├── README.md
├── .gitignore
└── PS01-labor_in_Malawi.ipynb


/README.md:
--------------------------------------------------------------------------------
1 | # Reproduction of Economic papers using python 3.0
2 | I decided to start a series of reproducing economics papers using Python.
3 | I will try to get the same results, using their data, that are shown in the paper, however, I will concentrate on how they came to the conclusion of choosing that particular model and explaining all the minor findings.
4 | The purpose of this repository is to post reproductions of the results of famous economic papers using python. In lieu of general codes, I'll concentrate on analyzing findings.
5 | 


--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
  1 | # Byte-compiled / optimized / DLL files
  2 | __pycache__/
  3 | *.py[cod]
  4 | *$py.class
  5 | 
  6 | # C extensions
  7 | *.so
  8 | 
  9 | # Distribution / packaging
 10 | .Python
 11 | build/
 12 | develop-eggs/
 13 | dist/
 14 | downloads/
 15 | eggs/
 16 | .eggs/
 17 | lib/
 18 | lib64/
 19 | parts/
 20 | sdist/
 21 | var/
 22 | wheels/
 23 | pip-wheel-metadata/
 24 | share/python-wheels/
 25 | *.egg-info/
 26 | .installed.cfg
 27 | *.egg
 28 | MANIFEST
 29 | 
 30 | # PyInstaller
 31 | #  Usually these files are written by a python script from a template
 32 | #  before PyInstaller builds the exe, so as to inject date/other infos into it.
 33 | *.manifest
 34 | *.spec
 35 | 
 36 | # Installer logs
 37 | pip-log.txt
 38 | pip-delete-this-directory.txt
 39 | 
 40 | # Unit test / coverage reports
 41 | htmlcov/
 42 | .tox/
 43 | .nox/
 44 | .coverage
 45 | .coverage.*
 46 | .cache
 47 | nosetests.xml
 48 | coverage.xml
 49 | *.cover
 50 | *.py,cover
 51 | .hypothesis/
 52 | .pytest_cache/
 53 | 
 54 | # Translations
 55 | *.mo
 56 | *.pot
 57 | 
 58 | # Django stuff:
 59 | *.log
 60 | local_settings.py
 61 | db.sqlite3
 62 | db.sqlite3-journal
 63 | 
 64 | # Flask stuff:
 65 | instance/
 66 | .webassets-cache
 67 | 
 68 | # Scrapy stuff:
 69 | .scrapy
 70 | 
 71 | # Sphinx documentation
 72 | docs/_build/
 73 | 
 74 | # PyBuilder
 75 | target/
 76 | 
 77 | # Jupyter Notebook
 78 | .ipynb_checkpoints
 79 | 
 80 | # IPython
 81 | profile_default/
 82 | ipython_config.py
 83 | 
 84 | # pyenv
 85 | .python-version
 86 | 
 87 | # pipenv
 88 | #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
 89 | #   However, in case of collaboration, if having platform-specific dependencies or dependencies
 90 | #   having no cross-platform support, pipenv may install dependencies that don't work, or not
 91 | #   install all needed dependencies.
 92 | #Pipfile.lock
 93 | 
 94 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow
 95 | __pypackages__/
 96 | 
 97 | # Celery stuff
 98 | celerybeat-schedule
 99 | celerybeat.pid
100 | 
101 | # SageMath parsed files
102 | *.sage.py
103 | 
104 | # Environments
105 | .env
106 | .venv
107 | env/
108 | venv/
109 | ENV/
110 | env.bak/
111 | venv.bak/
112 | 
113 | # Spyder project settings
114 | .spyderproject
115 | .spyproject
116 | 
117 | # Rope project settings
118 | .ropeproject
119 | 
120 | # mkdocs documentation
121 | /site
122 | 
123 | # mypy
124 | .mypy_cache/
125 | .dmypy.json
126 | dmypy.json
127 | 
128 | # Pyre type checker
129 | .pyre/
130 | 


--------------------------------------------------------------------------------
/PS01-labor_in_Malawi.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "metadata": {},
   6 |    "source": [
   7 |     "# Problem Solving 01\n",
   8 |     "_____\n",
   9 |     "## Replication of a paper published by Dr. Jessica Goldberg - \"Experimental Evidence about Labor Supply in Rural Malawi\"\n",
  10 |     "\n",
  11 |     "> #### Original paper, published by **_American Economic Journal_** in 2016 can be found **[here](https://drive.google.com/file/d/18QQqtV2gj5xQBtjcXm9OIFUcILiN7vYD/view?usp=sharing)**\n",
  12 |     "\n",
  13 |     "_______________________\n",
  14 |     "\n",
  15 |     "In this session, we work on a paper that analysis labor supply in Malawi in an experimental setting.\n",
  16 |     "\n",
  17 |     "_Abstract: I use a field experiment to estimate the wage elasticity of employment in the day labor market in rural Malawi. Once a week for 12 consecutive weeks, I make job offers for a workfare-type program to 529 adults. The daily wage varies from the tenth to the ninetieth percentile of the wage distribution, and individuals are entitled to work a maximum of one day per week. In this context (the low agricultural season), 74 percent of individuals worked at the lowest wage, and consequently the estimated labor supply elasticity is low (0.15), regardless of observable characteristics._\n",
  18 |     "\n",
  19 |     "The paper uses data collected by the author and her colleagues in Malawi. They randomly offered jobs with different wages to individuals in 10 villages for 12 consecutive weeks and recorded acceptance rates. They used data to estimate the elasticity of labor supply to wage. \n",
  20 |     "The variable of interest in this paper is acceptance rate in each village in each week and the explanatory variable is wage.\n",
  21 |     "\n",
  22 |     "The other explanatory variables may be variables that distinguish each village from the others.\n",
  23 |     "\n",
  24 |     "The main finding of the paper is that in the off-season, the majority of workers accept the job offer at the lowest wage, and the elasticity of labor is low, meaning that the main force of accepting job is probably factors beyond wage."
  25 |    ]
  26 |   },
  27 |   {
  28 |    "cell_type": "markdown",
  29 |    "metadata": {},
  30 |    "source": [
  31 |     "_loading all the neccessary tools needed for the project:_"
  32 |    ]
  33 |   },
  34 |   {
  35 |    "cell_type": "code",
  36 |    "execution_count": 1,
  37 |    "metadata": {},
  38 |    "outputs": [],
  39 |    "source": [
  40 |     "%%capture\n",
  41 |     "! pip install seaborn\n",
  42 |     "import seaborn as sns\n",
  43 |     "import matplotlib.pyplot as plt\n",
  44 |     "%matplotlib inline\n",
  45 |     "import numpy as np\n",
  46 |     "import pandas as pd\n",
  47 |     "from matplotlib.ticker import StrMethodFormatter"
  48 |    ]
  49 |   },
  50 |   {
  51 |    "cell_type": "markdown",
  52 |    "metadata": {},
  53 |    "source": [
  54 |     "## Part 1\n",
  55 |     "-----\n",
  56 |     "loading the dataset"
  57 |    ]
  58 |   },
  59 |   {
  60 |    "cell_type": "code",
  61 |    "execution_count": 2,
  62 |    "metadata": {},
  63 |    "outputs": [
  64 |     {
  65 |      "data": {
  66 |       "text/html": [
  67 |        "<div>\n",
  68 |        "<style scoped>\n",
  69 |        "    .dataframe tbody tr th:only-of-type {\n",
  70 |        "        vertical-align: middle;\n",
  71 |        "    }\n",
  72 |        "\n",
  73 |        "    .dataframe tbody tr th {\n",
  74 |        "        vertical-align: top;\n",
  75 |        "    }\n",
  76 |        "\n",
  77 |        "    .dataframe thead th {\n",
  78 |        "        text-align: right;\n",
  79 |        "    }\n",
  80 |        "</style>\n",
  81 |        "<table border=\"1\" class=\"dataframe\">\n",
  82 |        "  <thead>\n",
  83 |        "    <tr style=\"text-align: right;\">\n",
  84 |        "      <th></th>\n",
  85 |        "      <th>week</th>\n",
  86 |        "      <th>village</th>\n",
  87 |        "      <th>vil_labor</th>\n",
  88 |        "      <th>vil_hh</th>\n",
  89 |        "      <th>badshock_prev</th>\n",
  90 |        "      <th>goodshock_prev</th>\n",
  91 |        "      <th>badshock_prev_lnwage</th>\n",
  92 |        "      <th>goodshock_prev_lnwage</th>\n",
  93 |        "      <th>wage</th>\n",
  94 |        "      <th>lnwage</th>\n",
  95 |        "      <th>...</th>\n",
  96 |        "      <th>wagedum3</th>\n",
  97 |        "      <th>wagedum4</th>\n",
  98 |        "      <th>wagedum5</th>\n",
  99 |        "      <th>wagedum6</th>\n",
 100 |        "      <th>wagedum7</th>\n",
 101 |        "      <th>wagedum8</th>\n",
 102 |        "      <th>wagedum9</th>\n",
 103 |        "      <th>wagedum10</th>\n",
 104 |        "      <th>wagedum11</th>\n",
 105 |        "      <th>wagedum12</th>\n",
 106 |        "    </tr>\n",
 107 |        "  </thead>\n",
 108 |        "  <tbody>\n",
 109 |        "    <tr>\n",
 110 |        "      <td>0</td>\n",
 111 |        "      <td>1</td>\n",
 112 |        "      <td>CHIMOWA</td>\n",
 113 |        "      <td>1.000000</td>\n",
 114 |        "      <td>1.0000</td>\n",
 115 |        "      <td>NaN</td>\n",
 116 |        "      <td>NaN</td>\n",
 117 |        "      <td>NaN</td>\n",
 118 |        "      <td>NaN</td>\n",
 119 |        "      <td>100.0</td>\n",
 120 |        "      <td>4.605170</td>\n",
 121 |        "      <td>...</td>\n",
 122 |        "      <td>0</td>\n",
 123 |        "      <td>0</td>\n",
 124 |        "      <td>0</td>\n",
 125 |        "      <td>0</td>\n",
 126 |        "      <td>0</td>\n",
 127 |        "      <td>1</td>\n",
 128 |        "      <td>0</td>\n",
 129 |        "      <td>0</td>\n",
 130 |        "      <td>0</td>\n",
 131 |        "      <td>0</td>\n",
 132 |        "    </tr>\n",
 133 |        "    <tr>\n",
 134 |        "      <td>1</td>\n",
 135 |        "      <td>2</td>\n",
 136 |        "      <td>CHIMOWA</td>\n",
 137 |        "      <td>0.857143</td>\n",
 138 |        "      <td>0.7500</td>\n",
 139 |        "      <td>0.285714</td>\n",
 140 |        "      <td>0.326531</td>\n",
 141 |        "      <td>1.169813</td>\n",
 142 |        "      <td>1.336929</td>\n",
 143 |        "      <td>60.0</td>\n",
 144 |        "      <td>4.094345</td>\n",
 145 |        "      <td>...</td>\n",
 146 |        "      <td>0</td>\n",
 147 |        "      <td>1</td>\n",
 148 |        "      <td>0</td>\n",
 149 |        "      <td>0</td>\n",
 150 |        "      <td>0</td>\n",
 151 |        "      <td>0</td>\n",
 152 |        "      <td>0</td>\n",
 153 |        "      <td>0</td>\n",
 154 |        "      <td>0</td>\n",
 155 |        "      <td>0</td>\n",
 156 |        "    </tr>\n",
 157 |        "    <tr>\n",
 158 |        "      <td>2</td>\n",
 159 |        "      <td>3</td>\n",
 160 |        "      <td>CHIMOWA</td>\n",
 161 |        "      <td>0.000000</td>\n",
 162 |        "      <td>0.0000</td>\n",
 163 |        "      <td>0.448980</td>\n",
 164 |        "      <td>0.306122</td>\n",
 165 |        "      <td>2.149486</td>\n",
 166 |        "      <td>1.465559</td>\n",
 167 |        "      <td>120.0</td>\n",
 168 |        "      <td>4.787492</td>\n",
 169 |        "      <td>...</td>\n",
 170 |        "      <td>0</td>\n",
 171 |        "      <td>0</td>\n",
 172 |        "      <td>0</td>\n",
 173 |        "      <td>0</td>\n",
 174 |        "      <td>0</td>\n",
 175 |        "      <td>0</td>\n",
 176 |        "      <td>0</td>\n",
 177 |        "      <td>1</td>\n",
 178 |        "      <td>0</td>\n",
 179 |        "      <td>0</td>\n",
 180 |        "    </tr>\n",
 181 |        "    <tr>\n",
 182 |        "      <td>3</td>\n",
 183 |        "      <td>4</td>\n",
 184 |        "      <td>CHIMOWA</td>\n",
 185 |        "      <td>0.897959</td>\n",
 186 |        "      <td>0.8125</td>\n",
 187 |        "      <td>0.918367</td>\n",
 188 |        "      <td>0.183673</td>\n",
 189 |        "      <td>3.123549</td>\n",
 190 |        "      <td>0.624710</td>\n",
 191 |        "      <td>30.0</td>\n",
 192 |        "      <td>3.401197</td>\n",
 193 |        "      <td>...</td>\n",
 194 |        "      <td>0</td>\n",
 195 |        "      <td>0</td>\n",
 196 |        "      <td>0</td>\n",
 197 |        "      <td>0</td>\n",
 198 |        "      <td>0</td>\n",
 199 |        "      <td>0</td>\n",
 200 |        "      <td>0</td>\n",
 201 |        "      <td>0</td>\n",
 202 |        "      <td>0</td>\n",
 203 |        "      <td>0</td>\n",
 204 |        "    </tr>\n",
 205 |        "    <tr>\n",
 206 |        "      <td>4</td>\n",
 207 |        "      <td>5</td>\n",
 208 |        "      <td>CHIMOWA</td>\n",
 209 |        "      <td>1.000000</td>\n",
 210 |        "      <td>1.0000</td>\n",
 211 |        "      <td>0.204082</td>\n",
 212 |        "      <td>0.183673</td>\n",
 213 |        "      <td>0.959282</td>\n",
 214 |        "      <td>0.863354</td>\n",
 215 |        "      <td>110.0</td>\n",
 216 |        "      <td>4.700480</td>\n",
 217 |        "      <td>...</td>\n",
 218 |        "      <td>0</td>\n",
 219 |        "      <td>0</td>\n",
 220 |        "      <td>0</td>\n",
 221 |        "      <td>0</td>\n",
 222 |        "      <td>0</td>\n",
 223 |        "      <td>0</td>\n",
 224 |        "      <td>1</td>\n",
 225 |        "      <td>0</td>\n",
 226 |        "      <td>0</td>\n",
 227 |        "      <td>0</td>\n",
 228 |        "    </tr>\n",
 229 |        "  </tbody>\n",
 230 |        "</table>\n",
 231 |        "<p>5 rows × 29 columns</p>\n",
 232 |        "</div>"
 233 |       ],
 234 |       "text/plain": [
 235 |        "   week  village  vil_labor  vil_hh  badshock_prev  goodshock_prev  \\\n",
 236 |        "0     1  CHIMOWA   1.000000  1.0000            NaN             NaN   \n",
 237 |        "1     2  CHIMOWA   0.857143  0.7500       0.285714        0.326531   \n",
 238 |        "2     3  CHIMOWA   0.000000  0.0000       0.448980        0.306122   \n",
 239 |        "3     4  CHIMOWA   0.897959  0.8125       0.918367        0.183673   \n",
 240 |        "4     5  CHIMOWA   1.000000  1.0000       0.204082        0.183673   \n",
 241 |        "\n",
 242 |        "   badshock_prev_lnwage  goodshock_prev_lnwage   wage    lnwage  ...  \\\n",
 243 |        "0                   NaN                    NaN  100.0  4.605170  ...   \n",
 244 |        "1              1.169813               1.336929   60.0  4.094345  ...   \n",
 245 |        "2              2.149486               1.465559  120.0  4.787492  ...   \n",
 246 |        "3              3.123549               0.624710   30.0  3.401197  ...   \n",
 247 |        "4              0.959282               0.863354  110.0  4.700480  ...   \n",
 248 |        "\n",
 249 |        "   wagedum3  wagedum4  wagedum5  wagedum6  wagedum7  wagedum8  wagedum9  \\\n",
 250 |        "0         0         0         0         0         0         1         0   \n",
 251 |        "1         0         1         0         0         0         0         0   \n",
 252 |        "2         0         0         0         0         0         0         0   \n",
 253 |        "3         0         0         0         0         0         0         0   \n",
 254 |        "4         0         0         0         0         0         0         1   \n",
 255 |        "\n",
 256 |        "   wagedum10  wagedum11  wagedum12  \n",
 257 |        "0          0          0          0  \n",
 258 |        "1          0          0          0  \n",
 259 |        "2          1          0          0  \n",
 260 |        "3          0          0          0  \n",
 261 |        "4          0          0          0  \n",
 262 |        "\n",
 263 |        "[5 rows x 29 columns]"
 264 |       ]
 265 |      },
 266 |      "execution_count": 2,
 267 |      "metadata": {},
 268 |      "output_type": "execute_result"
 269 |     }
 270 |    ],
 271 |    "source": [
 272 |     "path = \"PS03.dta\"\n",
 273 |     "df = pd.read_stata(path)\n",
 274 |     "df.head(5)"
 275 |    ]
 276 |   },
 277 |   {
 278 |    "cell_type": "markdown",
 279 |    "metadata": {},
 280 |    "source": [
 281 |     "### 1.a) First, we have to know our variable of interest, acceptance rate, and the main explanatory variable, wage."
 282 |    ]
 283 |   },
 284 |   {
 285 |    "cell_type": "code",
 286 |    "execution_count": 3,
 287 |    "metadata": {},
 288 |    "outputs": [
 289 |     {
 290 |      "data": {
 291 |       "text/plain": [
 292 |        "count    120.000000\n",
 293 |        "mean       0.845476\n",
 294 |        "std        0.171205\n",
 295 |        "min        0.000000\n",
 296 |        "25%        0.809310\n",
 297 |        "50%        0.907692\n",
 298 |        "75%        0.958333\n",
 299 |        "max        1.000000\n",
 300 |        "Name: vil_labor, dtype: float64"
 301 |       ]
 302 |      },
 303 |      "execution_count": 3,
 304 |      "metadata": {},
 305 |      "output_type": "execute_result"
 306 |     }
 307 |    ],
 308 |    "source": [
 309 |     "df['vil_labor'].describe()"
 310 |    ]
 311 |   },
 312 |   {
 313 |    "cell_type": "markdown",
 314 |    "metadata": {},
 315 |    "source": [
 316 |     "By observing dependent variable <code>'vil_labor'</code> we see that the average acceptance rate among the villages was **84%**"
 317 |    ]
 318 |   },
 319 |   {
 320 |    "cell_type": "code",
 321 |    "execution_count": 4,
 322 |    "metadata": {},
 323 |    "outputs": [
 324 |     {
 325 |      "data": {
 326 |       "text/plain": [
 327 |        "count    120.000000\n",
 328 |        "mean      85.000000\n",
 329 |        "std       34.665264\n",
 330 |        "min       30.000000\n",
 331 |        "25%       57.500000\n",
 332 |        "50%       85.000000\n",
 333 |        "75%      112.500000\n",
 334 |        "max      140.000000\n",
 335 |        "Name: wage, dtype: float64"
 336 |       ]
 337 |      },
 338 |      "execution_count": 4,
 339 |      "metadata": {},
 340 |      "output_type": "execute_result"
 341 |     }
 342 |    ],
 343 |    "source": [
 344 |     "df['wage'].describe()"
 345 |    ]
 346 |   },
 347 |   {
 348 |    "cell_type": "markdown",
 349 |    "metadata": {},
 350 |    "source": [
 351 |     "By observing independent variable <code>'wage'</code> we see that the average offered wage among the villages was **85** Malawi Kwacha"
 352 |    ]
 353 |   },
 354 |   {
 355 |    "cell_type": "code",
 356 |    "execution_count": 5,
 357 |    "metadata": {},
 358 |    "outputs": [
 359 |     {
 360 |      "data": {
 361 |       "text/plain": [
 362 |        "Text(0.5, 1.0, 'Histogram for the A-Rate ')"
 363 |       ]
 364 |      },
 365 |      "execution_count": 5,
 366 |      "metadata": {},
 367 |      "output_type": "execute_result"
 368 |     },
 369 |     {
 370 |      "data": {
 371 |       "image/png": "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\n",
 372 |       "text/plain": [
 373 |        "<Figure size 432x288 with 1 Axes>"
 374 |       ]
 375 |      },
 376 |      "metadata": {
 377 |       "needs_background": "light"
 378 |      },
 379 |      "output_type": "display_data"
 380 |     }
 381 |    ],
 382 |    "source": [
 383 |     "y = df['vil_labor']\n",
 384 |     "plt.hist(y, color='green', zorder=2, rwidth=0.95)\n",
 385 |     "plt.grid(axis='y', alpha=0.75)\n",
 386 |     "plt.grid(axis='x', alpha=0.75)\n",
 387 |     "plt.ylabel('Frequency',fontsize=12)\n",
 388 |     "plt.xlabel('Acceptance Rate',fontsize=12)\n",
 389 |     "plt.title('Histogram for the A-Rate ',fontsize=15)"
 390 |    ]
 391 |   },
 392 |   {
 393 |    "cell_type": "markdown",
 394 |    "metadata": {},
 395 |    "source": []
 396 |   },
 397 |   {
 398 |    "cell_type": "markdown",
 399 |    "metadata": {},
 400 |    "source": [
 401 |     "### 1.b) I'll Find the mean and standard deviation of acceptance rate for the 20 observations with the lowest wage, 20 observations with the highest wage."
 402 |    ]
 403 |   },
 404 |   {
 405 |    "cell_type": "code",
 406 |    "execution_count": 6,
 407 |    "metadata": {},
 408 |    "outputs": [
 409 |     {
 410 |      "data": {
 411 |       "text/html": [
 412 |        "<div>\n",
 413 |        "<style scoped>\n",
 414 |        "    .dataframe tbody tr th:only-of-type {\n",
 415 |        "        vertical-align: middle;\n",
 416 |        "    }\n",
 417 |        "\n",
 418 |        "    .dataframe tbody tr th {\n",
 419 |        "        vertical-align: top;\n",
 420 |        "    }\n",
 421 |        "\n",
 422 |        "    .dataframe thead th {\n",
 423 |        "        text-align: right;\n",
 424 |        "    }\n",
 425 |        "</style>\n",
 426 |        "<table border=\"1\" class=\"dataframe\">\n",
 427 |        "  <thead>\n",
 428 |        "    <tr style=\"text-align: right;\">\n",
 429 |        "      <th></th>\n",
 430 |        "      <th>wage</th>\n",
 431 |        "      <th>vil_labor</th>\n",
 432 |        "    </tr>\n",
 433 |        "  </thead>\n",
 434 |        "  <tbody>\n",
 435 |        "    <tr>\n",
 436 |        "      <td>count</td>\n",
 437 |        "      <td>20.000000</td>\n",
 438 |        "      <td>20.000000</td>\n",
 439 |        "    </tr>\n",
 440 |        "    <tr>\n",
 441 |        "      <td>mean</td>\n",
 442 |        "      <td>135.000000</td>\n",
 443 |        "      <td>0.936237</td>\n",
 444 |        "    </tr>\n",
 445 |        "    <tr>\n",
 446 |        "      <td>std</td>\n",
 447 |        "      <td>5.129892</td>\n",
 448 |        "      <td>0.048356</td>\n",
 449 |        "    </tr>\n",
 450 |        "    <tr>\n",
 451 |        "      <td>min</td>\n",
 452 |        "      <td>130.000000</td>\n",
 453 |        "      <td>0.836735</td>\n",
 454 |        "    </tr>\n",
 455 |        "    <tr>\n",
 456 |        "      <td>25%</td>\n",
 457 |        "      <td>130.000000</td>\n",
 458 |        "      <td>0.902071</td>\n",
 459 |        "    </tr>\n",
 460 |        "    <tr>\n",
 461 |        "      <td>50%</td>\n",
 462 |        "      <td>135.000000</td>\n",
 463 |        "      <td>0.950820</td>\n",
 464 |        "    </tr>\n",
 465 |        "    <tr>\n",
 466 |        "      <td>75%</td>\n",
 467 |        "      <td>140.000000</td>\n",
 468 |        "      <td>0.978941</td>\n",
 469 |        "    </tr>\n",
 470 |        "    <tr>\n",
 471 |        "      <td>max</td>\n",
 472 |        "      <td>140.000000</td>\n",
 473 |        "      <td>1.000000</td>\n",
 474 |        "    </tr>\n",
 475 |        "  </tbody>\n",
 476 |        "</table>\n",
 477 |        "</div>"
 478 |       ],
 479 |       "text/plain": [
 480 |        "             wage  vil_labor\n",
 481 |        "count   20.000000  20.000000\n",
 482 |        "mean   135.000000   0.936237\n",
 483 |        "std      5.129892   0.048356\n",
 484 |        "min    130.000000   0.836735\n",
 485 |        "25%    130.000000   0.902071\n",
 486 |        "50%    135.000000   0.950820\n",
 487 |        "75%    140.000000   0.978941\n",
 488 |        "max    140.000000   1.000000"
 489 |       ]
 490 |      },
 491 |      "execution_count": 6,
 492 |      "metadata": {},
 493 |      "output_type": "execute_result"
 494 |     }
 495 |    ],
 496 |    "source": [
 497 |     "df_wage_labor = df[['wage', 'vil_labor']]\n",
 498 |     "top20 = df_wage_labor.nlargest(20, ['wage', 'vil_labor'])\n",
 499 |     "top20.describe()"
 500 |    ]
 501 |   },
 502 |   {
 503 |    "cell_type": "code",
 504 |    "execution_count": 7,
 505 |    "metadata": {},
 506 |    "outputs": [
 507 |     {
 508 |      "data": {
 509 |       "text/html": [
 510 |        "<div>\n",
 511 |        "<style scoped>\n",
 512 |        "    .dataframe tbody tr th:only-of-type {\n",
 513 |        "        vertical-align: middle;\n",
 514 |        "    }\n",
 515 |        "\n",
 516 |        "    .dataframe tbody tr th {\n",
 517 |        "        vertical-align: top;\n",
 518 |        "    }\n",
 519 |        "\n",
 520 |        "    .dataframe thead th {\n",
 521 |        "        text-align: right;\n",
 522 |        "    }\n",
 523 |        "</style>\n",
 524 |        "<table border=\"1\" class=\"dataframe\">\n",
 525 |        "  <thead>\n",
 526 |        "    <tr style=\"text-align: right;\">\n",
 527 |        "      <th></th>\n",
 528 |        "      <th>wage</th>\n",
 529 |        "      <th>vil_labor</th>\n",
 530 |        "    </tr>\n",
 531 |        "  </thead>\n",
 532 |        "  <tbody>\n",
 533 |        "    <tr>\n",
 534 |        "      <td>count</td>\n",
 535 |        "      <td>20.000000</td>\n",
 536 |        "      <td>20.000000</td>\n",
 537 |        "    </tr>\n",
 538 |        "    <tr>\n",
 539 |        "      <td>mean</td>\n",
 540 |        "      <td>35.000000</td>\n",
 541 |        "      <td>0.749579</td>\n",
 542 |        "    </tr>\n",
 543 |        "    <tr>\n",
 544 |        "      <td>std</td>\n",
 545 |        "      <td>5.129892</td>\n",
 546 |        "      <td>0.166202</td>\n",
 547 |        "    </tr>\n",
 548 |        "    <tr>\n",
 549 |        "      <td>min</td>\n",
 550 |        "      <td>30.000000</td>\n",
 551 |        "      <td>0.302326</td>\n",
 552 |        "    </tr>\n",
 553 |        "    <tr>\n",
 554 |        "      <td>25%</td>\n",
 555 |        "      <td>30.000000</td>\n",
 556 |        "      <td>0.652975</td>\n",
 557 |        "    </tr>\n",
 558 |        "    <tr>\n",
 559 |        "      <td>50%</td>\n",
 560 |        "      <td>35.000000</td>\n",
 561 |        "      <td>0.794005</td>\n",
 562 |        "    </tr>\n",
 563 |        "    <tr>\n",
 564 |        "      <td>75%</td>\n",
 565 |        "      <td>40.000000</td>\n",
 566 |        "      <td>0.856280</td>\n",
 567 |        "    </tr>\n",
 568 |        "    <tr>\n",
 569 |        "      <td>max</td>\n",
 570 |        "      <td>40.000000</td>\n",
 571 |        "      <td>0.959184</td>\n",
 572 |        "    </tr>\n",
 573 |        "  </tbody>\n",
 574 |        "</table>\n",
 575 |        "</div>"
 576 |       ],
 577 |       "text/plain": [
 578 |        "            wage  vil_labor\n",
 579 |        "count  20.000000  20.000000\n",
 580 |        "mean   35.000000   0.749579\n",
 581 |        "std     5.129892   0.166202\n",
 582 |        "min    30.000000   0.302326\n",
 583 |        "25%    30.000000   0.652975\n",
 584 |        "50%    35.000000   0.794005\n",
 585 |        "75%    40.000000   0.856280\n",
 586 |        "max    40.000000   0.959184"
 587 |       ]
 588 |      },
 589 |      "execution_count": 7,
 590 |      "metadata": {},
 591 |      "output_type": "execute_result"
 592 |     }
 593 |    ],
 594 |    "source": [
 595 |     "bottom20 = df_wage_labor.nsmallest(20, ['wage', 'vil_labor'])\n",
 596 |     "bottom20.describe()"
 597 |    ]
 598 |   },
 599 |   {
 600 |    "cell_type": "markdown",
 601 |    "metadata": {},
 602 |    "source": [
 603 |     "It is a good idea to compare the acceptance rate for the bottom and upper 20 villages. Based on this observations, even that the mean wage for the top 20 is **286%** more than for the bottom *(avg. for the top 20 is 135 Kwacha; avg. for the bottom is 35 Kwacha)*, we see that there is a small gap of **18.66%** in acceptance rate between those two groups *(93.62% acceptance rate for the top and 74.96% for the bottom)*\n",
 604 |     "\n",
 605 |     "##### There is not enough evidence to assume that wages influence if residents of the village accept the job or not\n"
 606 |    ]
 607 |   },
 608 |   {
 609 |    "cell_type": "markdown",
 610 |    "metadata": {},
 611 |    "source": [
 612 |     "### 1.c.) Find the correlation coefficient between wage and acceptance rate."
 613 |    ]
 614 |   },
 615 |   {
 616 |    "cell_type": "code",
 617 |    "execution_count": 8,
 618 |    "metadata": {},
 619 |    "outputs": [
 620 |     {
 621 |      "name": "stdout",
 622 |      "output_type": "stream",
 623 |      "text": [
 624 |       "We've a WEAK POSITIVE correlation with coeficient of: 0.34560122231666063\n"
 625 |      ]
 626 |     }
 627 |    ],
 628 |    "source": [
 629 |     "x1_corr = df['wage'].corr(df['vil_labor'])\n",
 630 |     "\n",
 631 |     "if x1_corr > 0 and x1_corr < 0.5:\n",
 632 |     "    print('We\\'ve a WEAK POSITIVE correlation with coeficient of:', x1_corr)\n",
 633 |     "elif x1_corr > 0.5 and x1_corr <= 1:\n",
 634 |     "    print('We\\'ve a STRONG POSITIVE correlation with coeficient of:', x1_corr)\n",
 635 |     "elif x1_corr < 0 and x1_corr > -0.5:\n",
 636 |     "    print('We\\'ve a WEAK NEGATIVE correlation with coeficient of:', x1_corr)\n",
 637 |     "else:\n",
 638 |     "    print('We\\'ve a STRONG NEGATIVE correlation with coeficient of:', x1_corr)"
 639 |    ]
 640 |   },
 641 |   {
 642 |    "cell_type": "markdown",
 643 |    "metadata": {},
 644 |    "source": [
 645 |     "### 1.d) Let’s draw a scatter-graph to visualize the relationship between wage and job acceptance rate\n",
 646 |     "Let's see if this confirms our assumptions that despite the wage differences, people are still willing to accept the job"
 647 |    ]
 648 |   },
 649 |   {
 650 |    "cell_type": "code",
 651 |    "execution_count": 9,
 652 |    "metadata": {},
 653 |    "outputs": [
 654 |     {
 655 |      "data": {
 656 |       "image/png": "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\n",
 657 |       "text/plain": [
 658 |        "<Figure size 432x288 with 1 Axes>"
 659 |       ]
 660 |      },
 661 |      "metadata": {
 662 |       "needs_background": "light"
 663 |      },
 664 |      "output_type": "display_data"
 665 |     }
 666 |    ],
 667 |    "source": [
 668 |     "sns.regplot(x=\"wage\", y=\"vil_labor\", data=df, color='purple')\n",
 669 |     "plt.ylabel('Acceptance Rate', fontsize=12)\n",
 670 |     "plt.xlabel('Wage', fontsize=12)\n",
 671 |     "plt.title('Scatter-Graph of A-Rate and Wage')\n",
 672 |     "plt.grid(axis='y', alpha=0.75)\n",
 673 |     "plt.grid(axis='x', alpha=0.75)"
 674 |    ]
 675 |   },
 676 |   {
 677 |    "cell_type": "markdown",
 678 |    "metadata": {},
 679 |    "source": [
 680 |     "**Yes!** graph confirms that there is a small influence of the wage offered on if villager accepted the job or not."
 681 |    ]
 682 |   },
 683 |   {
 684 |    "cell_type": "markdown",
 685 |    "metadata": {},
 686 |    "source": [
 687 |     "## Part 2:\n",
 688 |     "-----------\n",
 689 |     "### 2.a) We run a regression of wage on acceptance rate."
 690 |    ]
 691 |   },
 692 |   {
 693 |    "cell_type": "code",
 694 |    "execution_count": 10,
 695 |    "metadata": {},
 696 |    "outputs": [],
 697 |    "source": [
 698 |     "from sklearn.model_selection import train_test_split \n",
 699 |     "from sklearn.linear_model import LinearRegression\n",
 700 |     "from sklearn import metrics"
 701 |    ]
 702 |   },
 703 |   {
 704 |    "cell_type": "code",
 705 |    "execution_count": 11,
 706 |    "metadata": {},
 707 |    "outputs": [
 708 |     {
 709 |      "data": {
 710 |       "text/html": [
 711 |        "<table class=\"simpletable\">\n",
 712 |        "<caption>OLS Regression Results</caption>\n",
 713 |        "<tr>\n",
 714 |        "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.119</td>\n",
 715 |        "</tr>\n",
 716 |        "<tr>\n",
 717 |        "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.112</td>\n",
 718 |        "</tr>\n",
 719 |        "<tr>\n",
 720 |        "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   16.01</td>\n",
 721 |        "</tr>\n",
 722 |        "<tr>\n",
 723 |        "  <th>Date:</th>             <td>Mon, 16 Dec 2019</td> <th>  Prob (F-statistic):</th> <td>0.000111</td>\n",
 724 |        "</tr>\n",
 725 |        "<tr>\n",
 726 |        "  <th>Time:</th>                 <td>23:38:21</td>     <th>  Log-Likelihood:    </th> <td>  49.648</td>\n",
 727 |        "</tr>\n",
 728 |        "<tr>\n",
 729 |        "  <th>No. Observations:</th>      <td>   120</td>      <th>  AIC:               </th> <td>  -95.30</td>\n",
 730 |        "</tr>\n",
 731 |        "<tr>\n",
 732 |        "  <th>Df Residuals:</th>          <td>   118</td>      <th>  BIC:               </th> <td>  -89.72</td>\n",
 733 |        "</tr>\n",
 734 |        "<tr>\n",
 735 |        "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n",
 736 |        "</tr>\n",
 737 |        "<tr>\n",
 738 |        "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
 739 |        "</tr>\n",
 740 |        "</table>\n",
 741 |        "<table class=\"simpletable\">\n",
 742 |        "<tr>\n",
 743 |        "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
 744 |        "</tr>\n",
 745 |        "<tr>\n",
 746 |        "  <th>Intercept</th> <td>    0.7004</td> <td>    0.039</td> <td>   17.894</td> <td> 0.000</td> <td>    0.623</td> <td>    0.778</td>\n",
 747 |        "</tr>\n",
 748 |        "<tr>\n",
 749 |        "  <th>x</th>         <td>    0.0017</td> <td>    0.000</td> <td>    4.001</td> <td> 0.000</td> <td>    0.001</td> <td>    0.003</td>\n",
 750 |        "</tr>\n",
 751 |        "</table>\n",
 752 |        "<table class=\"simpletable\">\n",
 753 |        "<tr>\n",
 754 |        "  <th>Omnibus:</th>       <td>83.233</td> <th>  Durbin-Watson:     </th> <td>   1.811</td> \n",
 755 |        "</tr>\n",
 756 |        "<tr>\n",
 757 |        "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 475.521</td> \n",
 758 |        "</tr>\n",
 759 |        "<tr>\n",
 760 |        "  <th>Skew:</th>          <td>-2.436</td> <th>  Prob(JB):          </th> <td>5.52e-104</td>\n",
 761 |        "</tr>\n",
 762 |        "<tr>\n",
 763 |        "  <th>Kurtosis:</th>      <td>11.448</td> <th>  Cond. No.          </th> <td>    244.</td> \n",
 764 |        "</tr>\n",
 765 |        "</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
 766 |       ],
 767 |       "text/plain": [
 768 |        "<class 'statsmodels.iolib.summary.Summary'>\n",
 769 |        "\"\"\"\n",
 770 |        "                            OLS Regression Results                            \n",
 771 |        "==============================================================================\n",
 772 |        "Dep. Variable:                      y   R-squared:                       0.119\n",
 773 |        "Model:                            OLS   Adj. R-squared:                  0.112\n",
 774 |        "Method:                 Least Squares   F-statistic:                     16.01\n",
 775 |        "Date:                Mon, 16 Dec 2019   Prob (F-statistic):           0.000111\n",
 776 |        "Time:                        23:38:21   Log-Likelihood:                 49.648\n",
 777 |        "No. Observations:                 120   AIC:                            -95.30\n",
 778 |        "Df Residuals:                     118   BIC:                            -89.72\n",
 779 |        "Df Model:                           1                                         \n",
 780 |        "Covariance Type:            nonrobust                                         \n",
 781 |        "==============================================================================\n",
 782 |        "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
 783 |        "------------------------------------------------------------------------------\n",
 784 |        "Intercept      0.7004      0.039     17.894      0.000       0.623       0.778\n",
 785 |        "x              0.0017      0.000      4.001      0.000       0.001       0.003\n",
 786 |        "==============================================================================\n",
 787 |        "Omnibus:                       83.233   Durbin-Watson:                   1.811\n",
 788 |        "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              475.521\n",
 789 |        "Skew:                          -2.436   Prob(JB):                    5.52e-104\n",
 790 |        "Kurtosis:                      11.448   Cond. No.                         244.\n",
 791 |        "==============================================================================\n",
 792 |        "\n",
 793 |        "Warnings:\n",
 794 |        "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
 795 |        "\"\"\""
 796 |       ]
 797 |      },
 798 |      "execution_count": 11,
 799 |      "metadata": {},
 800 |      "output_type": "execute_result"
 801 |     }
 802 |    ],
 803 |    "source": [
 804 |     "import statsmodels.formula.api as smf\n",
 805 |     "\n",
 806 |     "#The coefficients for wage seems to be small. Generated a new variable that is 1000 times smaller than wage (wage/1000) and use it instead of wage\n",
 807 |     "x = df[['wage']]\n",
 808 |     "y = df['vil_labor']\n",
 809 |     "\n",
 810 |     "#running regression acceptance rate on wage\n",
 811 |     "reg = smf.ols('y ~ x', data=df).fit()\n",
 812 |     "reg.summary()"
 813 |    ]
 814 |   },
 815 |   {
 816 |    "cell_type": "markdown",
 817 |    "metadata": {},
 818 |    "source": [
 819 |     "Our explanatory <code>'wage'</code> showed to have a strong explanatory power as it's <code>p-value</code> is approx. **0** (which means that we are 99% confident it is statistically significant).\n",
 820 |     "Also, explanatory variable shows that offering of an additional 1 Kwacha increases acceptance rate by **0.0017**\n",
 821 |     "\n",
 822 |     "However, if we look that the <code>R-squared</code>, which is the measure of goodness of fit of our model, we see that our model is the explanation of the outcome only by approx. **12%**"
 823 |    ]
 824 |   },
 825 |   {
 826 |    "cell_type": "code",
 827 |    "execution_count": 12,
 828 |    "metadata": {},
 829 |    "outputs": [],
 830 |    "source": [
 831 |     "#now once again we regress acceptance rate on wages\n",
 832 |     "reg = LinearRegression()\n",
 833 |     "\n",
 834 |     "x = df[['wage']]\n",
 835 |     "y = df['vil_labor']\n",
 836 |     "\n",
 837 |     "#fitting the model\n",
 838 |     "reg = reg.fit(x, y)\n",
 839 |     "\n",
 840 |     "#creating yhat or the prediction line\n",
 841 |     "yhat = reg.predict(x)"
 842 |    ]
 843 |   },
 844 |   {
 845 |    "cell_type": "markdown",
 846 |    "metadata": {},
 847 |    "source": [
 848 |     "### 2.b) We visualize our results:"
 849 |    ]
 850 |   },
 851 |   {
 852 |    "cell_type": "code",
 853 |    "execution_count": 13,
 854 |    "metadata": {},
 855 |    "outputs": [
 856 |     {
 857 |      "data": {
 858 |       "image/png": "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\n",
 859 |       "text/plain": [
 860 |        "<Figure size 432x288 with 1 Axes>"
 861 |       ]
 862 |      },
 863 |      "metadata": {
 864 |       "needs_background": "light"
 865 |      },
 866 |      "output_type": "display_data"
 867 |     }
 868 |    ],
 869 |    "source": [
 870 |     "plt.plot(x, yhat, color='green', label='Regression Line')\n",
 871 |     "plt.scatter(x, y, c='red', label='Actual Data')\n",
 872 |     "plt.ylabel('Acceptance Rate', fontsize=12)\n",
 873 |     "plt.xlabel('Wage', fontsize=12)\n",
 874 |     "plt.grid(axis='y', alpha=0.75)\n",
 875 |     "plt.grid(axis='x', alpha=0.75)\n",
 876 |     "plt.legend()\n",
 877 |     "plt.show()"
 878 |    ]
 879 |   },
 880 |   {
 881 |    "cell_type": "markdown",
 882 |    "metadata": {},
 883 |    "source": [
 884 |     "### 2.c) Coefficient for the wage is tiny. I will generate new variable 1000x smaller than wage and use it instead"
 885 |    ]
 886 |   },
 887 |   {
 888 |    "cell_type": "code",
 889 |    "execution_count": 14,
 890 |    "metadata": {},
 891 |    "outputs": [
 892 |     {
 893 |      "data": {
 894 |       "text/html": [
 895 |        "<table class=\"simpletable\">\n",
 896 |        "<caption>OLS Regression Results</caption>\n",
 897 |        "<tr>\n",
 898 |        "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.119</td>\n",
 899 |        "</tr>\n",
 900 |        "<tr>\n",
 901 |        "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.112</td>\n",
 902 |        "</tr>\n",
 903 |        "<tr>\n",
 904 |        "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   16.01</td>\n",
 905 |        "</tr>\n",
 906 |        "<tr>\n",
 907 |        "  <th>Date:</th>             <td>Mon, 16 Dec 2019</td> <th>  Prob (F-statistic):</th> <td>0.000111</td>\n",
 908 |        "</tr>\n",
 909 |        "<tr>\n",
 910 |        "  <th>Time:</th>                 <td>23:38:21</td>     <th>  Log-Likelihood:    </th> <td>  49.648</td>\n",
 911 |        "</tr>\n",
 912 |        "<tr>\n",
 913 |        "  <th>No. Observations:</th>      <td>   120</td>      <th>  AIC:               </th> <td>  -95.30</td>\n",
 914 |        "</tr>\n",
 915 |        "<tr>\n",
 916 |        "  <th>Df Residuals:</th>          <td>   118</td>      <th>  BIC:               </th> <td>  -89.72</td>\n",
 917 |        "</tr>\n",
 918 |        "<tr>\n",
 919 |        "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n",
 920 |        "</tr>\n",
 921 |        "<tr>\n",
 922 |        "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
 923 |        "</tr>\n",
 924 |        "</table>\n",
 925 |        "<table class=\"simpletable\">\n",
 926 |        "<tr>\n",
 927 |        "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
 928 |        "</tr>\n",
 929 |        "<tr>\n",
 930 |        "  <th>Intercept</th> <td>    0.7004</td> <td>    0.039</td> <td>   17.894</td> <td> 0.000</td> <td>    0.623</td> <td>    0.778</td>\n",
 931 |        "</tr>\n",
 932 |        "<tr>\n",
 933 |        "  <th>wage1000</th>  <td>    1.7069</td> <td>    0.427</td> <td>    4.001</td> <td> 0.000</td> <td>    0.862</td> <td>    2.552</td>\n",
 934 |        "</tr>\n",
 935 |        "</table>\n",
 936 |        "<table class=\"simpletable\">\n",
 937 |        "<tr>\n",
 938 |        "  <th>Omnibus:</th>       <td>83.233</td> <th>  Durbin-Watson:     </th> <td>   1.811</td> \n",
 939 |        "</tr>\n",
 940 |        "<tr>\n",
 941 |        "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 475.521</td> \n",
 942 |        "</tr>\n",
 943 |        "<tr>\n",
 944 |        "  <th>Skew:</th>          <td>-2.436</td> <th>  Prob(JB):          </th> <td>5.52e-104</td>\n",
 945 |        "</tr>\n",
 946 |        "<tr>\n",
 947 |        "  <th>Kurtosis:</th>      <td>11.448</td> <th>  Cond. No.          </th> <td>    29.2</td> \n",
 948 |        "</tr>\n",
 949 |        "</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
 950 |       ],
 951 |       "text/plain": [
 952 |        "<class 'statsmodels.iolib.summary.Summary'>\n",
 953 |        "\"\"\"\n",
 954 |        "                            OLS Regression Results                            \n",
 955 |        "==============================================================================\n",
 956 |        "Dep. Variable:                      y   R-squared:                       0.119\n",
 957 |        "Model:                            OLS   Adj. R-squared:                  0.112\n",
 958 |        "Method:                 Least Squares   F-statistic:                     16.01\n",
 959 |        "Date:                Mon, 16 Dec 2019   Prob (F-statistic):           0.000111\n",
 960 |        "Time:                        23:38:21   Log-Likelihood:                 49.648\n",
 961 |        "No. Observations:                 120   AIC:                            -95.30\n",
 962 |        "Df Residuals:                     118   BIC:                            -89.72\n",
 963 |        "Df Model:                           1                                         \n",
 964 |        "Covariance Type:            nonrobust                                         \n",
 965 |        "==============================================================================\n",
 966 |        "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
 967 |        "------------------------------------------------------------------------------\n",
 968 |        "Intercept      0.7004      0.039     17.894      0.000       0.623       0.778\n",
 969 |        "wage1000       1.7069      0.427      4.001      0.000       0.862       2.552\n",
 970 |        "==============================================================================\n",
 971 |        "Omnibus:                       83.233   Durbin-Watson:                   1.811\n",
 972 |        "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              475.521\n",
 973 |        "Skew:                          -2.436   Prob(JB):                    5.52e-104\n",
 974 |        "Kurtosis:                      11.448   Cond. No.                         29.2\n",
 975 |        "==============================================================================\n",
 976 |        "\n",
 977 |        "Warnings:\n",
 978 |        "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
 979 |        "\"\"\""
 980 |       ]
 981 |      },
 982 |      "execution_count": 14,
 983 |      "metadata": {},
 984 |      "output_type": "execute_result"
 985 |     }
 986 |    ],
 987 |    "source": [
 988 |     "wage1000 = df['wage'] / 1000\n",
 989 |     "\n",
 990 |     "reg = smf.ols('y ~ wage1000', data=df).fit()\n",
 991 |     "reg.summary()"
 992 |    ]
 993 |   },
 994 |   {
 995 |    "cell_type": "markdown",
 996 |    "metadata": {},
 997 |    "source": [
 998 |     "Now we see that any additional _10 Kwacha_ increases acceptance rate by **1.7%**"
 999 |    ]
1000 |   },
1001 |   {
1002 |    "cell_type": "markdown",
1003 |    "metadata": {},
1004 |    "source": [
1005 |     "### 2.d) to make sure that our model is a good model we check if sum of the residuals is equal 0."
1006 |    ]
1007 |   },
1008 |   {
1009 |    "cell_type": "code",
1010 |    "execution_count": 15,
1011 |    "metadata": {},
1012 |    "outputs": [
1013 |     {
1014 |      "name": "stdout",
1015 |      "output_type": "stream",
1016 |      "text": [
1017 |       "sum of the residuals is:\t -4.5075054799781356e-14\n",
1018 |       "average of the residuals is:\t -3.811765717879704e-16\n"
1019 |      ]
1020 |     }
1021 |    ],
1022 |    "source": [
1023 |     "print('sum of the residuals is:\\t', np.sum(reg.resid))\n",
1024 |     "print('average of the residuals is:\\t', np.mean(reg.resid))"
1025 |    ]
1026 |   },
1027 |   {
1028 |    "cell_type": "markdown",
1029 |    "metadata": {},
1030 |    "source": [
1031 |     "in both cases we see that they are very very close to 0!"
1032 |    ]
1033 |   },
1034 |   {
1035 |    "cell_type": "markdown",
1036 |    "metadata": {},
1037 |    "source": [
1038 |     "## 2.e) Now instead of 'wage' we will run regression using 'lnwage' which is interpreted as a percentage change in wage"
1039 |    ]
1040 |   },
1041 |   {
1042 |    "cell_type": "code",
1043 |    "execution_count": 16,
1044 |    "metadata": {},
1045 |    "outputs": [
1046 |     {
1047 |      "data": {
1048 |       "text/html": [
1049 |        "<table class=\"simpletable\">\n",
1050 |        "<caption>OLS Regression Results</caption>\n",
1051 |        "<tr>\n",
1052 |        "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.116</td>\n",
1053 |        "</tr>\n",
1054 |        "<tr>\n",
1055 |        "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.109</td>\n",
1056 |        "</tr>\n",
1057 |        "<tr>\n",
1058 |        "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   15.49</td>\n",
1059 |        "</tr>\n",
1060 |        "<tr>\n",
1061 |        "  <th>Date:</th>             <td>Mon, 16 Dec 2019</td> <th>  Prob (F-statistic):</th> <td>0.000140</td>\n",
1062 |        "</tr>\n",
1063 |        "<tr>\n",
1064 |        "  <th>Time:</th>                 <td>23:38:21</td>     <th>  Log-Likelihood:    </th> <td>  49.418</td>\n",
1065 |        "</tr>\n",
1066 |        "<tr>\n",
1067 |        "  <th>No. Observations:</th>      <td>   120</td>      <th>  AIC:               </th> <td>  -94.84</td>\n",
1068 |        "</tr>\n",
1069 |        "<tr>\n",
1070 |        "  <th>Df Residuals:</th>          <td>   118</td>      <th>  BIC:               </th> <td>  -89.26</td>\n",
1071 |        "</tr>\n",
1072 |        "<tr>\n",
1073 |        "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n",
1074 |        "</tr>\n",
1075 |        "<tr>\n",
1076 |        "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
1077 |        "</tr>\n",
1078 |        "</table>\n",
1079 |        "<table class=\"simpletable\">\n",
1080 |        "<tr>\n",
1081 |        "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
1082 |        "</tr>\n",
1083 |        "<tr>\n",
1084 |        "  <th>Intercept</th> <td>    0.3060</td> <td>    0.138</td> <td>    2.220</td> <td> 0.028</td> <td>    0.033</td> <td>    0.579</td>\n",
1085 |        "</tr>\n",
1086 |        "<tr>\n",
1087 |        "  <th>lnwage</th>    <td>    0.1242</td> <td>    0.032</td> <td>    3.936</td> <td> 0.000</td> <td>    0.062</td> <td>    0.187</td>\n",
1088 |        "</tr>\n",
1089 |        "</table>\n",
1090 |        "<table class=\"simpletable\">\n",
1091 |        "<tr>\n",
1092 |        "  <th>Omnibus:</th>       <td>82.986</td> <th>  Durbin-Watson:     </th> <td>   1.832</td> \n",
1093 |        "</tr>\n",
1094 |        "<tr>\n",
1095 |        "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 464.288</td> \n",
1096 |        "</tr>\n",
1097 |        "<tr>\n",
1098 |        "  <th>Skew:</th>          <td>-2.439</td> <th>  Prob(JB):          </th> <td>1.52e-101</td>\n",
1099 |        "</tr>\n",
1100 |        "<tr>\n",
1101 |        "  <th>Kurtosis:</th>      <td>11.311</td> <th>  Cond. No.          </th> <td>    42.9</td> \n",
1102 |        "</tr>\n",
1103 |        "</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
1104 |       ],
1105 |       "text/plain": [
1106 |        "<class 'statsmodels.iolib.summary.Summary'>\n",
1107 |        "\"\"\"\n",
1108 |        "                            OLS Regression Results                            \n",
1109 |        "==============================================================================\n",
1110 |        "Dep. Variable:                      y   R-squared:                       0.116\n",
1111 |        "Model:                            OLS   Adj. R-squared:                  0.109\n",
1112 |        "Method:                 Least Squares   F-statistic:                     15.49\n",
1113 |        "Date:                Mon, 16 Dec 2019   Prob (F-statistic):           0.000140\n",
1114 |        "Time:                        23:38:21   Log-Likelihood:                 49.418\n",
1115 |        "No. Observations:                 120   AIC:                            -94.84\n",
1116 |        "Df Residuals:                     118   BIC:                            -89.26\n",
1117 |        "Df Model:                           1                                         \n",
1118 |        "Covariance Type:            nonrobust                                         \n",
1119 |        "==============================================================================\n",
1120 |        "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
1121 |        "------------------------------------------------------------------------------\n",
1122 |        "Intercept      0.3060      0.138      2.220      0.028       0.033       0.579\n",
1123 |        "lnwage         0.1242      0.032      3.936      0.000       0.062       0.187\n",
1124 |        "==============================================================================\n",
1125 |        "Omnibus:                       82.986   Durbin-Watson:                   1.832\n",
1126 |        "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              464.288\n",
1127 |        "Skew:                          -2.439   Prob(JB):                    1.52e-101\n",
1128 |        "Kurtosis:                      11.311   Cond. No.                         42.9\n",
1129 |        "==============================================================================\n",
1130 |        "\n",
1131 |        "Warnings:\n",
1132 |        "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
1133 |        "\"\"\""
1134 |       ]
1135 |      },
1136 |      "execution_count": 16,
1137 |      "metadata": {},
1138 |      "output_type": "execute_result"
1139 |     }
1140 |    ],
1141 |    "source": [
1142 |     "lnwage = df['lnwage']\n",
1143 |     "\n",
1144 |     "reg = smf.ols('y ~ lnwage', data=df).fit()\n",
1145 |     "reg.summary()"
1146 |    ]
1147 |   },
1148 |   {
1149 |    "cell_type": "markdown",
1150 |    "metadata": {},
1151 |    "source": [
1152 |     "Here we see that **1%** change in the <code>wage</code> changes acceptance rate by **12.42%.**"
1153 |    ]
1154 |   },
1155 |   {
1156 |    "cell_type": "markdown",
1157 |    "metadata": {},
1158 |    "source": [
1159 |     "### 2.f) Now we just manually compute the regression which was used in the study to calculate the elasticity of the wages\n",
1160 |     "#### regression used in the model is **labor = α + β\\*ln(wage) + e**"
1161 |    ]
1162 |   },
1163 |   {
1164 |    "cell_type": "code",
1165 |    "execution_count": 2,
1166 |    "metadata": {},
1167 |    "outputs": [
1168 |     {
1169 |      "name": "stdout",
1170 |      "output_type": "stream",
1171 |      "text": [
1172 |       "Elasticity of the job acceptance is based on wage: 0.4302\n"
1173 |      ]
1174 |     }
1175 |    ],
1176 |    "source": [
1177 |     "x = 1\n",
1178 |     "labor = 0.3060 + 0.1242*x\n",
1179 |     "print('Elasticity of the job acceptance is based on wage:',labor)"
1180 |    ]
1181 |   },
1182 |   {
1183 |    "cell_type": "markdown",
1184 |    "metadata": {},
1185 |    "source": [
1186 |     "Even though I used exactly the same model with the same variables from the same dataset my elasticity came to be a little higher than found in the original paper (0.35). This can explain by a small difference in the data. In original data, it appears they got rid of the village which had a 0% acceptance rate (probably there was something happening at that time, so nobody accepted the job), while this data is present in my analysis. However, we still can canclude that findings are somewhat **inelastic**"
1187 |    ]
1188 |   },
1189 |   {
1190 |    "cell_type": "markdown",
1191 |    "metadata": {},
1192 |    "source": [
1193 |     "# Part 3:\n",
1194 |     "-----------\n",
1195 |     "### 3.a) Now in trying to reproduce the other columns of Table 4 of the paper, we would like to calculate two sets of variables called “village effects” and “week effects”. We work only on village effects. Week effects are similar. "
1196 |    ]
1197 |   },
1198 |   {
1199 |    "cell_type": "code",
1200 |    "execution_count": 18,
1201 |    "metadata": {},
1202 |    "outputs": [
1203 |     {
1204 |      "data": {
1205 |       "text/html": [
1206 |        "<table class=\"simpletable\">\n",
1207 |        "<caption>OLS Regression Results</caption>\n",
1208 |        "<tr>\n",
1209 |        "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.202</td>\n",
1210 |        "</tr>\n",
1211 |        "<tr>\n",
1212 |        "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.128</td>\n",
1213 |        "</tr>\n",
1214 |        "<tr>\n",
1215 |        "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   2.752</td>\n",
1216 |        "</tr>\n",
1217 |        "<tr>\n",
1218 |        "  <th>Date:</th>             <td>Mon, 16 Dec 2019</td> <th>  Prob (F-statistic):</th>  <td>0.00461</td>\n",
1219 |        "</tr>\n",
1220 |        "<tr>\n",
1221 |        "  <th>Time:</th>                 <td>23:38:21</td>     <th>  Log-Likelihood:    </th> <td>  55.524</td>\n",
1222 |        "</tr>\n",
1223 |        "<tr>\n",
1224 |        "  <th>No. Observations:</th>      <td>   120</td>      <th>  AIC:               </th> <td>  -89.05</td>\n",
1225 |        "</tr>\n",
1226 |        "<tr>\n",
1227 |        "  <th>Df Residuals:</th>          <td>   109</td>      <th>  BIC:               </th> <td>  -58.38</td>\n",
1228 |        "</tr>\n",
1229 |        "<tr>\n",
1230 |        "  <th>Df Model:</th>              <td>    10</td>      <th>                     </th>     <td> </td>   \n",
1231 |        "</tr>\n",
1232 |        "<tr>\n",
1233 |        "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
1234 |        "</tr>\n",
1235 |        "</table>\n",
1236 |        "<table class=\"simpletable\">\n",
1237 |        "<tr>\n",
1238 |        "                 <td></td>                   <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
1239 |        "</tr>\n",
1240 |        "<tr>\n",
1241 |        "  <th>Intercept</th>                      <td>    0.3228</td> <td>    0.143</td> <td>    2.255</td> <td> 0.026</td> <td>    0.039</td> <td>    0.607</td>\n",
1242 |        "</tr>\n",
1243 |        "<tr>\n",
1244 |        "  <th>C(village)[T.HASHAMU]</th>          <td>   -0.1058</td> <td>    0.065</td> <td>   -1.622</td> <td> 0.108</td> <td>   -0.235</td> <td>    0.023</td>\n",
1245 |        "</tr>\n",
1246 |        "<tr>\n",
1247 |        "  <th>C(village)[T.KACHULE]</th>          <td>   -0.0631</td> <td>    0.065</td> <td>   -0.966</td> <td> 0.336</td> <td>   -0.192</td> <td>    0.066</td>\n",
1248 |        "</tr>\n",
1249 |        "<tr>\n",
1250 |        "  <th>C(village)[T.KADZINJA/KHUNGWA]</th> <td>    0.0347</td> <td>    0.065</td> <td>    0.531</td> <td> 0.596</td> <td>   -0.095</td> <td>    0.164</td>\n",
1251 |        "</tr>\n",
1252 |        "<tr>\n",
1253 |        "  <th>C(village)[T.KAFOTOKOZA]</th>       <td>    0.0257</td> <td>    0.065</td> <td>    0.394</td> <td> 0.694</td> <td>   -0.104</td> <td>    0.155</td>\n",
1254 |        "</tr>\n",
1255 |        "<tr>\n",
1256 |        "  <th>C(village)[T.KAMWENDO]</th>         <td>    0.0128</td> <td>    0.065</td> <td>    0.195</td> <td> 0.845</td> <td>   -0.117</td> <td>    0.142</td>\n",
1257 |        "</tr>\n",
1258 |        "<tr>\n",
1259 |        "  <th>C(village)[T.KUNFUNDA]</th>         <td>   -0.0855</td> <td>    0.065</td> <td>   -1.310</td> <td> 0.193</td> <td>   -0.215</td> <td>    0.044</td>\n",
1260 |        "</tr>\n",
1261 |        "<tr>\n",
1262 |        "  <th>C(village)[T.MANASE]</th>           <td>   -0.0409</td> <td>    0.065</td> <td>   -0.626</td> <td> 0.532</td> <td>   -0.170</td> <td>    0.088</td>\n",
1263 |        "</tr>\n",
1264 |        "<tr>\n",
1265 |        "  <th>C(village)[T.MSANGU/KALUTE]</th>    <td>    0.0272</td> <td>    0.065</td> <td>    0.418</td> <td> 0.677</td> <td>   -0.102</td> <td>    0.157</td>\n",
1266 |        "</tr>\n",
1267 |        "<tr>\n",
1268 |        "  <th>C(village)[T.NJONJA]</th>           <td>    0.0272</td> <td>    0.065</td> <td>    0.417</td> <td> 0.678</td> <td>   -0.102</td> <td>    0.157</td>\n",
1269 |        "</tr>\n",
1270 |        "<tr>\n",
1271 |        "  <th>lnwage</th>                         <td>    0.1242</td> <td>    0.031</td> <td>    3.980</td> <td> 0.000</td> <td>    0.062</td> <td>    0.186</td>\n",
1272 |        "</tr>\n",
1273 |        "</table>\n",
1274 |        "<table class=\"simpletable\">\n",
1275 |        "<tr>\n",
1276 |        "  <th>Omnibus:</th>       <td>94.244</td> <th>  Durbin-Watson:     </th> <td>   2.025</td> \n",
1277 |        "</tr>\n",
1278 |        "<tr>\n",
1279 |        "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 715.205</td> \n",
1280 |        "</tr>\n",
1281 |        "<tr>\n",
1282 |        "  <th>Skew:</th>          <td>-2.719</td> <th>  Prob(JB):          </th> <td>4.96e-156</td>\n",
1283 |        "</tr>\n",
1284 |        "<tr>\n",
1285 |        "  <th>Kurtosis:</th>      <td>13.652</td> <th>  Cond. No.          </th> <td>    51.1</td> \n",
1286 |        "</tr>\n",
1287 |        "</table><br/><br/>Warnings:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
1288 |       ],
1289 |       "text/plain": [
1290 |        "<class 'statsmodels.iolib.summary.Summary'>\n",
1291 |        "\"\"\"\n",
1292 |        "                            OLS Regression Results                            \n",
1293 |        "==============================================================================\n",
1294 |        "Dep. Variable:                      y   R-squared:                       0.202\n",
1295 |        "Model:                            OLS   Adj. R-squared:                  0.128\n",
1296 |        "Method:                 Least Squares   F-statistic:                     2.752\n",
1297 |        "Date:                Mon, 16 Dec 2019   Prob (F-statistic):            0.00461\n",
1298 |        "Time:                        23:38:21   Log-Likelihood:                 55.524\n",
1299 |        "No. Observations:                 120   AIC:                            -89.05\n",
1300 |        "Df Residuals:                     109   BIC:                            -58.38\n",
1301 |        "Df Model:                          10                                         \n",
1302 |        "Covariance Type:            nonrobust                                         \n",
1303 |        "==================================================================================================\n",
1304 |        "                                     coef    std err          t      P>|t|      [0.025      0.975]\n",
1305 |        "--------------------------------------------------------------------------------------------------\n",
1306 |        "Intercept                          0.3228      0.143      2.255      0.026       0.039       0.607\n",
1307 |        "C(village)[T.HASHAMU]             -0.1058      0.065     -1.622      0.108      -0.235       0.023\n",
1308 |        "C(village)[T.KACHULE]             -0.0631      0.065     -0.966      0.336      -0.192       0.066\n",
1309 |        "C(village)[T.KADZINJA/KHUNGWA]     0.0347      0.065      0.531      0.596      -0.095       0.164\n",
1310 |        "C(village)[T.KAFOTOKOZA]           0.0257      0.065      0.394      0.694      -0.104       0.155\n",
1311 |        "C(village)[T.KAMWENDO]             0.0128      0.065      0.195      0.845      -0.117       0.142\n",
1312 |        "C(village)[T.KUNFUNDA]            -0.0855      0.065     -1.310      0.193      -0.215       0.044\n",
1313 |        "C(village)[T.MANASE]              -0.0409      0.065     -0.626      0.532      -0.170       0.088\n",
1314 |        "C(village)[T.MSANGU/KALUTE]        0.0272      0.065      0.418      0.677      -0.102       0.157\n",
1315 |        "C(village)[T.NJONJA]               0.0272      0.065      0.417      0.678      -0.102       0.157\n",
1316 |        "lnwage                             0.1242      0.031      3.980      0.000       0.062       0.186\n",
1317 |        "==============================================================================\n",
1318 |        "Omnibus:                       94.244   Durbin-Watson:                   2.025\n",
1319 |        "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              715.205\n",
1320 |        "Skew:                          -2.719   Prob(JB):                    4.96e-156\n",
1321 |        "Kurtosis:                      13.652   Cond. No.                         51.1\n",
1322 |        "==============================================================================\n",
1323 |        "\n",
1324 |        "Warnings:\n",
1325 |        "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
1326 |        "\"\"\""
1327 |       ]
1328 |      },
1329 |      "execution_count": 18,
1330 |      "metadata": {},
1331 |      "output_type": "execute_result"
1332 |     }
1333 |    ],
1334 |    "source": [
1335 |     "lnwage = df['lnwage']\n",
1336 |     "village = df['village']\n",
1337 |     "\n",
1338 |     "reg = smf.ols('y ~ lnwage + C(village)', data=df).fit()\n",
1339 |     "reg.summary()"
1340 |    ]
1341 |   },
1342 |   {
1343 |    "cell_type": "markdown",
1344 |    "metadata": {},
1345 |    "source": [
1346 |     "After controlling for individual village, we see that effect of a wage on the acceptance rate didn't change, and none of the village variables is statistically significant and the effect on acceptance rate is marginally or non-existence."
1347 |    ]
1348 |   },
1349 |   {
1350 |    "cell_type": "code",
1351 |    "execution_count": null,
1352 |    "metadata": {},
1353 |    "outputs": [],
1354 |    "source": []
1355 |   }
1356 |  ],
1357 |  "metadata": {
1358 |   "kernelspec": {
1359 |    "display_name": "Python 3",
1360 |    "language": "python",
1361 |    "name": "python3"
1362 |   },
1363 |   "language_info": {
1364 |    "codemirror_mode": {
1365 |     "name": "ipython",
1366 |     "version": 3
1367 |    },
1368 |    "file_extension": ".py",
1369 |    "mimetype": "text/x-python",
1370 |    "name": "python",
1371 |    "nbconvert_exporter": "python",
1372 |    "pygments_lexer": "ipython3",
1373 |    "version": "3.7.4"
1374 |   }
1375 |  },
1376 |  "nbformat": 4,
1377 |  "nbformat_minor": 4
1378 | }
1379 | 


--------------------------------------------------------------------------------