|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "code", |
| 5 | + "execution_count": 1, |
| 6 | + "metadata": {}, |
| 7 | + "outputs": [], |
| 8 | + "source": [ |
| 9 | + "%%capture\n", |
| 10 | + "import stata_setup, os\n", |
| 11 | + "if os.name == 'nt':\n", |
| 12 | + " stata_setup.config('C:/Program Files/Stata17/','mp')\n", |
| 13 | + "else:\n", |
| 14 | + " stata_setup.config('/usr/local/stata17','mp')" |
| 15 | + ] |
| 16 | + }, |
| 17 | + { |
| 18 | + "cell_type": "markdown", |
| 19 | + "metadata": {}, |
| 20 | + "source": [ |
| 21 | + "## Data Preparation" |
| 22 | + ] |
| 23 | + }, |
| 24 | + { |
| 25 | + "cell_type": "code", |
| 26 | + "execution_count": 2, |
| 27 | + "metadata": {}, |
| 28 | + "outputs": [ |
| 29 | + { |
| 30 | + "name": "stdout", |
| 31 | + "output_type": "stream", |
| 32 | + "text": [ |
| 33 | + "\n" |
| 34 | + ] |
| 35 | + } |
| 36 | + ], |
| 37 | + "source": [ |
| 38 | + "%%stata -qui\n", |
| 39 | + "\n", |
| 40 | + "use \"../data/data\", clear\n", |
| 41 | + "\n", |
| 42 | + "quietly tabulate year, generate(y_)\n", |
| 43 | + "quietly tabulate cluster, generate(c_)\n", |
| 44 | + "\n", |
| 45 | + "* Generate the Flesch-Kincaid Grade Level indicator\n", |
| 46 | + "summarize flesch_kincaid_grade_level, detail\n", |
| 47 | + "local cutoff = r(p90)\n", |
| 48 | + "gen int FKG_01 = (flesch_kincaid_grade_level >= `cutoff')\n", |
| 49 | + "\n", |
| 50 | + "* Generate the excess number of sentences count\n", |
| 51 | + "summarize num_sentences, detail\n", |
| 52 | + "local cutoff_sentences = r(p5)\n", |
| 53 | + "gen int excess_sentences = num_sentences - `cutoff_sentences'\n", |
| 54 | + "replace excess_sentences = 0 if excess_sentences < 0\n", |
| 55 | + "\n", |
| 56 | + "local journals ecm jpe qje res //AER based category\n", |
| 57 | + "\n", |
| 58 | + "local jel_imp a_imp b_imp c_imp e_imp f_imp g_imp h_imp i_imp j_imp k_imp /// \n", |
| 59 | + "\t\tl_imp m_imp n_imp o_imp p_imp q_imp r_imp y_imp z_imp // D JEL based case\n", |
| 60 | + "\n", |
| 61 | + "\n", |
| 62 | + "#delimit ;\n", |
| 63 | + "vl set log_num_authors log_num_pages both_genders prop_women\n", |
| 64 | + " `journals' `jel_imp' y_2-y_20 c_2-c_215 jel_flag\n", |
| 65 | + " , dummy clear nonotes;\n", |
| 66 | + "vl create fe = vldummy - (both_genders jel_flag);\n", |
| 67 | + "vl substitute mfe = i.fe;\n", |
| 68 | + "vl create controls = vlcontinuous - (prop_women);\n", |
| 69 | + "vl create controls_dummy = (both_genders jel_flag);\n", |
| 70 | + "vl substitute baseline = i.controls_dummy controls;\n", |
| 71 | + "vl rebuild;\n", |
| 72 | + "#delimit cr" |
| 73 | + ] |
| 74 | + }, |
| 75 | + { |
| 76 | + "cell_type": "markdown", |
| 77 | + "metadata": {}, |
| 78 | + "source": [ |
| 79 | + "# Elastic Net - Logistic" |
| 80 | + ] |
| 81 | + }, |
| 82 | + { |
| 83 | + "cell_type": "code", |
| 84 | + "execution_count": 3, |
| 85 | + "metadata": {}, |
| 86 | + "outputs": [ |
| 87 | + { |
| 88 | + "name": "stdout", |
| 89 | + "output_type": "stream", |
| 90 | + "text": [ |
| 91 | + "\n" |
| 92 | + ] |
| 93 | + } |
| 94 | + ], |
| 95 | + "source": [ |
| 96 | + "%%stata -qui -eret steret\n", |
| 97 | + "#delimit ;\n", |
| 98 | + "elasticnet logit FKG_01 prop_women $baseline $mfe, alpha(0.99) lambda(0.02) nolog;\n", |
| 99 | + "#delimit cr" |
| 100 | + ] |
| 101 | + }, |
| 102 | + { |
| 103 | + "cell_type": "code", |
| 104 | + "execution_count": 4, |
| 105 | + "metadata": {}, |
| 106 | + "outputs": [ |
| 107 | + { |
| 108 | + "name": "stdout", |
| 109 | + "output_type": "stream", |
| 110 | + "text": [ |
| 111 | + "------------------------------------------------------------------------------\n", |
| 112 | + " FKG_01 | Coefficient\n", |
| 113 | + "-------------+----------------------------------------------------------------\n", |
| 114 | + " c_4 |\n", |
| 115 | + " 0 | -.3811678\n", |
| 116 | + " 1 | .3843454\n", |
| 117 | + " |\n", |
| 118 | + " _cons | -1.816232\n", |
| 119 | + "------------------------------------------------------------------------------\n" |
| 120 | + ] |
| 121 | + } |
| 122 | + ], |
| 123 | + "source": [ |
| 124 | + "%stata ereturn display" |
| 125 | + ] |
| 126 | + }, |
| 127 | + { |
| 128 | + "cell_type": "markdown", |
| 129 | + "metadata": {}, |
| 130 | + "source": [ |
| 131 | + "# Elastic Net - Poisson" |
| 132 | + ] |
| 133 | + }, |
| 134 | + { |
| 135 | + "cell_type": "code", |
| 136 | + "execution_count": 5, |
| 137 | + "metadata": {}, |
| 138 | + "outputs": [ |
| 139 | + { |
| 140 | + "name": "stdout", |
| 141 | + "output_type": "stream", |
| 142 | + "text": [ |
| 143 | + "\n" |
| 144 | + ] |
| 145 | + } |
| 146 | + ], |
| 147 | + "source": [ |
| 148 | + "%%stata -qui -eret steret\n", |
| 149 | + "#delimit ;\n", |
| 150 | + "elasticnet poisson excess_sentences prop_women $baseline $mfe, alpha(0.7) lambda(.1) nolog;\n", |
| 151 | + "#delimit cr" |
| 152 | + ] |
| 153 | + }, |
| 154 | + { |
| 155 | + "cell_type": "code", |
| 156 | + "execution_count": 6, |
| 157 | + "metadata": {}, |
| 158 | + "outputs": [ |
| 159 | + { |
| 160 | + "name": "stdout", |
| 161 | + "output_type": "stream", |
| 162 | + "text": [ |
| 163 | + "------------------------------------------------------------------------------\n", |
| 164 | + "excess_sen~s | Coefficient\n", |
| 165 | + "-------------+----------------------------------------------------------------\n", |
| 166 | + "log_num_pa~s | .3588161\n", |
| 167 | + " |\n", |
| 168 | + " ecm |\n", |
| 169 | + " 0 | -.1451147\n", |
| 170 | + " 1 | .1451147\n", |
| 171 | + " |\n", |
| 172 | + " qje |\n", |
| 173 | + " 0 | -.0868885\n", |
| 174 | + " 1 | .0868885\n", |
| 175 | + " |\n", |
| 176 | + " res |\n", |
| 177 | + " 0 | -.1660911\n", |
| 178 | + " 1 | .1660911\n", |
| 179 | + " |\n", |
| 180 | + " c_imp |\n", |
| 181 | + " 0 | -.0183949\n", |
| 182 | + " 1 | .0183949\n", |
| 183 | + " |\n", |
| 184 | + " c_86 |\n", |
| 185 | + " 0 | -.1177174\n", |
| 186 | + " 1 | .1177467\n", |
| 187 | + " |\n", |
| 188 | + " c_114 |\n", |
| 189 | + " 0 | -.2093475\n", |
| 190 | + " 1 | .2098763\n", |
| 191 | + " |\n", |
| 192 | + " c_136 |\n", |
| 193 | + " 0 | -.5765329\n", |
| 194 | + " 1 | .5765334\n", |
| 195 | + " |\n", |
| 196 | + " c_142 |\n", |
| 197 | + " 0 | -.0506581\n", |
| 198 | + " 1 | .0506593\n", |
| 199 | + " |\n", |
| 200 | + " c_174 |\n", |
| 201 | + " 0 | -.0596673\n", |
| 202 | + " 1 | .0596695\n", |
| 203 | + " |\n", |
| 204 | + " _cons | .9339063\n", |
| 205 | + "------------------------------------------------------------------------------\n" |
| 206 | + ] |
| 207 | + } |
| 208 | + ], |
| 209 | + "source": [ |
| 210 | + "%stata ereturn display" |
| 211 | + ] |
| 212 | + } |
| 213 | + ], |
| 214 | + "metadata": { |
| 215 | + "kernelspec": { |
| 216 | + "display_name": "Python 3", |
| 217 | + "language": "python", |
| 218 | + "name": "python3" |
| 219 | + }, |
| 220 | + "language_info": { |
| 221 | + "codemirror_mode": { |
| 222 | + "name": "ipython", |
| 223 | + "version": 3 |
| 224 | + }, |
| 225 | + "file_extension": ".py", |
| 226 | + "mimetype": "text/x-python", |
| 227 | + "name": "python", |
| 228 | + "nbconvert_exporter": "python", |
| 229 | + "pygments_lexer": "ipython3", |
| 230 | + "version": "3.12.3" |
| 231 | + } |
| 232 | + }, |
| 233 | + "nbformat": 4, |
| 234 | + "nbformat_minor": 2 |
| 235 | +} |
0 commit comments