
      "MULTICOLLINEARITY CONDITION NUMBER           10.444\n",
      "\n",
      "TEST ON NORMALITY OF ERRORS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Jarque-Bera                       2          16.443           0.0003\n",
      "\n",
      "DIAGNOSTICS FOR HETEROSKEDASTICITY\n",
      "RANDOM COEFFICIENTS\n",
      "TEST                             DF        VALUE           PROB\n",
      "Breusch-Pagan test                3          18.499           0.0003\n",
      "Koenker-Bassett test              3          11.542           0.0091\n",
      "\n",
      "REGIMES DIAGNOSTICS - CHOW TEST\n",
      "                 VARIABLE        DF        VALUE           PROB\n",
      "                 CONSTANT        11         110.297           0.0000\n",
      "                     PS90        11          95.473           0.0000\n",
      "                     RD90        11          75.733           0.0000\n",
      "                     UE90        11          52.373           0.0000\n",
      "              Global test        44         532.110           0.0000\n",
      "================================ END OF REPORT =====================================\n"
     ]
    }
   ],
   "source": [
    "reg = spreg.OLS_Regimes(y,x,\n",
    "      regimes=results._trace[11][0], w=w, name_y=['HR90'], name_x=['RD90','PS90','UE90'], name_regimes='skater_reg')\n",
    "print(reg.summary)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "887b4d0d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [conda env:myenv] *",
   "language": "python",
   "name": "conda-env-myenv-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}