Skip to content

Instantly share code, notes, and snippets.

@vincenttzc

vincenttzc/gist:418fc5f35f936b51793f461d331d0cca

Created November 11, 2017 10:00
Show Gist options
  • Save vincenttzc/418fc5f35f936b51793f461d331d0cca to your computer and use it in GitHub Desktop.
Save vincenttzc/418fc5f35f936b51793f461d331d0cca to your computer and use it in GitHub Desktop.
Download ZIP
RE Project - Hospital with Age Dummy
Raw
gistfile1.txt
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Attaching package: 'dplyr'\n",
"\n",
"The following objects are masked from 'package:stats':\n",
"\n",
" filter, lag\n",
"\n",
"The following objects are masked from 'package:base':\n",
"\n",
" intersect, setdiff, setequal, union\n",
"\n",
"Warning message:\n",
"\"package 'sandwich' was built under R version 3.4.2\"Warning message:\n",
"\"package 'lmtest' was built under R version 3.4.2\"Loading required package: zoo\n",
"Warning message:\n",
"\"package 'zoo' was built under R version 3.4.2\"\n",
"Attaching package: 'zoo'\n",
"\n",
"The following objects are masked from 'package:base':\n",
"\n",
" as.Date, as.Date.numeric\n",
"\n"
]
}
],
"source": [
"## Loading library and working directory\n",
"library(ggplot2)\n",
"library(dplyr)\n",
"library(foreign)\n",
"library(sandwich)\n",
"library(lmtest)\n",
"\n",
"\n",
"setwd(\"C:\\\\Users\\\\vince\\\\Documents\\\\R Scripts\\\\R data\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"## Model 1"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data1 <- read.csv('Model1.csv')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t1009 obs. of 14 variables:\n",
" $ month : Factor w/ 24 levels \"2009-04\",\"2009-05\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ town : Factor w/ 1 level \"YISHUN\": 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ flat_type : Factor w/ 5 levels \"3 ROOM\",\"4 ROOM\",..: 2 2 3 4 1 3 2 2 2 2 ...\n",
" $ block : Factor w/ 159 levels \"201\",\"202\",\"203\",..: 20 20 21 24 135 141 119 123 83 89 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 1 1 1 1 2 2 3 3 4 4 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 3 4 1 2 3 3 2 2 4 ...\n",
" $ floor_area_sqm : int 108 103 121 146 74 122 84 103 84 84 ...\n",
" $ flat_model : Factor w/ 7 levels \"Apartment\",\"Improved\",..: 4 4 2 3 4 2 7 4 7 7 ...\n",
" $ lease_commence_date: int 1988 1988 1988 1988 1987 1987 1985 1986 1987 1987 ...\n",
" $ Age : int 21 21 21 21 22 22 24 23 22 22 ...\n",
" $ resale_price : int 275000 260000 302000 399000 230000 373000 272000 315000 248500 270000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 1 0 ...\n",
" $ Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n"
]
}
],
"source": [
"str(data1)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data1$Age <- as.factor(data1$Age)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t1009 obs. of 14 variables:\n",
" $ month : Factor w/ 24 levels \"2009-04\",\"2009-05\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ town : Factor w/ 1 level \"YISHUN\": 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ flat_type : Factor w/ 5 levels \"3 ROOM\",\"4 ROOM\",..: 2 2 3 4 1 3 2 2 2 2 ...\n",
" $ block : Factor w/ 159 levels \"201\",\"202\",\"203\",..: 20 20 21 24 135 141 119 123 83 89 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 1 1 1 1 2 2 3 3 4 4 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 3 4 1 2 3 3 2 2 4 ...\n",
" $ floor_area_sqm : int 108 103 121 146 74 122 84 103 84 84 ...\n",
" $ flat_model : Factor w/ 7 levels \"Apartment\",\"Improved\",..: 4 4 2 3 4 2 7 4 7 7 ...\n",
" $ lease_commence_date: int 1988 1988 1988 1988 1987 1987 1985 1986 1987 1987 ...\n",
" $ Age : Factor w/ 12 levels \"16\",\"17\",\"18\",..: 6 6 6 6 7 7 9 8 7 7 ...\n",
" $ resale_price : int 275000 260000 302000 399000 230000 373000 272000 315000 248500 270000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 1 0 ...\n",
" $ Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n"
]
}
],
"source": [
"str(data1)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
" month town flat_type block \n",
" 2010-06: 65 YISHUN:1009 3 ROOM :228 345 : 15 \n",
" 2010-05: 58 4 ROOM :508 771 : 15 \n",
" 2010-10: 54 5 ROOM :174 776 : 15 \n",
" 2010-07: 53 EXECUTIVE : 84 303 : 14 \n",
" 2010-08: 53 MULTI-GENERATION: 15 353 : 14 \n",
" 2010-03: 51 354 : 14 \n",
" (Other):675 (Other):922 \n",
" street_name storey_range floor_area_sqm flat_model \n",
" YISHUN ST 61 :230 01 TO 03:273 Min. : 64.00 Apartment : 51 \n",
" YISHUN RING RD:170 04 TO 06:300 1st Qu.: 83.00 Improved :167 \n",
" YISHUN AVE 4 :162 07 TO 09:223 Median : 91.00 Maisonette : 33 \n",
" YISHUN ST 72 :129 10 TO 12:202 Mean : 99.19 Model A :337 \n",
" YISHUN CTRL : 84 13 TO 15: 11 3rd Qu.:121.00 Multi Generation: 15 \n",
" YISHUN AVE 3 : 65 Max. :181.00 New Generation : 88 \n",
" (Other) :169 Simplified :318 \n",
" lease_commence_date Age resale_price Treatment \n",
" Min. :1984 22 :274 Min. :165500 Min. :0.0000 \n",
" 1st Qu.:1986 23 :247 1st Qu.:280000 1st Qu.:0.0000 \n",
" Median :1987 24 :127 Median :317000 Median :0.0000 \n",
" Mean :1987 21 :126 Mean :334341 Mean :0.1655 \n",
" 3rd Qu.:1988 25 : 96 3rd Qu.:378000 3rd Qu.:0.0000 \n",
" Max. :1993 17 : 43 Max. :760888 Max. :1.0000 \n",
" (Other): 96 \n",
" Period2 Treatment_Period2\n",
" Min. :0.0000 Min. :0.00000 \n",
" 1st Qu.:0.0000 1st Qu.:0.00000 \n",
" Median :1.0000 Median :0.00000 \n",
" Mean :0.5263 Mean :0.08821 \n",
" 3rd Qu.:1.0000 3rd Qu.:0.00000 \n",
" Max. :1.0000 Max. :1.00000 \n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"summary(data1)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data1 <- data1 %>% mutate(ln_resale_price = log(resale_price))"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t1009 obs. of 15 variables:\n",
" $ month : Factor w/ 24 levels \"2009-04\",\"2009-05\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ town : Factor w/ 1 level \"YISHUN\": 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ flat_type : Factor w/ 5 levels \"3 ROOM\",\"4 ROOM\",..: 2 2 3 4 1 3 2 2 2 2 ...\n",
" $ block : Factor w/ 159 levels \"201\",\"202\",\"203\",..: 20 20 21 24 135 141 119 123 83 89 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 1 1 1 1 2 2 3 3 4 4 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 3 4 1 2 3 3 2 2 4 ...\n",
" $ floor_area_sqm : int 108 103 121 146 74 122 84 103 84 84 ...\n",
" $ flat_model : Factor w/ 7 levels \"Apartment\",\"Improved\",..: 4 4 2 3 4 2 7 4 7 7 ...\n",
" $ lease_commence_date: int 1988 1988 1988 1988 1987 1987 1985 1986 1987 1987 ...\n",
" $ Age : Factor w/ 12 levels \"16\",\"17\",\"18\",..: 6 6 6 6 7 7 9 8 7 7 ...\n",
" $ resale_price : int 275000 260000 302000 399000 230000 373000 272000 315000 248500 270000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 1 0 ...\n",
" $ Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ ln_resale_price : num 12.5 12.5 12.6 12.9 12.3 ...\n"
]
}
],
"source": [
"str(data1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"fit1 <- lm(data = data1, ln_resale_price ~ Treatment + Period2 + Treatment_Period2 + Age + month + flat_type + block + storey_range + floor_area_sqm + flat_model )"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"0.968796745642398"
],
"text/latex": [
"0.968796745642398"
],
"text/markdown": [
"0.968796745642398"
],
"text/plain": [
"[1] 0.9687967"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"summary(fit1)$r.squared "
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\n",
"t test of coefficients:\n",
"\n",
" Estimate Std. Error t value Pr(>|t|) \n",
"(Intercept) 11.90021002 0.05914490 201.2043 < 2.2e-16 ***\n",
"Treatment 0.10831968 0.04009370 2.7017 0.0070447 ** \n",
"Period2 0.25866963 0.02120865 12.1964 < 2.2e-16 ***\n",
"Treatment_Period2 -0.00352053 0.00765452 -0.4599 0.6456920 \n",
"Age17 0.00045324 0.02484431 0.0182 0.9854494 \n",
"Age18 -0.01309186 0.03393549 -0.3858 0.6997568 \n",
"Age19 -0.02531434 0.04659850 -0.5432 0.5871126 \n",
"Age20 0.12619499 0.04769102 2.6461 0.0083018 ** \n",
"Age21 0.11717973 0.04434541 2.6424 0.0083914 ** \n",
"Age22 0.10926336 0.04510373 2.4225 0.0156346 * \n",
"Age23 0.10244597 0.04824320 2.1235 0.0340141 * \n",
"Age24 0.09482856 0.05245462 1.8078 0.0710079 . \n",
"Age25 0.07154571 0.05821645 1.2290 0.2194463 \n",
"Age26 0.07600274 0.06740567 1.1275 0.2598497 \n",
"Age27 0.04383534 0.07554874 0.5802 0.5619248 \n",
"month2009-05 -0.00864507 0.01337904 -0.6462 0.5183571 \n",
"month2009-06 0.00636297 0.01078056 0.5902 0.5552051 \n",
"month2009-07 0.02221025 0.01135191 1.9565 0.0507497 . \n",
"month2009-08 0.02831928 0.01099690 2.5752 0.0101957 * \n",
"month2009-09 0.03795007 0.01269025 2.9905 0.0028703 ** \n",
"month2009-10 0.06035517 0.01125161 5.3641 1.064e-07 ***\n",
"month2009-11 0.07192084 0.00986901 7.2875 7.549e-13 ***\n",
"month2009-12 0.09202476 0.01162488 7.9162 8.118e-15 ***\n",
"month2010-01 0.10632477 0.01367760 7.7736 2.332e-14 ***\n",
"month2010-02 0.12805312 0.01360750 9.4105 < 2.2e-16 ***\n",
"month2010-03 0.12604815 0.01331642 9.4656 < 2.2e-16 ***\n",
"month2010-04 -0.12783026 0.01345301 -9.5020 < 2.2e-16 ***\n",
"month2010-05 -0.10653619 0.01393710 -7.6441 6.000e-14 ***\n",
"month2010-06 -0.08496277 0.01386571 -6.1275 1.396e-09 ***\n",
"month2010-07 -0.07244072 0.01309155 -5.5334 4.251e-08 ***\n",
"month2010-08 -0.04711464 0.01310296 -3.5957 0.0003432 ***\n",
"month2010-09 -0.04647357 0.01429802 -3.2504 0.0012006 ** \n",
"month2010-10 -0.00708659 0.01380689 -0.5133 0.6079071 \n",
"month2010-11 -0.01730454 0.01483327 -1.1666 0.2437166 \n",
"month2010-12 -0.00504607 0.01540685 -0.3275 0.7433590 \n",
"month2011-01 0.01538581 0.01030122 1.4936 0.1356749 \n",
"month2011-02 0.02121709 0.01100952 1.9272 0.0543120 . \n",
"flat_type4 ROOM 0.11031745 0.02058625 5.3588 1.095e-07 ***\n",
"flat_type5 ROOM 0.24098783 0.04804985 5.0154 6.516e-07 ***\n",
"flat_typeEXECUTIVE 0.40320255 0.06948052 5.8031 9.362e-09 ***\n",
"flat_typeMULTI-GENERATION 0.41718322 0.07105762 5.8711 6.332e-09 ***\n",
"block202 0.01287630 0.01760556 0.7314 0.4647621 \n",
"block203 0.04907803 0.01997364 2.4571 0.0142150 * \n",
"block204 -0.00276266 0.01497493 -0.1845 0.8536791 \n",
"block208 0.00219937 0.02979164 0.0738 0.9411680 \n",
"block302 -0.08189976 0.01903109 -4.3035 1.889e-05 ***\n",
"block303 -0.09413441 0.01977975 -4.7591 2.305e-06 ***\n",
"block304 -0.10218135 0.02090606 -4.8876 1.232e-06 ***\n",
"block305 -0.07538724 0.02963085 -2.5442 0.0111384 * \n",
"block306 -0.05763601 0.01786582 -3.2260 0.0013059 ** \n",
"block320 -0.12244561 0.02858878 -4.2830 2.067e-05 ***\n",
"block321 -0.14083799 0.02054472 -6.8552 1.419e-11 ***\n",
"block322 -0.12204288 0.02872458 -4.2487 2.402e-05 ***\n",
"block323 -0.13271990 0.02454331 -5.4076 8.429e-08 ***\n",
"block324 -0.21822394 0.03118442 -6.9979 5.480e-12 ***\n",
"block325 -0.21086154 0.03247765 -6.4925 1.477e-10 ***\n",
"block326 -0.21297178 0.03115494 -6.8359 1.611e-11 ***\n",
"block327 -0.16984111 0.02383629 -7.1253 2.310e-12 ***\n",
"block345 -0.20187000 0.02250609 -8.9696 < 2.2e-16 ***\n",
"block346 -0.18944459 0.02045619 -9.2610 < 2.2e-16 ***\n",
"block349 -0.19159341 0.03197230 -5.9925 3.117e-09 ***\n",
"block350 -0.18005782 0.02017149 -8.9264 < 2.2e-16 ***\n",
"block350A -0.34387195 0.03104370 -11.0770 < 2.2e-16 ***\n",
"block351 -0.18702330 0.05939206 -3.1490 0.0016991 ** \n",
"block352 -0.21787207 0.04206374 -5.1796 2.813e-07 ***\n",
"block353 -0.20583038 0.02903185 -7.0898 2.943e-12 ***\n",
"block354 -0.18330593 0.02779604 -6.5947 7.717e-11 ***\n",
"block355 -0.22333230 0.06220897 -3.5900 0.0003507 ***\n",
"block356 -0.19940558 0.03007258 -6.6308 6.122e-11 ***\n",
"block415 -0.07274387 0.04464078 -1.6295 0.1035908 \n",
"block416 -0.08515452 0.03971406 -2.1442 0.0323168 * \n",
"block602 -0.14946313 0.04445368 -3.3622 0.0008097 ***\n",
"block603 -0.18356888 0.04282523 -4.2865 2.036e-05 ***\n",
"block604 -0.06767777 0.02623127 -2.5800 0.0100552 * \n",
"block605 -0.20812067 0.04294686 -4.8460 1.512e-06 ***\n",
"block607 -0.08123158 0.03276848 -2.4790 0.0133808 * \n",
"block608 0.00897285 0.03911901 0.2294 0.8186372 \n",
"block609 -0.05873250 0.02053508 -2.8601 0.0043447 ** \n",
"block610 -0.06231471 0.02296391 -2.7136 0.0067982 ** \n",
"block611 -0.10197722 0.03787995 -2.6921 0.0072477 ** \n",
"block612 -0.06423632 0.02413703 -2.6613 0.0079388 ** \n",
"block613 -0.04335926 0.02054416 -2.1105 0.0351202 * \n",
"block614 -0.13860259 0.03104062 -4.4652 9.143e-06 ***\n",
"block615 -0.02627392 0.02122388 -1.2379 0.2160991 \n",
"block616 0.00867943 0.03068422 0.2829 0.7773547 \n",
"block617 -0.03185981 0.02079501 -1.5321 0.1258938 \n",
"block618 0.04001940 0.03698075 1.0822 0.2795022 \n",
"block619 -0.01889257 0.01760827 -1.0729 0.2836212 \n",
"block620 0.01258064 0.01898324 0.6627 0.5076976 \n",
"block621 -0.03924730 0.02082158 -1.8849 0.0597992 . \n",
"block622 0.00592209 0.01843794 0.3212 0.7481496 \n",
"block624 -0.04977333 0.02321848 -2.1437 0.0323567 * \n",
"block625 -0.09785891 0.06782950 -1.4427 0.1494891 \n",
"block626 -0.01780302 0.02460342 -0.7236 0.4695222 \n",
"block627 -0.01497961 0.01955488 -0.7660 0.4438835 \n",
"block628 -0.05524118 0.03212955 -1.7193 0.0859399 . \n",
"block629 -0.04265981 0.02117340 -2.0148 0.0442598 * \n",
"block630 -0.04074219 0.02401854 -1.6963 0.0902198 . \n",
"block631 0.03795275 0.04382655 0.8660 0.3867615 \n",
"block632 -0.08770175 0.02321858 -3.7772 0.0001703 ***\n",
"block633 -0.12705319 0.03693230 -3.4402 0.0006113 ***\n",
"block633A 0.08418950 0.03750598 2.2447 0.0250589 * \n",
"block634 -0.09333474 0.02106387 -4.4310 1.068e-05 ***\n",
"block635 -0.04861870 0.01802138 -2.6978 0.0071255 ** \n",
"block636 -0.09393016 0.03047647 -3.0821 0.0021259 ** \n",
"block636A 0.02971574 0.03118561 0.9529 0.3409438 \n",
"block637 -0.08857909 0.02964604 -2.9879 0.0028946 ** \n",
"block638 -0.08520064 0.02045581 -4.1651 3.449e-05 ***\n",
"block639 -0.19010127 0.04243506 -4.4798 8.553e-06 ***\n",
"block640 -0.09894355 0.03003342 -3.2944 0.0010293 ** \n",
"block641 -0.02721775 0.02173643 -1.2522 0.2108713 \n",
"block642 -0.16399260 0.04517469 -3.6302 0.0003011 ***\n",
"block643 -0.25343446 0.05208502 -4.8658 1.372e-06 ***\n",
"block644 -0.19725463 0.04556876 -4.3287 1.689e-05 ***\n",
"block645 -0.05992656 0.01930697 -3.1039 0.0019769 ** \n",
"block645A -0.10449720 0.01845152 -5.6633 2.067e-08 ***\n",
"block646 -0.16653932 0.04235633 -3.9319 9.156e-05 ***\n",
"block647 -0.18246564 0.04189668 -4.3551 1.502e-05 ***\n",
"block651 -0.18425585 0.04644533 -3.9672 7.923e-05 ***\n",
"block652 -0.05965040 0.03437269 -1.7354 0.0830530 . \n",
"block653 -0.18481283 0.04336831 -4.2615 2.271e-05 ***\n",
"block654 -0.12434558 0.03285812 -3.7843 0.0001656 ***\n",
"block655 -0.18390899 0.04344521 -4.2331 2.571e-05 ***\n",
"block657 -0.18519833 0.04485110 -4.1292 4.021e-05 ***\n",
"block658 -0.20155379 0.04656639 -4.3283 1.692e-05 ***\n",
"block659 -0.13130364 0.04183512 -3.1386 0.0017595 ** \n",
"block660 -0.17172064 0.04257402 -4.0335 6.020e-05 ***\n",
"block661 -0.06497816 0.02241923 -2.8983 0.0038537 ** \n",
"block662 -0.09720485 0.01875347 -5.1833 2.760e-07 ***\n",
"block663 -0.08106686 0.02322700 -3.4902 0.0005089 ***\n",
"block663A 0.07700603 0.04100126 1.8781 0.0607240 . \n",
"block664 0.06313830 0.04199783 1.5034 0.1331362 \n",
"block664A 0.03832194 0.03728734 1.0277 0.3043782 \n",
"block666 -0.09330924 0.04547453 -2.0519 0.0405027 * \n",
"block666A -0.13445904 0.05720292 -2.3506 0.0189858 * \n",
"block744 0.02457600 0.03619314 0.6790 0.4973182 \n",
"block745 0.06645224 0.02146094 3.0964 0.0020267 ** \n",
"block746 0.05833353 0.02486922 2.3456 0.0192380 * \n",
"block747 -0.02017460 0.02271749 -0.8881 0.3747715 \n",
"block748 0.01003766 0.02518390 0.3986 0.6903127 \n",
"block749 0.07597325 0.04158199 1.8271 0.0680597 . \n",
"block750 0.01680924 0.02942524 0.5713 0.5679881 \n",
"block751 0.05911889 0.02560523 2.3089 0.0212041 * \n",
"block752 -0.01356651 0.03028514 -0.4480 0.6543031 \n",
"block753 0.02782462 0.01733225 1.6054 0.1088059 \n",
"block754 -0.00459803 0.02664968 -0.1725 0.8630597 \n",
"block755 -0.04907517 0.03282183 -1.4952 0.1352549 \n",
"block756 0.01753088 0.02631535 0.6662 0.5054842 \n",
"block757 -0.02530511 0.02193206 -1.1538 0.2489270 \n",
"block758 -0.04292393 0.02205580 -1.9462 0.0519846 . \n",
"block759 -0.03185137 0.02876723 -1.1072 0.2685342 \n",
"block760 -0.01256680 0.02207188 -0.5694 0.5692722 \n",
"block761 -0.10006796 0.04176589 -2.3959 0.0168061 * \n",
"block762 -0.02512901 0.02912878 -0.8627 0.3885669 \n",
"block763 -0.04029210 0.01849959 -2.1780 0.0296960 * \n",
"block764 -0.03623670 0.03204116 -1.1309 0.2584166 \n",
"block765 -0.01462694 0.02818875 -0.5189 0.6039782 \n",
"block766 -0.02267298 0.02659417 -0.8526 0.3941602 \n",
"block767 -0.08216419 0.01826842 -4.4976 7.884e-06 ***\n",
"block768 -0.05601625 0.02754048 -2.0340 0.0422834 * \n",
"block769 -0.08619945 0.04135251 -2.0845 0.0374295 * \n",
"block770 -0.04989370 0.02591012 -1.9256 0.0545011 . \n",
"block771 -0.06316082 0.02742816 -2.3028 0.0215461 * \n",
"block772 -0.03824297 0.02708852 -1.4118 0.1584024 \n",
"block773 -0.09817679 0.02049801 -4.7896 1.990e-06 ***\n",
"block775 -0.01951796 0.02254639 -0.8657 0.3869238 \n",
"block776 -0.03344789 0.02426059 -1.3787 0.1683731 \n",
"block777 -0.04772492 0.04205873 -1.1347 0.2568304 \n",
"block778 -0.05435783 0.02786738 -1.9506 0.0514529 . \n",
"block779 -0.02008469 0.01623340 -1.2372 0.2163574 \n",
"block780 -0.12946977 0.05186003 -2.4965 0.0127409 * \n",
"block781 -0.02818213 0.02078104 -1.3561 0.1754333 \n",
"block783 -0.03777605 0.01942554 -1.9447 0.0521644 . \n",
"block784 -0.03856446 0.01652836 -2.3332 0.0198818 * \n",
"block785 -0.05089762 0.02749566 -1.8511 0.0645196 . \n",
"block786 -0.00752832 0.02032371 -0.3704 0.7111666 \n",
"block787 -0.02004652 0.02098792 -0.9551 0.3397911 \n",
"block788 -0.04954614 0.01598760 -3.0990 0.0020091 ** \n",
"block789 -0.10367049 0.05101230 -2.0323 0.0424551 * \n",
"block790 0.00398871 0.02036087 0.1959 0.8447375 \n",
"block791 -0.05468200 0.03596846 -1.5203 0.1288346 \n",
"block792 -0.09935197 0.02785758 -3.5664 0.0003833 ***\n",
"block796 0.01418782 0.02234506 0.6349 0.5256468 \n",
"block796A -0.04814389 0.01556828 -3.0924 0.0020538 ** \n",
"block797 0.03108556 0.05343599 0.5817 0.5609086 \n",
"block855 -0.04567749 0.02552341 -1.7896 0.0738895 . \n",
"block858 -0.02299421 0.01991490 -1.1546 0.2485876 \n",
"block859 -0.02394462 0.02114554 -1.1324 0.2578157 \n",
"block860 -0.04452995 0.02009637 -2.2158 0.0269832 * \n",
"block861 -0.04949435 0.02719164 -1.8202 0.0690995 . \n",
"block862 -0.03976144 0.02095650 -1.8973 0.0581422 . \n",
"block863 -0.02053404 0.02230524 -0.9206 0.3575392 \n",
"block926 -0.12178006 0.01422500 -8.5610 < 2.2e-16 ***\n",
"block927 0.01099822 0.01663536 0.6611 0.5087151 \n",
"block928 0.03360974 0.04395806 0.7646 0.4447421 \n",
"block932 0.02283721 0.01583921 1.4418 0.1497441 \n",
"storey_range04 TO 06 0.02944434 0.00430886 6.8334 1.638e-11 ***\n",
"storey_range07 TO 09 0.04967700 0.00464313 10.6990 < 2.2e-16 ***\n",
"storey_range10 TO 12 0.06271884 0.00434382 14.4386 < 2.2e-16 ***\n",
"storey_range13 TO 15 0.04526319 0.01243867 3.6389 0.0002913 ***\n",
"floor_area_sqm 0.00434774 0.00064833 6.7060 3.768e-11 ***\n",
"flat_modelImproved -0.01615277 0.03890603 -0.4152 0.6781253 \n",
"flat_modelMaisonette -0.03356367 0.01415513 -2.3711 0.0179685 * \n",
"flat_modelModel A 0.05752479 0.01428961 4.0256 6.219e-05 ***\n",
"flat_modelNew Generation 0.05363448 0.01650396 3.2498 0.0012029 ** \n",
"---\n",
"Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"## Robust SE\n",
"coeftest(fit1, vcov = vcovHC(fit1, \"HC1\")) "
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 150, 164, 168, 177, 355, 648, 699, 813, 818, 973, 988, 1009\"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 150, 164, 168, 177, 355, 648, 699, 813, 818, 973, 988, 1009\"Warning message in sqrt(crit * p * (1 - hh)/hh):\n",
"\"NaNs produced\"Warning message in sqrt(crit * p * (1 - hh)/hh):\n",
"\"NaNs produced\""
]
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAMAAADKOT/pAAAAOVBMVEUAAABNTU1oaGh8fHx/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\n2EfwYPf7owAAAABJRU5ErkJggg==",
"text/plain": [
"Plot with title \"\""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"par(mfrow = c(2, 2))\n",
"plot(fit1)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"## Model 2"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data2 <- read.csv('Model2.csv')"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t1009 obs. of 16 variables:\n",
" $ month : Factor w/ 24 levels \"2009-04\",\"2009-05\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ town : Factor w/ 1 level \"YISHUN\": 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ flat_type : Factor w/ 5 levels \"3 ROOM\",\"4 ROOM\",..: 2 2 3 4 1 3 2 2 2 2 ...\n",
" $ block : Factor w/ 159 levels \"201\",\"202\",\"203\",..: 20 20 21 24 135 141 119 123 83 89 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 1 1 1 1 2 2 3 3 4 4 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 3 4 1 2 3 3 2 2 4 ...\n",
" $ floor_area_sqm : int 108 103 121 146 74 122 84 103 84 84 ...\n",
" $ flat_model : Factor w/ 7 levels \"Apartment\",\"Improved\",..: 4 4 2 3 4 2 7 4 7 7 ...\n",
" $ lease_commence_date: int 1988 1988 1988 1988 1987 1987 1985 1986 1987 1987 ...\n",
" $ resale_price : int 275000 260000 302000 399000 230000 373000 272000 315000 248500 270000 ...\n",
" $ Age : int 21 21 21 21 22 22 24 23 22 22 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 1 0 ...\n",
" $ Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Period3 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period3 : int 0 0 0 0 0 0 0 0 0 0 ...\n"
]
}
],
"source": [
"str(data2)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data2 <- data2 %>% mutate(ln_resale_price = log(resale_price))"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data2$Age <- as.factor(data2$Age)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t1009 obs. of 17 variables:\n",
" $ month : Factor w/ 24 levels \"2009-04\",\"2009-05\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ town : Factor w/ 1 level \"YISHUN\": 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ flat_type : Factor w/ 5 levels \"3 ROOM\",\"4 ROOM\",..: 2 2 3 4 1 3 2 2 2 2 ...\n",
" $ block : Factor w/ 159 levels \"201\",\"202\",\"203\",..: 20 20 21 24 135 141 119 123 83 89 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 1 1 1 1 2 2 3 3 4 4 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 3 4 1 2 3 3 2 2 4 ...\n",
" $ floor_area_sqm : int 108 103 121 146 74 122 84 103 84 84 ...\n",
" $ flat_model : Factor w/ 7 levels \"Apartment\",\"Improved\",..: 4 4 2 3 4 2 7 4 7 7 ...\n",
" $ lease_commence_date: int 1988 1988 1988 1988 1987 1987 1985 1986 1987 1987 ...\n",
" $ resale_price : int 275000 260000 302000 399000 230000 373000 272000 315000 248500 270000 ...\n",
" $ Age : Factor w/ 12 levels \"16\",\"17\",\"18\",..: 6 6 6 6 7 7 9 8 7 7 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 1 0 ...\n",
" $ Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Period3 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period3 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ ln_resale_price : num 12.5 12.5 12.6 12.9 12.3 ...\n"
]
}
],
"source": [
"str(data2)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\n",
"t test of coefficients:\n",
"\n",
" Estimate Std. Error t value Pr(>|t|) \n",
"(Intercept) 11.89893892 0.05887259 202.1134 < 2.2e-16 ***\n",
"Treatment 0.10848801 0.04007254 2.7073 0.0069276 ** \n",
"Period2 0.21227703 0.01439623 14.7453 < 2.2e-16 ***\n",
"Treatment_Period2 -0.00774520 0.00848355 -0.9130 0.3615340 \n",
"Period3 0.25684814 0.02132436 12.0448 < 2.2e-16 ***\n",
"Treatment_Period3 0.00274287 0.00978696 0.2803 0.7793519 \n",
"Age17 -0.00012306 0.02488420 -0.0049 0.9960555 \n",
"Age18 -0.01319477 0.03388672 -0.3894 0.6970992 \n",
"Age19 -0.02776753 0.04675665 -0.5939 0.5527642 \n",
"Age20 0.12682012 0.04743608 2.6735 0.0076590 ** \n",
"Age21 0.11826233 0.04411297 2.6809 0.0074931 ** \n",
"Age22 0.11078019 0.04490898 2.4668 0.0138415 * \n",
"Age23 0.10467903 0.04811095 2.1758 0.0298624 * \n",
"Age24 0.09665289 0.05226477 1.8493 0.0647828 . \n",
"Age25 0.07360155 0.05802614 1.2684 0.2050154 \n",
"Age26 0.07903754 0.06729023 1.1746 0.2405123 \n",
"Age27 0.04787855 0.07552904 0.6339 0.5263206 \n",
"month2009-05 -0.00874771 0.01338184 -0.6537 0.5134922 \n",
"month2009-06 0.00634902 0.01077683 0.5891 0.5559358 \n",
"month2009-07 0.02209979 0.01134891 1.9473 0.0518464 . \n",
"month2009-08 0.02856032 0.01099492 2.5976 0.0095599 ** \n",
"month2009-09 0.03799390 0.01268203 2.9959 0.0028207 ** \n",
"month2009-10 0.06042098 0.01125459 5.3686 1.040e-07 ***\n",
"month2009-11 0.07199024 0.00986693 7.2961 7.119e-13 ***\n",
"month2009-12 0.09211035 0.01161683 7.9290 7.386e-15 ***\n",
"month2010-01 0.10588484 0.01363136 7.7677 2.438e-14 ***\n",
"month2010-02 0.12773787 0.01357746 9.4081 < 2.2e-16 ***\n",
"month2010-03 0.12567414 0.01328233 9.4618 < 2.2e-16 ***\n",
"month2010-04 -0.08108047 0.00980700 -8.2676 5.640e-16 ***\n",
"month2010-05 -0.05986574 0.01041843 -5.7461 1.296e-08 ***\n",
"month2010-06 -0.03815254 0.01017703 -3.7489 0.0001904 ***\n",
"month2010-07 -0.02583532 0.00964717 -2.6780 0.0075572 ** \n",
"month2010-08 -0.00048738 0.01016242 -0.0480 0.9617607 \n",
"month2010-10 -0.00641627 0.01386605 -0.4627 0.6436816 \n",
"month2010-11 -0.01686435 0.01482179 -1.1378 0.2555403 \n",
"month2010-12 -0.00451642 0.01542577 -0.2928 0.7697626 \n",
"month2011-01 0.01627951 0.01041043 1.5638 0.1182659 \n",
"month2011-02 0.02120915 0.01104591 1.9201 0.0552005 . \n",
"flat_type4 ROOM 0.11015831 0.02049100 5.3759 9.994e-08 ***\n",
"flat_type5 ROOM 0.24310037 0.04796500 5.0683 4.985e-07 ***\n",
"flat_typeEXECUTIVE 0.40445114 0.06931395 5.8351 7.797e-09 ***\n",
"flat_typeMULTI-GENERATION 0.41453592 0.07034269 5.8931 5.575e-09 ***\n",
"block202 0.01234702 0.01764367 0.6998 0.4842556 \n",
"block203 0.04843570 0.02001401 2.4201 0.0157377 * \n",
"block204 -0.00279447 0.01494426 -0.1870 0.8517133 \n",
"block208 0.00203647 0.03000572 0.0679 0.9459065 \n",
"block302 -0.08216377 0.01901567 -4.3208 1.749e-05 ***\n",
"block303 -0.09420490 0.01971403 -4.7786 2.099e-06 ***\n",
"block304 -0.10252060 0.02088992 -4.9077 1.116e-06 ***\n",
"block305 -0.07585007 0.02959936 -2.5626 0.0105717 * \n",
"block306 -0.05866992 0.01798534 -3.2621 0.0011526 ** \n",
"block320 -0.12253159 0.02867621 -4.2729 2.161e-05 ***\n",
"block321 -0.14120285 0.02056146 -6.8674 1.310e-11 ***\n",
"block322 -0.12225584 0.02863435 -4.2696 2.193e-05 ***\n",
"block323 -0.13282593 0.02447937 -5.4260 7.633e-08 ***\n",
"block324 -0.22013479 0.03115309 -7.0662 3.457e-12 ***\n",
"block325 -0.21266335 0.03254178 -6.5351 1.129e-10 ***\n",
"block326 -0.21475938 0.03126542 -6.8689 1.297e-11 ***\n",
"block327 -0.17032531 0.02377944 -7.1627 1.790e-12 ***\n",
"block345 -0.20207063 0.02248412 -8.9873 < 2.2e-16 ***\n",
"block346 -0.18969041 0.02045053 -9.2756 < 2.2e-16 ***\n",
"block349 -0.19172290 0.03205997 -5.9801 3.354e-09 ***\n",
"block350 -0.18029579 0.02014122 -8.9516 < 2.2e-16 ***\n",
"block350A -0.34627211 0.03129252 -11.0657 < 2.2e-16 ***\n",
"block351 -0.18879260 0.05951555 -3.1722 0.0015707 ** \n",
"block352 -0.21971066 0.04228366 -5.1961 2.583e-07 ***\n",
"block353 -0.20552378 0.02891626 -7.1076 2.610e-12 ***\n",
"block354 -0.18300543 0.02772716 -6.6002 7.454e-11 ***\n",
"block355 -0.22536782 0.06212696 -3.6275 0.0003042 ***\n",
"block356 -0.20147180 0.03015660 -6.6809 4.438e-11 ***\n",
"block415 -0.07176825 0.04415577 -1.6253 0.1044820 \n",
"block416 -0.08372720 0.03959349 -2.1147 0.0347656 * \n",
"block602 -0.15162338 0.04459441 -3.4001 0.0007070 ***\n",
"block603 -0.18661643 0.04281281 -4.3589 1.477e-05 ***\n",
"block604 -0.06555798 0.02633143 -2.4897 0.0129855 * \n",
"block605 -0.20831687 0.04283763 -4.8629 1.392e-06 ***\n",
"block607 -0.08207187 0.03296558 -2.4896 0.0129892 * \n",
"block608 0.00941923 0.04010608 0.2349 0.8143789 \n",
"block609 -0.05951247 0.02055328 -2.8955 0.0038880 ** \n",
"block610 -0.06321248 0.02302518 -2.7454 0.0061795 ** \n",
"block611 -0.10463103 0.03809231 -2.7468 0.0061532 ** \n",
"block612 -0.06530718 0.02421335 -2.6972 0.0071401 ** \n",
"block613 -0.04426516 0.02059776 -2.1490 0.0319305 * \n",
"block614 -0.14124902 0.03120212 -4.5269 6.891e-06 ***\n",
"block615 -0.02649877 0.02117097 -1.2517 0.2110597 \n",
"block616 0.00740133 0.03056976 0.2421 0.8087546 \n",
"block617 -0.03190123 0.02073743 -1.5383 0.1243594 \n",
"block618 0.04264137 0.03700487 1.1523 0.2495334 \n",
"block619 -0.01987136 0.01751680 -1.1344 0.2569581 \n",
"block620 0.01208199 0.01891239 0.6388 0.5231092 \n",
"block621 -0.03937296 0.02085827 -1.8876 0.0594344 . \n",
"block622 0.00542922 0.01848845 0.2937 0.7690975 \n",
"block624 -0.05020782 0.02313687 -2.1700 0.0302967 * \n",
"block625 -0.09827751 0.06792971 -1.4468 0.1483563 \n",
"block626 -0.01926183 0.02480700 -0.7765 0.4377016 \n",
"block627 -0.01533288 0.01946447 -0.7877 0.4310832 \n",
"block628 -0.05545632 0.03217227 -1.7237 0.0851414 . \n",
"block629 -0.04284973 0.02124316 -2.0171 0.0440167 * \n",
"block630 -0.04128327 0.02406520 -1.7155 0.0866437 . \n",
"block631 0.03985843 0.04389183 0.9081 0.3640947 \n",
"block632 -0.08730575 0.02297313 -3.8003 0.0001554 ***\n",
"block633 -0.12567409 0.03639188 -3.4534 0.0005826 ***\n",
"block633A 0.08930185 0.03764912 2.3720 0.0179293 * \n",
"block634 -0.09431754 0.02113080 -4.4635 9.215e-06 ***\n",
"block635 -0.04950777 0.01806033 -2.7412 0.0062568 ** \n",
"block636 -0.09524274 0.03067105 -3.1053 0.0019676 ** \n",
"block636A 0.02838743 0.03087470 0.9194 0.3581416 \n",
"block637 -0.08983820 0.02970364 -3.0245 0.0025699 ** \n",
"block638 -0.08608561 0.02049708 -4.1999 2.969e-05 ***\n",
"block639 -0.19005220 0.04245855 -4.4762 8.698e-06 ***\n",
"block640 -0.09767859 0.03030401 -3.2233 0.0013184 ** \n",
"block641 -0.02423528 0.02278062 -1.0639 0.2877141 \n",
"block642 -0.16517865 0.04511708 -3.6611 0.0002676 ***\n",
"block643 -0.25611268 0.05244864 -4.8831 1.260e-06 ***\n",
"block644 -0.19585909 0.04545507 -4.3088 1.845e-05 ***\n",
"block645 -0.06008380 0.01960284 -3.0651 0.0022491 ** \n",
"block645A -0.10350055 0.01907618 -5.4256 7.649e-08 ***\n",
"block646 -0.17119125 0.04251646 -4.0265 6.199e-05 ***\n",
"block647 -0.18133156 0.04196535 -4.3210 1.748e-05 ***\n",
"block651 -0.18291649 0.04641316 -3.9410 8.819e-05 ***\n",
"block652 -0.06069323 0.03423785 -1.7727 0.0766585 . \n",
"block653 -0.18558176 0.04316938 -4.2989 1.927e-05 ***\n",
"block654 -0.12800044 0.03300155 -3.8786 0.0001136 ***\n",
"block655 -0.18444774 0.04345130 -4.2449 2.442e-05 ***\n",
"block657 -0.18553101 0.04487794 -4.1341 3.938e-05 ***\n",
"block658 -0.20171978 0.04652338 -4.3359 1.636e-05 ***\n",
"block659 -0.13693554 0.04203479 -3.2577 0.0011705 ** \n",
"block660 -0.17245375 0.04248776 -4.0589 5.413e-05 ***\n",
"block661 -0.06733749 0.02264037 -2.9742 0.0030253 ** \n",
"block662 -0.09822021 0.01880149 -5.2241 2.232e-07 ***\n",
"block663 -0.08165499 0.02330873 -3.5032 0.0004851 ***\n",
"block663A 0.07895451 0.04083192 1.9336 0.0535077 . \n",
"block664 0.06262714 0.04168969 1.5022 0.1334331 \n",
"block664A 0.03771082 0.03688523 1.0224 0.3069078 \n",
"block666 -0.09206879 0.04505635 -2.0434 0.0413373 * \n",
"block666A -0.13544334 0.05729682 -2.3639 0.0183214 * \n",
"block744 0.02325568 0.03640410 0.6388 0.5231220 \n",
"block745 0.06644799 0.02136260 3.1105 0.0019338 ** \n",
"block746 0.05695416 0.02490904 2.2865 0.0224854 * \n",
"block747 -0.02087207 0.02271764 -0.9188 0.3584969 \n",
"block748 0.00883451 0.02516790 0.3510 0.7256632 \n",
"block749 0.07483548 0.04185249 1.7881 0.0741405 . \n",
"block750 0.01570201 0.02960662 0.5304 0.5960127 \n",
"block751 0.05866809 0.02561336 2.2905 0.0222492 * \n",
"block752 -0.01480684 0.03031197 -0.4885 0.6253422 \n",
"block753 0.02614575 0.01743318 1.4998 0.1340671 \n",
"block754 -0.00566432 0.02663395 -0.2127 0.8316360 \n",
"block755 -0.05039658 0.03287148 -1.5331 0.1256352 \n",
"block756 0.01630018 0.02630404 0.6197 0.5356420 \n",
"block757 -0.02623595 0.02185395 -1.2005 0.2302943 \n",
"block758 -0.04380025 0.02207268 -1.9844 0.0475552 * \n",
"block759 -0.03275147 0.02874901 -1.1392 0.2549509 \n",
"block760 -0.01376265 0.02218219 -0.6204 0.5351463 \n",
"block761 -0.10093069 0.04208292 -2.3984 0.0166952 * \n",
"block762 -0.02606780 0.02915783 -0.8940 0.3715770 \n",
"block763 -0.03950304 0.01856756 -2.1275 0.0336802 * \n",
"block764 -0.03727553 0.03203721 -1.1635 0.2449693 \n",
"block765 -0.01556699 0.02812453 -0.5535 0.5800736 \n",
"block766 -0.02286246 0.02641620 -0.8655 0.3870387 \n",
"block767 -0.08329742 0.01823115 -4.5690 5.672e-06 ***\n",
"block768 -0.05703218 0.02744520 -2.0780 0.0380229 * \n",
"block769 -0.08686241 0.04206691 -2.0649 0.0392565 * \n",
"block770 -0.05102342 0.02589764 -1.9702 0.0491592 * \n",
"block771 -0.06400740 0.02739632 -2.3364 0.0197181 * \n",
"block772 -0.03925886 0.02705033 -1.4513 0.1470796 \n",
"block773 -0.09925125 0.02055573 -4.8284 1.648e-06 ***\n",
"block775 -0.02029442 0.02254094 -0.9003 0.3682113 \n",
"block776 -0.03422874 0.02420496 -1.4141 0.1577140 \n",
"block777 -0.04811881 0.04215246 -1.1415 0.2539846 \n",
"block778 -0.05395563 0.02777173 -1.9428 0.0523864 . \n",
"block779 -0.02167961 0.01636611 -1.3247 0.1856593 \n",
"block780 -0.12987176 0.05182259 -2.5061 0.0124044 * \n",
"block781 -0.02849949 0.02078721 -1.3710 0.1707547 \n",
"block783 -0.03864856 0.01943579 -1.9885 0.0470927 * \n",
"block784 -0.03958665 0.01658182 -2.3874 0.0172006 * \n",
"block785 -0.05118097 0.02752836 -1.8592 0.0633631 . \n",
"block786 -0.00797666 0.02018324 -0.3952 0.6927913 \n",
"block787 -0.02034805 0.02099562 -0.9692 0.3327587 \n",
"block788 -0.05047889 0.01595667 -3.1635 0.0016175 ** \n",
"block789 -0.10383300 0.05074806 -2.0460 0.0410768 * \n",
"block790 0.00348066 0.02041820 0.1705 0.8646847 \n",
"block791 -0.05707326 0.03573453 -1.5971 0.1106266 \n",
"block792 -0.10214801 0.02802797 -3.6445 0.0002851 ***\n",
"block796 0.01303538 0.02230034 0.5845 0.5590232 \n",
"block796A -0.04793549 0.01552414 -3.0878 0.0020858 ** \n",
"block797 0.02966358 0.05321943 0.5574 0.5774214 \n",
"block855 -0.04596732 0.02547536 -1.8044 0.0715457 . \n",
"block858 -0.02341611 0.01994671 -1.1739 0.2407697 \n",
"block859 -0.02432550 0.02110811 -1.1524 0.2494898 \n",
"block860 -0.04430512 0.02003587 -2.2113 0.0272968 * \n",
"block861 -0.04937904 0.02712606 -1.8204 0.0690771 . \n",
"block862 -0.03969019 0.02090266 -1.8988 0.0579476 . \n",
"block863 -0.02089429 0.02233566 -0.9355 0.3498286 \n",
"block926 -0.12568913 0.01509825 -8.3247 3.623e-16 ***\n",
"block927 0.01265510 0.01748276 0.7239 0.4693613 \n",
"block928 0.03420888 0.04418166 0.7743 0.4389944 \n",
"block932 0.02631046 0.01676030 1.5698 0.1168537 \n",
"storey_range04 TO 06 0.02939252 0.00430253 6.8315 1.661e-11 ***\n",
"storey_range07 TO 09 0.04958736 0.00463803 10.6915 < 2.2e-16 ***\n",
"storey_range10 TO 12 0.06271009 0.00433642 14.4612 < 2.2e-16 ***\n",
"storey_range13 TO 15 0.04526137 0.01238291 3.6551 0.0002738 ***\n",
"floor_area_sqm 0.00435463 0.00064495 6.7519 2.797e-11 ***\n",
"flat_modelImproved -0.01864457 0.03872764 -0.4814 0.6303436 \n",
"flat_modelMaisonette -0.03389939 0.01441375 -2.3519 0.0189195 * \n",
"flat_modelModel A 0.05734944 0.01422460 4.0317 6.065e-05 ***\n",
"flat_modelNew Generation 0.05287573 0.01643043 3.2182 0.0013419 ** \n",
"---\n",
"Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fit2 <- lm(data = data2, ln_resale_price ~ Treatment + Period2 + Treatment_Period2 + Period3 + Treatment_Period3 + Age + month + flat_type + block + storey_range + floor_area_sqm + flat_model )\n",
"## Robust SE\n",
"coeftest(fit2, vcov = vcovHC(fit2, \"HC1\")) "
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"0.968825069343247"
],
"text/latex": [
"0.968825069343247"
],
"text/markdown": [
"0.968825069343247"
],
"text/plain": [
"[1] 0.9688251"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"summary(fit2)$r.squared "
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 150, 164, 168, 177, 355, 512, 648, 699, 813, 818, 973, 988, 1009\"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 150, 164, 168, 177, 355, 512, 648, 699, 813, 818, 973, 988, 1009\""
]
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAMAAADKOT/pAAAAOVBMVEUAAABNTU1oaGh8fHx/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\nP8LT5meYB2n2AAAAAElFTkSuQmCC",
"text/plain": [
"Plot with title \"\""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"par(mfrow = c(2, 2))\n",
"plot(fit2)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"## Model 3"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data3 <- read.csv('Model3.csv')\n"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t1194 obs. of 16 variables:\n",
" $ month : Factor w/ 30 levels \"2009-04\",\"2009-05\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ town : Factor w/ 1 level \"YISHUN\": 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ flat_type : Factor w/ 5 levels \"3 ROOM\",\"4 ROOM\",..: 2 2 3 4 1 3 2 2 2 2 ...\n",
" $ block : Factor w/ 162 levels \"201\",\"202\",\"203\",..: 20 20 21 24 137 143 120 124 84 90 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 1 1 1 1 2 2 3 3 4 4 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 3 4 1 2 3 3 2 2 4 ...\n",
" $ floor_area_sqm : int 108 103 121 146 74 122 84 103 84 84 ...\n",
" $ flat_model : Factor w/ 7 levels \"Apartment\",\"Improved\",..: 4 4 2 3 4 2 7 4 7 7 ...\n",
" $ lease_commence_date: int 1988 1988 1988 1988 1987 1987 1985 1986 1987 1987 ...\n",
" $ Age : int 21 21 21 21 22 22 24 23 22 22 ...\n",
" $ resale_price : int 275000 260000 302000 399000 230000 373000 272000 315000 248500 270000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 1 0 ...\n",
" $ Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Period3 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period3 : int 0 0 0 0 0 0 0 0 0 0 ...\n"
]
}
],
"source": [
"str(data3)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data3 <- data3 %>% mutate(ln_resale_price = log(resale_price))"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data3$Age <- as.factor(data3$Age)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t1194 obs. of 17 variables:\n",
" $ month : Factor w/ 30 levels \"2009-04\",\"2009-05\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ town : Factor w/ 1 level \"YISHUN\": 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ flat_type : Factor w/ 5 levels \"3 ROOM\",\"4 ROOM\",..: 2 2 3 4 1 3 2 2 2 2 ...\n",
" $ block : Factor w/ 162 levels \"201\",\"202\",\"203\",..: 20 20 21 24 137 143 120 124 84 90 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 1 1 1 1 2 2 3 3 4 4 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 3 4 1 2 3 3 2 2 4 ...\n",
" $ floor_area_sqm : int 108 103 121 146 74 122 84 103 84 84 ...\n",
" $ flat_model : Factor w/ 7 levels \"Apartment\",\"Improved\",..: 4 4 2 3 4 2 7 4 7 7 ...\n",
" $ lease_commence_date: int 1988 1988 1988 1988 1987 1987 1985 1986 1987 1987 ...\n",
" $ Age : Factor w/ 12 levels \"16\",\"17\",\"18\",..: 6 6 6 6 7 7 9 8 7 7 ...\n",
" $ resale_price : int 275000 260000 302000 399000 230000 373000 272000 315000 248500 270000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 1 0 ...\n",
" $ Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Period3 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period2 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ Treatment_Period3 : int 0 0 0 0 0 0 0 0 0 0 ...\n",
" $ ln_resale_price : num 12.5 12.5 12.6 12.9 12.3 ...\n"
]
}
],
"source": [
"str(data3)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\n",
"t test of coefficients:\n",
"\n",
" Estimate Std. Error t value Pr(>|t|) \n",
"(Intercept) 11.88418379 0.04974016 238.9253 < 2.2e-16 ***\n",
"Treatment 0.11183798 0.03332883 3.3556 0.0008224 ***\n",
"Period2 0.24566654 0.01972447 12.4549 < 2.2e-16 ***\n",
"Treatment_Period2 -0.00322176 0.00740462 -0.4351 0.6635851 \n",
"Period3 0.33473840 0.02098994 15.9476 < 2.2e-16 ***\n",
"Treatment_Period3 0.01555327 0.01044488 1.4891 0.1367883 \n",
"Age17 0.00940430 0.02396702 0.3924 0.6948590 \n",
"Age18 0.00718902 0.03058823 0.2350 0.8142379 \n",
"Age19 -0.00721713 0.04031174 -0.1790 0.8579488 \n",
"Age20 0.10837740 0.03937704 2.7523 0.0060272 ** \n",
"Age21 0.10730549 0.03639020 2.9487 0.0032665 ** \n",
"Age22 0.10526661 0.03748219 2.8084 0.0050772 ** \n",
"Age23 0.10531574 0.04095293 2.5716 0.0102687 * \n",
"Age24 0.11007906 0.04569334 2.4091 0.0161764 * \n",
"Age25 0.10219638 0.05150591 1.9842 0.0475160 * \n",
"Age26 0.10624659 0.05874048 1.8087 0.0707972 . \n",
"Age27 0.06341367 0.07560149 0.8388 0.4017927 \n",
"month2009-05 -0.00860058 0.01299623 -0.6618 0.5082713 \n",
"month2009-06 0.00642338 0.01042954 0.6159 0.5381150 \n",
"month2009-07 0.02360461 0.01106467 2.1333 0.0331456 * \n",
"month2009-08 0.02866658 0.01056254 2.7140 0.0067647 ** \n",
"month2009-09 0.03811579 0.01207856 3.1557 0.0016503 ** \n",
"month2009-10 0.06058484 0.01093145 5.5423 3.839e-08 ***\n",
"month2009-11 0.07313647 0.00952865 7.6754 3.980e-14 ***\n",
"month2009-12 0.09262748 0.01138009 8.1394 1.199e-15 ***\n",
"month2010-01 0.09737301 0.01312825 7.4171 2.592e-13 ***\n",
"month2010-02 0.12000465 0.01310319 9.1584 < 2.2e-16 ***\n",
"month2010-03 0.11748109 0.01254640 9.3637 < 2.2e-16 ***\n",
"month2010-04 -0.12118933 0.01282530 -9.4492 < 2.2e-16 ***\n",
"month2010-05 -0.10041255 0.01320722 -7.6028 6.774e-14 ***\n",
"month2010-06 -0.07932097 0.01305793 -6.0745 1.778e-09 ***\n",
"month2010-07 -0.06776605 0.01259395 -5.3808 9.278e-08 ***\n",
"month2010-08 -0.04322604 0.01233599 -3.5041 0.0004790 ***\n",
"month2010-09 -0.04170522 0.01364071 -3.0574 0.0022932 ** \n",
"month2010-10 -0.00053112 0.01327890 -0.0400 0.9681034 \n",
"month2010-11 -0.01208017 0.01402764 -0.8612 0.3893558 \n",
"month2010-12 -0.00165335 0.01450324 -0.1140 0.9092624 \n",
"month2011-01 0.01041911 0.00968505 1.0758 0.2822852 \n",
"month2011-02 0.01939510 0.01091782 1.7765 0.0759672 . \n",
"month2011-04 -0.06261043 0.01045430 -5.9890 2.963e-09 ***\n",
"month2011-05 -0.05507241 0.01122675 -4.9055 1.091e-06 ***\n",
"month2011-06 -0.04707666 0.01334292 -3.5282 0.0004378 ***\n",
"month2011-07 -0.02138082 0.01130427 -1.8914 0.0588669 . \n",
"month2011-08 -0.02106743 0.01716585 -1.2273 0.2200096 \n",
"flat_type4 ROOM 0.10929580 0.01834176 5.9589 3.540e-09 ***\n",
"flat_type5 ROOM 0.23552280 0.03818663 6.1677 1.012e-09 ***\n",
"flat_typeEXECUTIVE 0.37931707 0.06231964 6.0866 1.653e-09 ***\n",
"flat_typeMULTI-GENERATION 0.40599603 0.06366260 6.3773 2.774e-10 ***\n",
"block202 0.01131109 0.01470723 0.7691 0.4420293 \n",
"block203 0.04691115 0.01734699 2.7043 0.0069640 ** \n",
"block204 -0.00616653 0.01275049 -0.4836 0.6287562 \n",
"block208 -0.00207045 0.02367604 -0.0874 0.9303325 \n",
"block302 -0.06645902 0.01754927 -3.7870 0.0001618 ***\n",
"block303 -0.07302902 0.01782439 -4.0971 4.529e-05 ***\n",
"block304 -0.07974069 0.01901220 -4.1942 2.987e-05 ***\n",
"block305 -0.05840350 0.02865794 -2.0380 0.0418231 * \n",
"block306 -0.04658382 0.01684899 -2.7648 0.0058031 ** \n",
"block320 -0.10273432 0.02706590 -3.7957 0.0001563 ***\n",
"block321 -0.11500767 0.01925390 -5.9732 3.252e-09 ***\n",
"block322 -0.10457491 0.02755237 -3.7955 0.0001564 ***\n",
"block323 -0.12322435 0.02264561 -5.4414 6.680e-08 ***\n",
"block324 -0.19433079 0.02861923 -6.7902 1.939e-11 ***\n",
"block325 -0.19488626 0.02932148 -6.6465 4.976e-11 ***\n",
"block326 -0.20153439 0.03256953 -6.1878 8.955e-10 ***\n",
"block327 -0.15262200 0.02157357 -7.0745 2.854e-12 ***\n",
"block345 -0.17830068 0.02032045 -8.7744 < 2.2e-16 ***\n",
"block346 -0.17046745 0.01871509 -9.1086 < 2.2e-16 ***\n",
"block349 -0.17794145 0.02882994 -6.1721 9.855e-10 ***\n",
"block350 -0.17252119 0.01809450 -9.5345 < 2.2e-16 ***\n",
"block350A -0.32794480 0.02885994 -11.3633 < 2.2e-16 ***\n",
"block351 -0.17384257 0.05754334 -3.0211 0.0025843 ** \n",
"block352 -0.20378853 0.04048318 -5.0339 5.718e-07 ***\n",
"block353 -0.17745047 0.02613710 -6.7892 1.952e-11 ***\n",
"block354 -0.15707207 0.02574744 -6.1005 1.521e-09 ***\n",
"block355 -0.22071637 0.04706616 -4.6895 3.127e-06 ***\n",
"block356 -0.17699041 0.02859258 -6.1901 8.832e-10 ***\n",
"block415 -0.06964776 0.03539266 -1.9679 0.0493662 * \n",
"block416 -0.07535196 0.03039972 -2.4787 0.0133536 * \n",
"block602 -0.14257028 0.03748052 -3.8039 0.0001513 ***\n",
"block603 -0.17937661 0.03628943 -4.9429 9.049e-07 ***\n",
"block604 -0.06075680 0.02468901 -2.4609 0.0140311 * \n",
"block605 -0.19736678 0.03601031 -5.4808 5.385e-08 ***\n",
"block607 -0.07269468 0.03125248 -2.3260 0.0202196 * \n",
"block608 -0.02363668 0.04107283 -0.5755 0.5650975 \n",
"block609 -0.05128354 0.01892425 -2.7099 0.0068472 ** \n",
"block610 -0.06591294 0.02151357 -3.0638 0.0022454 ** \n",
"block611 -0.11242123 0.03470391 -3.2394 0.0012380 ** \n",
"block612 -0.04717143 0.02228894 -2.1164 0.0345660 * \n",
"block613 -0.03717483 0.01868012 -1.9901 0.0468605 * \n",
"block614 -0.11697719 0.02783164 -4.2030 2.875e-05 ***\n",
"block615 -0.00761401 0.01927646 -0.3950 0.6929363 \n",
"block616 0.00745057 0.02966921 0.2511 0.8017731 \n",
"block617 -0.01382726 0.01820948 -0.7593 0.4478298 \n",
"block618 0.03913238 0.03277865 1.1938 0.2328307 \n",
"block619 -0.01660675 0.01603335 -1.0358 0.3005684 \n",
"block620 0.01027000 0.01672041 0.6142 0.5392130 \n",
"block621 -0.01934420 0.01995829 -0.9692 0.3326692 \n",
"block622 0.01898694 0.01741320 1.0904 0.2758158 \n",
"block624 -0.02612062 0.02416487 -1.0809 0.2799929 \n",
"block625 -0.08820802 0.06650615 -1.3263 0.1850451 \n",
"block626 -0.00808326 0.01943208 -0.4160 0.6775194 \n",
"block627 0.00685917 0.01772527 0.3870 0.6988615 \n",
"block628 -0.03543630 0.02361950 -1.5003 0.1338596 \n",
"block629 -0.01882123 0.01853474 -1.0155 0.3101390 \n",
"block630 -0.02061869 0.02337527 -0.8821 0.3779541 \n",
"block631 0.03452821 0.04122478 0.8376 0.4024825 \n",
"block632 -0.07849057 0.02133876 -3.6783 0.0002476 ***\n",
"block633 -0.10622796 0.03036968 -3.4978 0.0004901 ***\n",
"block633A 0.10562176 0.03374424 3.1301 0.0017994 ** \n",
"block634 -0.07086581 0.01815212 -3.9040 0.0001011 ***\n",
"block635 -0.03597591 0.01672129 -2.1515 0.0316806 * \n",
"block636 -0.08215692 0.02541053 -3.2332 0.0012651 ** \n",
"block636A 0.04939331 0.03164208 1.5610 0.1188468 \n",
"block637 -0.07823798 0.02906945 -2.6914 0.0072362 ** \n",
"block637A 0.02698772 0.03484180 0.7746 0.4387757 \n",
"block638 -0.07534389 0.01929663 -3.9045 0.0001009 ***\n",
"block639 -0.18718609 0.03579903 -5.2288 2.086e-07 ***\n",
"block640 -0.09491684 0.02650376 -3.5813 0.0003588 ***\n",
"block641 -0.05819053 0.02901772 -2.0053 0.0452010 * \n",
"block642 -0.17231336 0.03919650 -4.3961 1.222e-05 ***\n",
"block643 -0.24301138 0.04381734 -5.5460 3.760e-08 ***\n",
"block644 -0.17800465 0.03745365 -4.7527 2.308e-06 ***\n",
"block645 -0.06491919 0.01735233 -3.7412 0.0001938 ***\n",
"block645A -0.11150229 0.01744955 -6.3900 2.562e-10 ***\n",
"block646 -0.16221688 0.03619478 -4.4818 8.277e-06 ***\n",
"block647 -0.17975628 0.03536175 -5.0834 4.441e-07 ***\n",
"block651 -0.17128014 0.03840254 -4.4601 9.140e-06 ***\n",
"block652 -0.06338432 0.02987423 -2.1217 0.0341132 * \n",
"block653 -0.18301670 0.03588324 -5.1003 4.070e-07 ***\n",
"block654 -0.13597666 0.02543791 -5.3454 1.123e-07 ***\n",
"block655 -0.18020679 0.03672949 -4.9063 1.086e-06 ***\n",
"block657 -0.18092592 0.03689379 -4.9040 1.099e-06 ***\n",
"block658 -0.18972574 0.03918477 -4.8418 1.494e-06 ***\n",
"block659 -0.13484419 0.03547844 -3.8007 0.0001532 ***\n",
"block660 -0.16861637 0.03628587 -4.6469 3.830e-06 ***\n",
"block661 -0.06785387 0.02026098 -3.3490 0.0008420 ***\n",
"block662 -0.07986780 0.01732078 -4.6111 4.536e-06 ***\n",
"block663 -0.07319728 0.02184506 -3.3507 0.0008367 ***\n",
"block663A 0.08067414 0.03577741 2.2549 0.0243605 * \n",
"block664 0.06677776 0.03912453 1.7068 0.0881763 . \n",
"block664A 0.03882486 0.03425306 1.1335 0.2572939 \n",
"block666 -0.08585856 0.03767058 -2.2792 0.0228700 * \n",
"block666A -0.12296862 0.05582055 -2.2029 0.0278322 * \n",
"block744 0.02985042 0.03093888 0.9648 0.3348737 \n",
"block745 0.05587746 0.01864727 2.9965 0.0027994 ** \n",
"block746 0.04223118 0.02395454 1.7630 0.0782172 . \n",
"block747 -0.03852531 0.01929121 -1.9970 0.0460974 * \n",
"block748 -0.00047458 0.02179437 -0.0218 0.9826316 \n",
"block749 0.06352449 0.03644655 1.7429 0.0816564 . \n",
"block750 0.03005821 0.03175291 0.9466 0.3440618 \n",
"block751 0.04716085 0.02868097 1.6443 0.1004301 \n",
"block752 -0.02243348 0.02396017 -0.9363 0.3493589 \n",
"block753 0.02962110 0.01594062 1.8582 0.0634385 . \n",
"block754 -0.01840757 0.02458743 -0.7487 0.4542435 \n",
"block755 -0.04432227 0.02804646 -1.5803 0.1143576 \n",
"block756 -0.00627516 0.02439469 -0.2572 0.7970518 \n",
"block757 -0.02708259 0.02168745 -1.2488 0.2120485 \n",
"block758 -0.04756038 0.02039466 -2.3320 0.0199026 * \n",
"block759 -0.04644259 0.02554169 -1.8183 0.0693230 . \n",
"block760 -0.01275063 0.02033008 -0.6272 0.5306872 \n",
"block761 -0.08784244 0.03362932 -2.6121 0.0091371 ** \n",
"block762 -0.04987302 0.02669218 -1.8685 0.0619978 . \n",
"block763 -0.05816457 0.02149828 -2.7055 0.0069377 ** \n",
"block764 -0.04903143 0.02768646 -1.7710 0.0768796 . \n",
"block765 -0.02557158 0.02662289 -0.9605 0.3370351 \n",
"block766 -0.03801116 0.02422053 -1.5694 0.1168831 \n",
"block767 -0.05634692 0.02286803 -2.4640 0.0139104 * \n",
"block768 -0.06411263 0.02436494 -2.6313 0.0086384 ** \n",
"block769 -0.08590168 0.03864985 -2.2226 0.0264732 * \n",
"block770 -0.04538983 0.02279190 -1.9915 0.0467046 * \n",
"block771 -0.07843603 0.02497761 -3.1403 0.0017386 ** \n",
"block772 -0.05610387 0.02489708 -2.2534 0.0244525 * \n",
"block773 -0.08862262 0.01854545 -4.7787 2.035e-06 ***\n",
"block775 -0.02372486 0.02158289 -1.0992 0.2719320 \n",
"block776 -0.03200243 0.02258842 -1.4168 0.1568705 \n",
"block777 -0.04074481 0.03995434 -1.0198 0.3080828 \n",
"block778 -0.02882953 0.02464271 -1.1699 0.2423256 \n",
"block779 -0.01098487 0.01482850 -0.7408 0.4589956 \n",
"block780 -0.11497767 0.05067667 -2.2688 0.0234945 * \n",
"block781 -0.00520384 0.02071809 -0.2512 0.8017326 \n",
"block782 -0.03190086 0.03383209 -0.9429 0.3459560 \n",
"block783 -0.02518088 0.01647312 -1.5286 0.1266856 \n",
"block784 -0.03695549 0.02076389 -1.7798 0.0754195 . \n",
"block785 -0.03442879 0.02308323 -1.4915 0.1361507 \n",
"block786 0.00067939 0.01973433 0.0344 0.9725438 \n",
"block787 -0.00784673 0.02136699 -0.3672 0.7135222 \n",
"block788 -0.03980404 0.01409869 -2.8232 0.0048504 ** \n",
"block789 -0.08130681 0.04894780 -1.6611 0.0970151 . \n",
"block790 0.01251385 0.01837516 0.6810 0.4960201 \n",
"block791 -0.04520699 0.03769235 -1.1994 0.2306752 \n",
"block792 -0.07932322 0.02483850 -3.1936 0.0014502 ** \n",
"block796 0.01743361 0.02110748 0.8259 0.4090369 \n",
"block796A -0.05227696 0.01493406 -3.5005 0.0004853 ***\n",
"block797 0.03409431 0.03608641 0.9448 0.3449960 \n",
"block855 -0.02999969 0.02376062 -1.2626 0.2070407 \n",
"block858 -0.00636554 0.01867535 -0.3409 0.7332878 \n",
"block859 -0.00478995 0.01880596 -0.2547 0.7990055 \n",
"block860 -0.02742735 0.01894635 -1.4476 0.1480401 \n",
"block861 -0.02784012 0.02429985 -1.1457 0.2522030 \n",
"block862 -0.02124194 0.01825049 -1.1639 0.2447438 \n",
"block863 -0.00428550 0.01933151 -0.2217 0.8246054 \n",
"block926 -0.12240773 0.01342745 -9.1162 < 2.2e-16 ***\n",
"block927 0.01349266 0.01590181 0.8485 0.3963677 \n",
"block928 0.03514627 0.04373527 0.8036 0.4218151 \n",
"block930 0.00105627 0.01962897 0.0538 0.9570963 \n",
"block932 0.02388295 0.01554729 1.5361 0.1248250 \n",
"storey_range04 TO 06 0.03058611 0.00377033 8.1123 1.479e-15 ***\n",
"storey_range07 TO 09 0.04818417 0.00408965 11.7820 < 2.2e-16 ***\n",
"storey_range10 TO 12 0.06175330 0.00396446 15.5767 < 2.2e-16 ***\n",
"storey_range13 TO 15 0.04871131 0.01169424 4.1654 3.382e-05 ***\n",
"floor_area_sqm 0.00450734 0.00058105 7.7572 2.174e-14 ***\n",
"flat_modelImproved -0.02014524 0.02451429 -0.8218 0.4114047 \n",
"flat_modelMaisonette -0.01977003 0.01464550 -1.3499 0.1773585 \n",
"flat_modelModel A 0.05182205 0.01266428 4.0920 4.629e-05 ***\n",
"flat_modelNew Generation 0.04205016 0.01682451 2.4993 0.0126053 * \n",
"---\n",
"Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fit3 <- lm(data = data3, ln_resale_price ~ Treatment + Period2 + Treatment_Period2 + Period3 + Treatment_Period3 + Age + month + flat_type + block + storey_range + floor_area_sqm + flat_model )\n",
"## Robust SE\n",
"coeftest(fit3, vcov = vcovHC(fit3, \"HC1\")) "
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"0.969406694789345"
],
"text/latex": [
"0.969406694789345"
],
"text/markdown": [
"0.969406694789345"
],
"text/plain": [
"[1] 0.9694067"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"summary(fit3)$r.squared "
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 150, 164, 168, 355, 648, 699, 813, 818, 988, 1188\"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 150, 164, 168, 355, 648, 699, 813, 818, 988, 1188\"Warning message in sqrt(crit * p * (1 - hh)/hh):\n",
"\"NaNs produced\"Warning message in sqrt(crit * p * (1 - hh)/hh):\n",
"\"NaNs produced\""
]
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAMAAADKOT/pAAAAOVBMVEUAAABNTU1oaGh8fHx/\nf3+MjIyampqnp6eysrK9vb2+vr7Hx8fQ0NDZ2dnh4eHp6enw8PD/AAD///8iIoPFAAAACXBI\nWXMAABJ0AAASdAHeZh94AAAgAElEQVR4nO2di4Lcpg6GSdI0zWmaC+//sGdnbHQBgQELG2b0\nt7vrsbkZ9CGBnV3nTSbTabm7G2AyvYIMJJNJQQaSyaQgA8lkUpCBZDIpyEAymRRkIJlMCjKQ\nTCYFGUgmk4IMJJNJQQaSyaQgA8lkUpCBZDIpyEAymRRkIJlMCjKQTCYFGUgmk4IMJJNJQQaS\nyaQgA8lkUpCBZDIpyEAymRRkIJlMCjKQTCYFGUgmk4IMJJNJQQaSyaQgA8lkUpCBZDIpyEAy\nmRRkIJlMCjKQTCYFGUgmk4IMJJNJQQaSyaQgA8lkUpCBZDIpyEAymRRkIJlMCjKQTCYFGUgm\nk4IMJJNJQQaSyaQgA8lkUpCBZDIpyEAymRRkIJlMCjKQTCYFGUgmk4IMJJNJQQaSyaQgA8lk\nUpCBZDIpyEAymRRkIJlMCjKQTCYFGUgmk4KmBMlt+vJfIYV0mE1TX+cj0zPjj+fZHxpFv52c\n+xEOmnOSD7+/fXbu87ffUZrM6Zs1pUWAUWdJGg7S52fmz5kiDKSinPsUDppz4vG/YUS+sySZ\n03drSovYu/Ob+1KfuOFCTertY64IA6moDyv/Zz9ozgmHH8B8++X9r28cmczp2zWlRYTurBoH\nA2k6fURe7td20JwzHP3+FOLDH85hGJc5fb+mtIgIpO+f3adt9vnx5WPl9AOufPvkvnlY1exr\nm68fgcU3/BhyPPTbfX7+/PwxBOyCZ2P+cbgFeXuoR1uAdZqycu6n+7odPL5/9N7n79vH358/\nLnyc/cd9+ucRcrjnSEVj9tT37dJD33b/Vjh9v6a0CB7afd12HvyjF0Nw/Ezx5fHhKwfpny3J\nt/3jdx5Of3lOlL8+Cvsex9klkLAFpE5TVh/d8/dzfYvD9Oy9Z889pqHnKP34so9UNGabvrqf\n4fA/EuJnTt+vKS0CFv6PTvvhvvz2v788PPqnx4l/H27l0eH/uk8//c9PHCTn/n3G0ftHzPHU\nv89J7J+PsqILWCeUE0pkLSB1mrL66J7N+dNh+vfx8ctvv//4vn//lIwZlOGF48zp+zVTW0Bh\n+/s5+Xx9hsK/H7ECbKs++/Drc9L7EZs9HG0X+Ab2c3g/CxdKIJEWkDpNWW2xwPcwTI+e/vFw\nH/s2rNu91S8vjhn5mB4bSC169tDnTz/2D2DiHzH1158/Q4q9H2Oz//Xjny8wKJhj098fo/fr\nEUTEF+LBoiXGj5gmG8L5tI3fx/QjDlPUt4/vbMxIGemxgdSiZw/958LOD/qKfz6CKvfpVwmk\nL8yxYI5N/33Edt+eE2J0wUBS1D5+f9eCFI3ZU2Qx9PO5QbGliE7PoyktIkRUZOcn6Me3z2GN\nJIL0t/v8/ccvOih7jl2fPj/+Fy4UQYpTGUhFhfH7WQdSOmYetud+/npEDz8ApOj0PJrSIrbu\n/LltNnxNVzM0+P4PRgiP4kEhdv/NfSe7pnLMkK6RoAWkTlNWe7zmPtM10tcsSOKY7Q+MPmZT\nuiWUO32/prSIvTs3l/Tc9fmYib4+wu5/ya7dD9xB+/yxsv39ZRuU//xPjLcxx66P8XpuHSQX\nEpC2pfAv3oIftmtXob17/nn6ELZrRy5TkNiY7fqxvcLwDwvAs6dv15QWsXfn780lbRH0o9v2\n16z+21M8H+/8vTn88HTnm2NpMEfQ5+3pQ3IhAunz832x7TtpAanTlFXonk9kBfTFZ0GKxizo\nB6xN2btAmdN3a0qLCN35bVslff+w57+f08/zdQR40vfYMPgGewrb0vYj4P5IgYEE5Aj6d4/T\n4gsRSP99fiC0factIHWacgrdsz8m+P4J3mwgl8n3aMyC9te8P0aK7SpkTt8sswjT9PohvwuU\nOX2PDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoykEwmBemD5EyVUu96GyN11Xep/iCp\nl/iiuhOk+6peSwbSAjKQ5peBtIAMpPllIC0gA2l+GUgLyECaXwbSAjKQ5peBtIAMpPllIC0g\nA2l+GUgLyECaXwbSAhrdUYXybYwqZSAtIANpfhlIC2hUR1W8KmZjVCkDaQEN6yiXKb/nXcw3\nl4G0gMZ11P6bru6o+sVkIC2gkR31/AWm91T9UjKQFtDYjnIGkoIMpAU0uKNKCyEbo0oZSAvI\nHsjOLwNpARlI88tAWkAG0vx6Q5DWezhiIM0paknvB5K7reZuGUhTilnS24Hk7qu6WwbSjOKW\nZCBNqr6wQb8Z91U9u94BpMIyaBGQOsOGIe0wiXoDkIrLoCXWSL2DNKghpqA4UHjpNdKB01lh\n185AmlN8Fn71XbtForeSDKTZ5PDtXqlP/vqrviSlFo0skZa7tgnYGmkubeNRsKxX9EjKy6B7\nQkHbtZtHYSycDNLTG70USGB8mrY/weaEgXSrnId/AJk3hlcCaYjJzxAnGkh3CqM6l07RsDZ6\nIZDGmLyB9N7ayRH/ITHdYBgG0vW/oeYCkG7aOTeQbhOGdenQ/xUlrC+ytQnKJVYVNyS2c8nh\npTKQ7lLWGyXb3QNDu8MMU6+RcAbCLQzy/VL1VPnsjPMO1EDydf04co10lGPcrt35hBKUK4Hk\nvM7E8t4gOfHXlYkPX19os6G6WhdZmICVyIyB9GZymU2GTNr6UpU1epBkv+P444AEqz2Rz5xd\nZI1kIJ3Vvk0WGVH2VaAXBkm2I0f+f350Tph1Ms5nnV07A+mc9u1mbhml9+leF6QcCwwkF/z3\nAOejR13XZoPoaS+penXtDDkH0cum4nupV4DEc171C9rzIJH+cXsQLKySzjZPMQ680ZrfDyS0\nzu1rP330dvfbeSS+L+x8PO0kyTuB6t6ZyG593KK3A8kxf1TN0QuDJLuE2BXu68lsU7r9Si9I\n+a2PW/RuIBGEXIj4q/6t0QuDlJvbk0jTs7knSR/lqHRRnSCJ2VpLqXg9q609byMXqSHngJRR\no/RKbKo7X2Nspi6/ME8zVLuoPl+mApKi3gkkCOqI3Vb/y9dxILnk4GyJbXXXcbF9zv5DkyRD\ng6PpcgcG0m0iewz70NX/8/GBICXGd7rE4yqzL8WFKzkzhf/FNsYOqbyqOimtNZKFdo0iFO1n\nWjh6IZDIc9V4AwGNM2OmeZBiv5IvRks6u3ZOqZFvC1ITRX41kErbawSGKFJj3ii3AVH8u3VJ\naixQVcWlXVtJ0BV1FV4VNUyqZIehlaO11kjRHMudjoPve8J8pCcVi2UVaXVYrr6NlZd2XUWV\ns253XqriPUDiHDX8ai1SxICUIYP2rl1kv5HXYSDtDwFyK6M4XmNPlvIt49bpUubOrUmyfI4C\nyfG0hSSvLY3HBQNBUi+RG1ryyYXZNVr2pJvbyWeHD5Jia6auCtyc81h6odxGaYJUtUjinUcv\nnDeshXTaGz0LGZByVIklkCL/EN7v2AHhBpGwQr6SYsMSdC8upJJ+7+bZiE8VJMlhZsvNLxDf\nACTE6K/Ts6BuyhElguXyyI6ukhx9PwH3YNIJF8M/mhSLJOk3/xMckINTtJy43Ia7im8yk32Y\nNZP54ijFi4pGdWc4WgUkMGVHz8V7bdQQgyNyPky40S4B80HE4YRXfhGo/SUicgC7Diz4OQ2S\n4q5dbYVHVbw0SJyic2HsGiDJJloyZPquh0MKIobAzzgHnJBiXQIScXDxe/asXF11lKm1xnlh\nkChG57zRs7QBKUfVnYDkuanEIO3GThii0VxI7AhNGL0xDtERecKR8I9reXippv4CTzfldUEi\nEJ31Rs/iBqQcVbfgkTzzKOAzgqtwHs3dhQAuKtKRPuUgkb4GeHDTLiSKmjXCK50ozzySKBfr\nfIkDUg4oUTZPGm2R6A1+ELLARaFPggI8rJFw02HP4QKUDnPkQaKOTlMGkrIib6QRQywCkhfv\nlkZdIdILC6HgPOA7uBZHL+FVQhOgRf3Z3gBCko85gnsykCZW4o1U7nEZkKT0gQfiZMDo0ZlA\nqAdnccWDC6qQmPLG/BJZJlEycRwcNMlAmlcO7WDzRlrlDkipXGIIuESSiCmDfyJn0aPgb2fY\nWdtBcow7dFbovILTo6swaA4B3LGT8n30qSOf1mT7YiChF/pLzxltJQ9IqVtiCKOEDGjv4QPd\nI0CvEm3DUUL20hlQIWxj8htODqM5kpq4oWR0nIsIax++G635tUCKOdIsekBK1RK5t6EX2NYC\ndSXBwnFxQ0+H756B5NKcoXTCC+LpYXkFQV8m/MQvvInGvjSQVAQQ/YWTo17hA1KqlgirGM9v\nnL1FRxmS3EmOJhIBMaQwDKRERoslSl7W14A3CiusTJB6vqNoenqv5/QyICUWoV3+gJSqJYYl\n/H7zoQtIvObZlC9wIwmBiU6GJVkoDj7zTKyywr3Q1vLmC2lzw9vT9T3AKlU9oWCw/tJeG0EN\nA1LqlsgWIbjQ8BiB0SAL/Yxn39gaKOaJpmFhJGIS9jHC/wzcwr3w9ZHLrfZoot6OErOYR/Kp\nNxpxU/ODBGsUFhcxOnw4EW0klEQcTpoemA2U4F4fBQ/WaSFx5FSw4VBWvIce94bsquo6Sspi\nIOGoqj18FasZkFK5RGrK+wm0fO+paTMyChBlP1CMHInGqAcCZgmA0Ex6Vwg8+cjDO9IFBtII\nIUUwuoMqGpCyr8TsPbL5fDsmkRz6Jnm9k/FNsI3AzzG3RGw+9Vi4kQexJnM3Ahn8DuPLuiDZ\nGukhHLERG3W8qgEpu0o8WCHgqt9jtCWZP3EWkshaimUMzMVokfUXVBzohTTYfhrcAYOlhU/k\nktTWSNDok1oZpISigRxNAxIxqzD902u4c0aW/3QrIUanyFbiowo+K2wQOAoh9317I/FafEt5\nN8PGNvvhRmteFyQcoOHe6FndgJQ9JXKrizbCgkmjTbvoXI4GCZfIF4lZIUWI1yC45JWTIQrt\nhgiUbitkbh/D1egS7wADqVUI0ei1EdQ4IGVPiWBwIZDj1x35j6yRpI2CXgk5PSAj1RR4Jz6R\nEBBKLPSdS26T3W282rpFS4IkjOT4Ogek7CrRka8UJPQQkSvo5kYqIc8SjR89ucYclUOE+O3k\n+i5z0ZH/S9lLHatlQguCBLc+5FWgbK0DUvaV6Ag9wlQNVg3mB/ZdBUlZYkFR+EcWYmCrPP4L\nmxhhmcRpynWAPkiKWg0kpAjH6pqKB6QMGY7uJBPw+GSNxIDBeIsbu2c/BFaKWGUdkw8AhTvy\nHttAW7Q32ZG2h5iw2ANSZIfRXaGjLtFaIOGwXc3RQJCOzSAX8MS7dgBXAMiT68yg651QOZ2P\nDn1EIWxzxBkikA4HUk4Q7uWwB8drJZBSii5s/TCQnHh4VKJ07/s5DosHP9DHjrgcEj8ENKLE\nPt7786FJZCXlI+pruy7K0GMPHfXmillCZCQu90bP+gekjJPXg8RDHbBEWKDA0giWEBmM2jch\n8pEf3Wjg5z06xNBGTzAKKz0W9GX7C66mK6cOizhanrWUs4BgUC7b7k5aMCBlnLwaJG5CYalA\nNhYc4BRW9JGNVwEkJSpu3uGiDJdJ5KdnpzAwC6htd1M2a3LVQGqVMJzXt2FAyih9/RqJmRCx\nv902wRkFI96S9XDTk9DDiBEXGefbEwXCPIJU7Is0jYFUK+j727zRsxU9Kevi78O7OgQpMvPd\nRgEkqKU9kEshwZKjWuMj2FDDj/Q6lBTFePUgpQAYSFnB8NyxwcAa0pFyzCC5MIPDVRonoT06\njJ889RHt8AgnYnbFfOALPdnySDL66DjcY9wJdJcPTkVd09O5B7FkbTFnCxgp0uN3OqOtLR0p\nh4BEVxmwEIo2wRxdEXnJgRQJKKaQNhPiY3BbWxu9T9DDDOg9g9f0ITSN+yDqz7Rrb7TmmUGC\nzr7bGz0b05FyBEhh9bN9ANsNmwkeNhxYzJfEf8796ZSIEHN44A6J52SI0SBvuxQ8JxzGvYae\nCKxAiAGXsI+rhcN15ZtA+eZ0pGwFKQnhdv3vf97jl9u/4LPbvrzbz5NjR67/+cO/wvnWr7ic\n0he0KXxFbYXj8BXdJ81H+yC5Dl/t2ueZk5oVJIDo9pguNKgnpdOPv2Gf2+OcDC4o3oDOupIW\nicFd1VrLlxwa7ilC7Acuid+1A0vPOCmxoxo6Nw0ku4qZT9KY3K0ukEbU7XDkESSyk5aYbbqE\nOSYg6vvalNF5uqDb25oNFtmuHZt+4onD8wvZjqrvW/V17ByCwZjGGz00DUi4wQDLeMEs/QE+\nPnehRqVszNGQtRtZ1OGgPtNk2OI3D/t5SU/kO6q6bytAIo3OlzOVhKGZQgNBah6kZ1pqdmBn\nJPATtgIOAekDK95pSAoV9uCRtxCYso0Ega0hXV8LkksOFKoeKej+Yb/osVfNIHFjqim5ZpAi\nw3KwC74vjRhIHpZNh7gIHqoU0BWXST756OljJFjUYQJPlvtxdwWPVMPWqDWSEw9PVz1MoWdn\n2O6ONcwj9QxSYmxgsNQvke0HFujlnujkwamSF47gsw9sgy9CFmEdFe41JckJcRzMKscdWBTW\nnU+Sq4J16xwiTZppaQSaCaTY2MAwyc6X95GVxgTJ3JRcTbTsKgSC3kUleQQJT4TWeQ+oSVtx\nuCg8tIlRFrOOR0KIZvRGD3WBVHMr7YOUGBvbEidVBlP2MRvJiQSfo406UlHynaeF8BNCzr19\npBWeJBF9D26u1PZlreqyLLJGkkZrNvWAxGbZ4/S1g+TiuZkGRw6wAqMs+Y4sO5L3isth0Vk2\nsvPokKR9CXIzsFwRNug8zhfsPEs6DKQldu2gx6fa7o51AqRDkhoHKTUoWMV7skMWLeeZhZfI\n8kcJsrm4W0L6CObhZ2iowxsK5GO/RV0ggBSdGAfSZeX0N0AYkxnVCVKNS2quO1kvgMHi7kJi\n2MGKc4wkLsgLF5lX8Ri6ieTR9VDwMmR1he4EE/lwUnJJEP/xk453+NnO7dTNVgudPrU3emgq\nkAIRPEEwTRLbcesn/V3ncY5TAQSFrIR82ghoOAvvxO2GcNPxhdhH9XgkJbu7027hHnCDYVaM\n+kCqXCQ11+3I/yQBsWpinaRnwTnhD2HVk0XGh++eY7lVHpdDlz4smvOhHNJSafqROiIyEPBy\nmY66UPdVjb0+xdvdR+oCCZyEct1kRwFT4K4CX6tESxQBHxEin5z2sOAJgSMsyDyiRrIhe2zx\nBqskKI3fY0OPYUlyR12nu6pOKJobo16QRtXtkmkcLXqfojPLFs5RMSQTrgCrJK13WJmwKgv4\n0ZPQUOlWmnrGhWIyHXWZ7qkax2IJb/TQXCCJARDGWOFnxIAASup3yisjHxHqaQGsEM+4cQQn\nsmbyYROhttNiUzm9RtLS9VUTiFbxRg/1gOSU7k/MnxYLMRKZ8R0JwejSCRbuqe0DESSI8zQB\nTeZp0TFz7PbBQbF418m3UuqJeJnk+OWbdHXVcW8vgtEpj6S/RiqkA1NL7Z7tQZTcDvFdCFII\nGJnzgTVQlBfRdbAjAMRF2zGNHJW6421Awu5eyhs9dCa00/ZI2V4js79HsyU2TpwEOhO0/dSr\ncK68B6bICgmdXJw1BG4kgkOQoBUhTW1HvDtIhCLs7WU0EUjC8ijJwQM15jg8ORHFbtSXwPiQ\nwQL+OIEUz93tcbB4fOgDWmSBVGcLZJuwpqOOy6Pgn9N1pixwdFndCpoHpKNpmaVzu/OInBGY\nvU9BiklyTNzDwYEnTEUg+RBQwmKN3QU0pOKO4sCw3FF1qu3OqmIuUELRUhhNC1KhH/dAbP+e\nLGO23B4sORLiBHBEayOHpaDX49uAvBW4PqN3QZsZ3YCLb5yCKN14R0e76GevrjFnHJ8lvdFD\nPSBp3WseJDBVoRJqwmiC0Ra0p4ODax3yH7g2H3wZi9vCNYdBGvV4uK5iXjBqP6yj0vazz/B/\nuIliR1VpJZAAomUeGgk645GU60YLC9/liIdYKCUFdwGIk/EED8xB6or54KurgAl6LHCZHuAl\nXpDfBWOL37RjJ8j/4i2/NEgu1vAah2gikHAyDoaYS4XRVfgBMZfDVIGI1Jl6sjdAvRChhkaN\nSB8ZZozvIDyM7oIkSm6ag4ROkjGZ7agayZ3XWcxARd5odHXD1AyS4tyRzV8CiWzTkdQkxEuS\n0w0xDMVCRkoS3Fd0AmplAICfixhm1WegiGI7LIjceJynUTp2Odiyd4rWdkZPdXmk4bNdmKUh\nFXFW9Np+zqGVszIZMlgwWn+Ez44Q+h7IvaOSaXFYRtXdNVoMtkS6cd4dN2lk1aHjX4GjLpAu\niL/Rjp2nByJIHh0P54jkitIRPxY+B1bCFsLWjD03ACgNd6ZN+VujHlG48aSc1wQpomhtjiYC\nKZ6nySF1TcRoo5k8NnLRWhmfsL0HH8i6iFTmMaJMmh21Sb6lQqskkuQ8jRKRbC/ldAm5gl/I\nGz00DUiC94kSQkDmqU/BTW8WuGEuNkhk+227SBOANwrDHF+U97M9ZuF7Dhnq+E3WdGJPR7dE\nm8pV1xT7hGjVh6+SekBqMIHquqFIqWxmfI6ZaDiknsYJuUhJ4Fq8p2HcVpqjhdKMJK6T4Ihi\nUV+iLk54qI6eTu+gT2NMnC9OXwCjTpAG7AgVQYoDMuk7o4vnIo6FPG3yOJ5YHSuU7WOH1xvS\nxmH5zFPSwFC6F0h03JOvBtKreaOH+kDSr7sMEg+Ust/pKj45gbZODDhEcEkzeBtC/nRDgycp\ngMSCPnJUY+0vBtLruSM/D0g46uI8vV9NHQ45I4ZL2xVAJnneREIychSv1B0kFUaeRnXMfimi\nOaOW5w0xUZucp7fZrQGj/nre6KFpQOK7dpHdMX/lWA4GoGCwAcEAEToldh2/XFwNVECqSSuI\nfMBeFOFItpthIM36QJZsd78SR+0ghcn9qB8q+iufPzavOECLKqJpkgQQvDlggSURF1eRR0Lv\nJ3KETYPGRO3IhnDjQNKRdtV/HZvFmhrnkY7T94B0VBp3V3gt3g0Qc0dM0pJycZ3ctNQvEp92\nkDTXuHukWDUN6V4No6Gh3WGGepCqzY0bP7nm4O0feQhZzBe5p2LVEkjCOcQ4KWDIrp2W9Krm\nWwyvxtHQNdKJiVaY0is8HNkOC8EcFHc0euxlPVL9oTMUQJNAitFuUUc2F/3slZbBc2/0ehz1\ngSQvVlTrPlV88s6O0GBpLYWNYtsEzU3NeaneW+oBic0DhWQH6bQs/sUx6gPJ+XN20V53c8Fk\nQcTfIKJ1H/uR7NnDBggF9dtPl0fKbDImBZfTaYxR7I1ekaMJQdJxdc6zF33i5op4yPfUdae6\n1tIZ2h22vGIVePo2/vIvvzx6ajqQNAre10SeABMHdmID5EG+f+x710hO3t5Iyi2s3s7e+btw\ndAlILYPUFUkJxYgb2XitwSPpoH1KvSDhUumg3Dxwp278r60JLw/RQz0gZd/dVKi7CaTjkRE8\nElk+8TIyVZ9G+7z99INUsUbaDkaA9E4c9YE0sG402zpKKtOwMM9va3FHrns/DCSFOWecAbrk\nYPt02vb/+isp6ZUxugOkg5510ddRgw7SuHjXjudKA0BtkBqyZ23tRhM8OwU8+//1MeoFyR0t\nY/dE5R6Ur0S7BEcNOkwSlZYHacwaqR6kfD2ttTsyXTVmPVv1Q8EbvY878r1rJAiXatJn05UK\nUAEJV0hRBpek2H5mnKTwkmu1qkEqJBxshcdd2KC/8PCdOOoCqSrycuJhdd1VcVtdG+LmsmFt\ndjfDMrwGSBFH/k0wmhekKvs7GiIa0WXXH4McTHMNiiA1ugI1kP5in3B91FLGqpoWJJWXA84t\nb3IlDnIRemskzNOAcPu1WIyj9/JH866RlKQ+jC4UO6Dxmrt2LvpZk/ZM1X9xb7T/K8e38Ued\nINXtZ3bu2k2up9/Q93SHdXZmOdvKrvxh4N8Ho16Qrq57JoF1XNf8yUH6S1gbvc1uXZCB1KEF\nQNJq42EBaUj3lhwNB0lza3UarQDSRb9FKObIs7+Ic7r6ddQBEnTQpVurU2n+NdIlVf8Vn4AN\nhvdaHz3UDhIY0aVbq5PpWis5sUYaWXXCkYffL/NuGHWAFMKayo56TZAuNpMJQYq3u0NqjO2U\nGrCKekGq7aiXBOniyG5GkLLJq/4qwAuq2yNdWvdcunqv4cSu3ZCqZW+0JX9HZ/SUgdSuFUDS\n2jhry3+1q55IBlK7VgBpVNUFbxQC/lWH9ZwMpA4tsEYaUnUJIu+T32/7VmoHSe9527o9Pv+u\n3fGbju1VH3K0TTDrDusZvecrQostiPt27VT8ZiigGNJtKXd/tFTP6uktQVotku8H6fRtVucn\nvyD6LfWOIF2+WXBWnc+RNOaLR/5jb+QDuW/LkYG0gm4Gqb7C9+XIQFpBnQ9kNUCq8kahwpX6\nVFvvCNJyY97VVqfiIRoKeGd/9KYgrTbmszxHMuX1niAtJgNpfhlIC6i1o+yh+fUykBZQ52ZD\nZ86uqhcLlvVlIC2gzu3vzqw9Va+2faMvA2kBTQ/Scg8U9GUgLSADaX4ZSAto+jWSgTQSpMNf\n2+XSpCZJfQ9k6/fsCslsjVSpcSBtL1+VcjqWtLH4d9LovjkPkk2Fw0Ai3ugIJAsMDjSqayqe\nN9moVGo0SOHlyYMk7eW/k7rWSDUPZA9i786q31LDQfL5f3t8PUiLBiAndu2OkhVj776q31Nj\n10jbwTRrpFXXYuNA8uFfiCtW/Z4auWt3lPPqXbtlQ8iRIIkhw3v+QYlTeqfnSAZSJq15pPN6\ndZDonPpOIGnd5oK9dY9eHCS+KnqnNVJDaFZKs2J33aIrQLrvGUXsgxaN+Qc32kBS0Gt7pGWD\nOS4DaX69CUgQ5SxpGMMeyB4Xv2R/3aHrQbp0a5WsijaOojrXiPX6du2qV4TnQVqjG4dq5HOk\nI1yu3bXb7IrXucjuQz9Ip++umsQFunGornizQavEU3LsB/0wvwl0PkfSsO/j/GGqmr8bh2oY\nSE48PFPiORlI56uWVprOH7+w9w56M5CCIdCxn98COh/IjvBIfKVJ/yTS/N04VO8CUiDHMQtb\nxAC6muhU9oIItIQAACAASURBVAAkkGClGbzRwYuvb6E3WSM5BhJWvsZ2041tjHc56Q/ijZbo\nxqF69V07bMxWYwTSGpoYJPNGuwaCdEOJR5Xhynipse/cbOjMWqo6Bcm80ab3AukB0Ht4pDEg\nRaUussS8RKNBKuW6Y/tb3gefXM3L01G/RD/G07wR6L1A2qfQ1WbSEx5Jt2otP/eCei+QoudI\nq2iezQZTTm8D0spq7yi16cLGqFIG0gJqf/IQvqk/kDVl9Da7diur71m4w8Prqn5bGUgLyECa\nXwbSAuoCiT40va7qt5WBtIDuBGnl3c4rZSAtoNtBSp6/GVGxDKQF1LNrp8VRvAGotyH4WjKQ\nFlDHcySH389VLYGkA+lryUBaQHe+2RBAomgaSKkMpAV0O0jRW/MGUioDaQHdD5L3tkYqy0Ba\nQLeDZLt2hzKQFtDtINlzpEMZSAtoWEftvwNokt+rsbTeFKS1ptZxIIXCszWs1E236j1BWmyx\nPKqp8XPWC6t+Ob0lSKtt3xpI88tAWkAG0vx6XZCYhfA/mWAgkYJtjaSilwUJH8l7NBhH6FrI\nRMY1NfNLuy79Y3CvodEg3bW16sJMSydc/Dtja1nIndub91W9lsaB5MJvhb4pbOCvtCz917AM\npPk1DCQSSd2zkGUguaO1wNQa3OpS8Wt22A0aCtLBqv5Kj2Qg9RW/ZofdIANpARlI82vgGgkO\nDKSTMpDm18Bdu2DJE2w2LP6ntw2k+fWyz5FeSbZrN78MpAU0F0gv5OoVZSAtoClAcuxdkcwr\nI++rK0C6Z7PhhTQDSIBM+ZWRt5V5pAU0AUgkgHuhV0YUZSAtoIlBWvuVEUVdD5K9WdysiUHy\nBtKmkc+RjnB5+86v1QQgITIGkqgr3mzQKvFtNQNI+C9PDCRJw0By4uGZEt9XU4AUn7LnSEwG\n0gKaCySTJANpARlI88vWSAvIQJpftmu3gAyk+XXrA1lTpdS73sZIXfVdOnC4Gktva8q4oidJ\nfIuqW3hjwlvrVi6iNpeB1J/4FhlIvTKQZk18iwykXhlIsya+RQZSrwykWRPfIgOpVwbSrIlv\nkYHUK9u1mzXxLTKQemUgzZr4FhlIvTKQZk18iwykXhlIsya+RQZSr+YfW5NpARlIJpOCDCST\nSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoykEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQy\nKWgASHuR/Nfr5X7Znpg426xc0ZqJfX/igzuUTs+m6t+J2PDbE2vSDfhdjNUtbKk7X8j5IuIS\nHRSMhfNPB4l97s9p54sW0p9vx7jE2Tu8W7m76E9Yd6sNxdV23YhbOShFVewPYzs4KdclJobT\n+kXXJHZ+eOLsHd6tuJnlhLV2epysobjarqsusvqea+rTk4vspVhXLrHcV3LqfBCYTVxuxxEb\ncuJMY3KJJwXpKd0Yy9Uka+KypeuqvVx9kcNKKBV5AFImcb6vRDYOVjJx0Tlvl+TKj66QWP6c\nS9xmDddK30x1PdI9LbyiiHyRxxyJiWtAQvM8ZoOZcP3+wSFISVmlZvAtj2lBGvEHGO4DqTJY\nnHOz4TRIWTJaArBMO1qoays5l7bxDidQdcteBaSmIseVkC+ywsqExC6f+HQAVsMGCRobEueS\nSolLd3iT2N8CKjWNJCzfQXVCTKEOkn4MOLCAfJE1HAmJS3/iSSj62NybEif56kE69KIkymv7\nI1YXqzIgUixvDEgtHTwxSFUcyYmPjDJ1AwVzb0jMLzclPrjDtKwpMWowaNXZfghITcnmBamO\no9xtFEFKiy64r5bE0cZFc+J8m9MtkTlByt5ykrKl1LokyhFbNZZNdZ+urrVIjF4c+1SRuNAs\nMXVxI64pMV5uTnxwh3HJk4KUv+U0WX1wWpNMfbewoYWz7tqZTO8nA8lkUpCBZDIpyEAymRRk\nIJlMCjKQTCYFGUgmk4IMJJNJQQaSyaQgA8lkUpCBZDIpyEAymRRkIJlMCjKQTCYFGUgmk4IM\nJJNJQQaSyaQgA8lkUpCBZDIpyEAymRRkIJlMCjKQTCYFGUgmk4IMJJNJQQaSyaQgA8lkUpCB\nZDIpyEAymRS0Lkj4V4bgV/ULiXKZBzbsjeRgENp+BX7xbxOEgmsLmmMs52hFj6r+XouBNFyt\nf18onzL6GzlHRc71dz3maEWPDKQ5NAAkF30uJ59jLOdoRY/Y/EX+miT+6VKMOPjfMdqz4BX4\n20UT/z3KaRX60ZFe9PTAeTowJBCkCcU/jpWMkiM1QUFzDOG6hsMDAexRdhCD5PCnS/JWBRSm\nSMGAw3EyEq7Q09jlDrteBglS0eTS1z1DuK7dRH8TkHzFUxleolfTlOv2xZ1y/HvhAD/KI1UE\nST4QxvUmrWs8skcqg/Q8dAaSps6BFApxjg+WlJmmMpDUlAGJ7omnIBGKsPPp8mrd/rhLMSfJ\nAOwH+YcVfGrLgSROgAGk+4dwXcMpeSTv2fg+D2J/lZnF1u2QmyR6pPQMOy+PVBEk+cD5WYZw\nXbspgSQN3wFIySia6iSClOvfxCOJM9rmWrzk10og3TqE69qNDFJ0wBPt3whIyWbFwh1ykyJO\n0pFwPrmWXqdrpHhs8GJujTTBEK5rNxFIjj+uCKei5OHhgyPHmMXWSB2KQRKeI/GPyXMkOiiY\n1nn+3ImncljQHENohmMyKchAMpkUZCCZTAoykEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQy\nKchAMpkUZCCZTAoykEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoykEwm\nBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoykEwmBRlIJpOCDCSTSUEGksmk\nIAPJZFKQgWQyKchAMpkUZCCZTAoykEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQyKchAMpkU\nZCCZTAoykEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoykEwmBRlIJpOC\nDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoykEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQ\ngWQyKchAMpkUZCCZTAoykEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoy\nkEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTApaBaTf3z479+V79rqTbyRz\nWtKPxvRvJrfpy3+FFNJhNk1VnS2p79UiTf39aRvHT78zCU6D9Nm1pX83uaAsSQbSAvrbffnl\n/a8v7lsmwWmQVhq0O7T3zzf3pT5xwwWF1PdqkaY693RFv1tHyEDSUuifqn4ykGYV79Jvn54O\n6mNd8/Uj2vuGCb5/dp++5/J9XPz8PVfAM2ohxWwpnfv11X36Z8gtLaYIJOzpH18+Vk4/4MpH\n137z2JXP79EwQY6HfrvPz5+fP6ZKdsEno/eokCbHRnzMs5/dV1oRaYhgFgO0CEjf3N+/4MOX\nsFr6Z4vaNxA+vn3d1sMkHxmKL3hRKICChCk/Uj0OjaQ4tMOe/r514Xfad185SNEwYY6nvrjH\nyP76KCy6wEYPKsTkpBHPKr/RiraG/J0xixH9M7Z4NX30y+dv2zr3X/fl98ei6Wn9/z4+Pu7h\n8e3H48LvL06c0/51n376n5+2HJkCtu8kpXuk/L5Pgu8t2Gz46VlPf3qc+PfRRbTvGEhRL2OO\np/59zlP/fJQVXaCjhxVictKI5zixin5gQwSzGNE/Q0tX1I+/H17k0RlfHxtHv92ncAVG6Otz\nIfX74ePZtae+PjvyxzaTZQoIxUDKbY9qpVB9mML294Mj2tMODHTru0eH/YhCO7i8c8VN+knO\nZ+ECGz2sMCRnjfgvyhUGUTaLAVrJRv7759Ojw6hd//rxzxcyQrvwejSOIV2mAHZZMoY31rMT\nPn/6sX+Anv72EVb9/BlSZPqO9TLm2PT3R7D26xEfxBfY6EGFkJycg4TRcObMYoDWspGfIYTY\n9QV6iPcYO71JBulLlNJAyunZCf+55wqF2eY/j2Xkp1+lvot6GXJs+u8jWPv2dCnRBRkkSC6A\nFA+ngRQJOoFz8Lf7/P3HLwISpq8DKSrAQMpr64SvW4DEe+THt89hghP7LunlkGPXp8+P/4UL\nyeix5OTcfphWFAcg47SGjXzdt3KeC5svsMR5dhF23Nd0PZmukb4WCuBrpK8GEtHWCT+3zYak\np4PBbhf+A/vFI2bf7OjDv3wnG6MpH1GFITk5R7DZK2JrpLHbDHsTLqjjvD7G4/vHivG/Lw+g\nvj92Yb5tUfJ//ifGxM8to4/L4mYD2YvLFPCLFhN27Xghb6y9EzaXRHr687ZTtnsksln2+WOs\nfn/ZQGLDhDl2fZj+cz8guRCN3j60ITk5ByBBRaQhglmM6J+hpavpW9g0enyAx0DhbNiB2EJk\nEmR7Eh5Lz5FIAZ8duCj6HMl7A+mpvRN+by4Je/pfPgTPZzbPxzfPp0Jf990FmgZzBH3ehiW5\nkIzeNrR7cnJubxypKCyXZLMY0T9DS9fTz78/Zpcv/24fHts7z275+/E6MgnCvn/g8DftMLrO\n/P4J32xIC/jvM4CEKQ0kUOiEb9vMjj39fB0BnxL8Ay8UfBz9vR1FwwQ5gv7dg6/4Ahs9HNqQ\nHM+FxmFF29sr/2XMYoDMRkwvrNHvM5CarqrIZLpQz5ccfn/N/msB/QqvqshkulD7a3efjlMq\nyUAyvaS+P9/OvK4+A8lkUpCBZDIpyEAymRRkIJlMCtIHyZkqpd71PWP0v9tu/zL9aTgbq75L\n9QdJvcQX1Z0g4eH/7mvFvfpTk8hAWkBzgPS+qiHJQFpABtJ1qnI/ggykBTQHSG8S2nWS9Log\nOfojLAbXZNdAulISScd0DQMJDDifb6h90H8K+ayJ/bPLll2W+zUHSG8jgZq7QcJvCiU2Vu/Y\nD3oSwVpEBtLtOiRpKEgsujpdYqNo5c6z0G61MG8OkN4ltBNlIMG/XCWuyUDqqfqdQEq5OSLp\nTUDyBlJf+et0kq6a9+7GgeTckcHeBpKtkarLX6iXVDUPSD5sjd20a1cEyXbttnKPXxV709Cu\nnSR7jrSAhrU6F3uLgL0XSKnKaL0uSC+kcR3lmJ++tOrlZCAtr6EP3JyBJCsG536QeM6ef8Lx\n5hodA9eB9HahXRNJ5pEW0OCOKs1oBlL+M5OBtIDmeCD7fmrZuTOQFpCBdJMaSBoIEiyC7nmz\n4YU0B0hvF9r5FpLGgfR8CFrcXTWQKrUqSC+3n1Tgaui7dr78Ms6L9fI4zQFSV97XGuMbQfKF\nxxSv1ckDtSZIK79LQvQn+4FpOEiFxxTL9/FVmgOk1tDuRUBi8NwAEiHJQDqplUDCddErgpTX\nyF27o5yX9jF7eXWxVfAcIFWnd8LxyrJfEEnrov+cAkd4DaLWAYn/y5k1eldHbwIS+SUo9OHW\nInPmHCBVhHb7G7ALdGm3cu6pAST17rk+tItAWiWKXwUkt/dq2t7X8U0G0v4tLJKwAfMP8Rwg\nVSV2oqEs4vmrlCGpEaTOv2Rxtm4FhTWReaRxVe8Wkilk/n4u6I9wxNTlkXId1qgbQMIDWyO1\nVl0R2mX+leALgKT567iYKWqY4G1rJNu166n6ECSX608DiaV8AZDsOdLAqgu4LOL5izog6W1A\nWlnLg7TazFWWiJSBtIB6Okp/HXsU2q0ULJ+SGkiHv/mxtsSzBbyLOjpqwGRXvUaqqXNp3iSS\n3uY50sqaA6SKxOzNhqM/jbXc8P9JDojeBCR47LXc6D20BEgu/LZ3Rw9zCdvKnkNav0UI5pmV\nHshGb/WvGVDMAVI5tHMUJMiYeai0JkhFkl7cIxFbwjFeTl2bDerr2CJI8N5LMJRcAFC8OLne\nFyQy8zl6ZjEtsP0NfEAMXQJpzTUSkiQQ1btrpxvajdrDMZCuqhoXR67MCi4Q0kvLBN5KIDml\nGYUWOMZYDCTFqg9DOwe7dhtPMhfOh0BQulDbrJuZS0k6AZLaQnbg0hMG53hHdmK1NnrMhlDN\nZsO2Ci1XnNm1a7GC2yNDNZBUd4RG7uGwQXN+wErvAs3hkQ4SOtjeOB7PkyDduen3h/1AvTpI\ntK49jh9azxAtABJ1ga0g0Q3GVUBK1LfZUAXSYXAxfo0k1fcmINWFdi2/nz0f2oVdb/5ig1gP\nKdZFx/VWcOtAav7Dvj0OPkh/WAUh85KI651AqpzrfBjXMyA5fIAUCosGNGoKQxxHpd4K7lwj\nqYJUk/y4jsu74vY1aqf6QSpnJd7oxBht2DiyixBO8EIyAUjX9HbnrtEf8h31ViC9y66dr4yV\niFOIIq+WXb8nNPt+t9tz81ZHSyL2Kfm4yBBpgFTVyVOCtKhGg1TYgjkK7XDXm+w1uChSc8xF\nxS6INXOZoEHRIymukUxFdW021BglmRuPq5ZAgkWWg4ewjh7SZNxT8SUTHBzHo7T2m7zXH/iG\nOhPaHZFUvWtnKquro1yNoR3OdjUg0vcYXEQUJCDvhAfwktJCKZX3e5v3uhik4xJP5n8b3dhR\nVSDtK6TnMcWI+iDqbJzISwgRa++3a5dCR1ovrTbnzZR4Mv/baA6QhNCOOJywA073KVwI+/ZU\nWJ4EQQgRq3YK2buxl8tAWlM9mw31u261VRfWSBE/0Sop7OqR3cEsSHXrHsTzJiNSeteucYzi\n/tIa5LdRf0ed7uLDRZYg2Asn/IDDosVKsV1Ni8ER3joZc5iceFaSvt0bSJU60VHDo4Y9gBNp\nSqAKli+ukeQdiGyj8v9Q4yKJIP0xkCbWHCBlnyP5lB+yTAoWD4+X2OYDKaetUYXfrnKRJJD+\n1Hsk1k3nZCBVamaQvBDeYfC/m3yI7zaKhLiuEQqIAe8zoRiZrtCubpkXBcRCgsM6TU/NAZJ4\nGfe85dUS23nwDCQSmzXvG/CMd0gDJBf9zKT3R9PGfb1wb3DdrBO7doOrJqjknRJbJeEyyXsg\nCfxaY8um2WoYCBLxRtOBdHd03aob23oQ2jlfCOzYC3jwlCnk8uikPEDVRNK9s2HmzYZRIJFn\nB9kkV+vuqKBZ84KUj+q4p/LojXCnISTz+4YEhn0rSAGkKksk2BlIJ9XaVG7CY6uuJAnagoub\n6DTfyrvZ3VSJMbM39w/sf//5k9kKp3dWM0RIkoF0Uj1NVbrJEyBxpJAVyIc7eTz0242LkzWh\nBJD+4Omsa2q+pSQUzCa4VjhMq6hns6E/a65q+Z+a14C088HXpuCzQkUu7PLhJtXcA1UEKR/i\nvcoD2eknulSvARJig+6HDAS6I1xJqdzCKP0pg5SL7F4FpLkHR9YcIGUSVFHkSMjGt/rSkrxr\nAum2SfEAJJ/zSplV4gkZSJWaeI2UeYxU8Ev7Pi45FSwJQju+hXe8qXXPaMqvCNHzx5sNOjKQ\nKtXVWo2p7ji0qwUJXrfbASG+B1DgqWG/oaJ9E5D0diBNvoAFUQpubO4hSC0uyQsHBAW230A2\n847bFzzatR11LrQLmRRafeuu3d1FHNXgK7Y9L9BhaNeOkQ//b26HgAQv59VUHee+fobMP0f6\nA0eC+JsNGq0ed9eDDX38kHFTeg2QGFGUKqgH10iFqh0+2CVvGN0R5EkgVWghkAYb+gVDdg6k\nMRtCja8Ipc7IAzn0EhktSB1XHTXIBWtkWxWFTGP08iCN7dLKyONkJayKOTzSCZBicIhn8sTH\nsA2G5KYdDeXY+0akpZeCREl6KZDCiIwp3YdiaS2jtMwaqRElCOvSB7IeWBJj861H8iDdsEY6\nC5LWSzbad80BH9OnGFEMKZ5UNN2unXz9nLAG8kGgCIO/8AHfJKJtOXOrzTod2mlJuUDkZ+Dc\nhMH8mPILlbbnUWjlQWh3YvPbw9ezIJfEdlJD4F9huKvHQNJpj6SkYSANnJs4rRepo6oB4bf8\nCyKbOPLREVIB/+XiCccrvNNLg86DpHMn40DSLTcTiV83lHOAJF/t8EjgfPazECtHD2jlO+Kr\npWnUt0byOHVcUnd9eQM4ikqFkMJAagMJgfI7CMCVR7bysxT0e7rPMIF6QLpmkHoKHNC70ri+\nJ0hn10jMKdFfikJ9kYubnY6pgdRf940SoZl/jVS5s4rB1nHVZ54jofMBl+TgZSFfeMFOuAn6\nax/uVdzQ2lw0z3uDdPEwDqvLJQetVTc5JO6UKFyhLLn6lKQD/K8RY2DpNVJDX/Z3O+2umwZv\nVKVOPGyqupafP1PrRO859qkqH+12lflAw6NVlnHGgeKtXhzRYQu6Mh3vrGZBQgD+9xHQ7V//\nI8fh6+P6nz91X4+ynuXtX/CZlPU8T8pn16N6xfOdX7X3kHxhGX0g6ehkgQ1L/mJSeU6ojTMq\nKq/tuWzCrjVSRdTQ5pHEzYbWqM67dH+C1MTeGSksIa7e7pF03iNptV8up97uKhrjhLfvogrk\noZICur7Rq3Zj+YQdHV63jj29RmoCCXDiD2GhpoAVJUs0h52+uxdJp9dILU6ghIV4pT58qrBr\nbk6OnSuWImZoBMm5uOpy8nzCYSA17doVC6hFiHsk/gJnCEc5SJl7K7b6ItEmjAWJ2F8uiXhu\n76qKKg45EmkiZVNzl3LGh/UceRJczQpSVTm7lP4ZBR7xaRZen2OxXiZYaAhcLlIPSFWZyCjm\nkhdBqrGCo86U0NnKxWkvHs80Jz3RsE24f78JpL0LTxvbEUg9wR28c0deVqCb4bRul3Z6Y2Bw\nkbo8Es4p5YJPgKTRW44ukEgFxMYg1qAZQiaGUHPlpLZ6Hy4n7OqGwxGqK6WqmnqCPLieDSio\nhIR9tGyhW14HpOqCO0BqjoiKLWATXDi9jxWCRIeLzha8Re21h7y37NopSQ8k3CJwETQQMjhh\nvARD6BuQwRoHkjt0K5npt22Nnm8AFhaXz0HiYZBQZd/MrjjcHcVoGZpyaPcMNhz1SR5GyuMZ\nKFoelb4BGathIHmORHPdp+0ww8VWLtkaYi9L1k3BdUOpN9yrg0QTQZYocINLrOryy+B347TC\nP+xzp/upAJK4a0enx4NiDyYIdc0Bkny9zSG5MA0hUx4CYEf37NhqWeQoMcnLyVoAJA1L3Wc0\nx9GB8YET+xB7cUUlPb71dcj1NluIRnuKUWhKRTFtIAFMcOSBpwCSjwZK5sORgSBNvZSkBX5n\nw/kV0jO/k/6NC0YMsEpyAEgmEoxaNhIkyRx6PBJY6/nm7Dr9e+2EYw9D5HCZRGvOtT8FScdm\nWnQ5SIkDPhxktU7ZC2LlBb4CYds0KLORNGQ0SOKd37gW0AEpeb8OYncKEgn8QtXZO0eQHBvd\ndUDi3XFKQ0FydPMPy3MUgg6QRq+RJgYpc7kSJcaUp79DiIG0o5ULEEjNJJTgQ3qdzv9eu8as\nuRLLl86U7xxA4ilIoVwBJCfVSNjjRR/MIt2zzKuDxBAKcbXfSCLrpIpbhqShleNmt5w0ftNq\nW95MicXa2kvHPHxA+I+Ipn0O5L8firaRvaJc2xLf3TtS1jlA6v2dDXJYF5ZFfMjI1NbSPgiW\nuu+zRyq/+7stb6bEk/mF4kiPOhIuRJEenvAeAaIxBim1I45r8tjx8AvmMC9ILf4IAII+j241\nsNTS4TcEdKD8n3XZj47+PtJgkKonFp6QOXlkQqgxnfBh9ztN0jNScnwm31aN1cwBkny9hiBw\n9+iFhNuG6K6iWt7Am/qn/Bf7sv9+vXGNxOciOUn2bFXPxK4Dv4fInTYmX3iIJRhIyXPBQjuS\nG5TyZG6ritMXAIm5G/G2cfarnklDCxpSK6r8N2TzvweCrRwKePCSm1NUe4CC64jDBv74VSoo\nGmK683AEdoZNgSOpnCEgVUxi1UXh4Zl37TCCzoPk2PPY+XUAUvZ3qjSPyWF6ZZCI9YfpL6R0\n4Xq2oJA+CfKOprxMtBjnuRSk6oJri3lKBilPUvIUlmzpZDwSHbXpdeyRtP4Yc5fP6gXJUeul\nk9/e8sIYgf9wbNfueCKIZ9hyWsdqSSpPL7E0jXLRz15VxBXpvlwJLTLJsSDBwX/LSOGvmuvM\nHHIJcijFbTxN6Dy6kti695AhJMkVHjcsDjzk+qtBoo6OkcR3caSSZgapniL0Sp6G3vtNh+hv\nIZLOg+TC/+eUcxCSqXuI0OSE0UYdt/rNiJ1QRKFl0Xzp48iDurkKc9t9Ugm87KU5QJK3v30I\n7iSg9g5y4d7pkyLItxUD55cB6Xxo57yvNMiyCvkjmNAO836MgRTtooLBu/AxW3fkemK3Q1de\nAVDSM8V1GOm04SDVesq6Yp7KglTwSZ4chNAgxAWh9/ZiWp8g3bdd99QfEaT9OdIfOBJ0JUhJ\n+FOwwb0/cZAgCz79I3E4FC+PQ+T6Anjxd5IK2Ax1smaxW41vIp0uhPuTTx3LZe6wsZTj6zl3\nxHjy5CcnCs2JzX1VLbuRpCxIhzkvBCmxKMKKtB0WpkWaJyR2lCeaMooiYBhJSEIMHiyAuh9E\nl6ApsxpdiY6SRFJ/3KLDqg8A2umhtIR+CsE2GYhq+EOy23om4cXtp1tA8sSCzqgeJJj82b5O\nsHY2wZMudnCKOipPTrm4AgxDPKMiPFTk3UCWT+iOMB9jNfVVgilkzGgOkKqfI5Fz0Knp/eN6\nKQqNK+4WxmE2kEoPYiEl8xCVM0e5xPKFyF+gP3CYKpmYIgcVbNtFJWFgRgcE3Y4nxYQi0DTS\nysLYhhGmVdTfZTllo3CaOaNjkPI+yUcryKhQTIZNJkNy0KjGBZW2lEDSES+QWXt61Ye+89nv\n7CM8tICikQ8YYuZS9qUv8ywkkYOhT9tMQCJRzK0gufD/OR0WQB2Q5wc+Ctx4qS7pTlx1HtSK\no3Wjr5bXSPeDxI0u6SLqDAgtzEUlvgTGk/ACngrCA1jLQIb9O2Qg2bDi6FYCadi6w+BD5Cw/\ngzeJzRAndJwfJxhCEQmSnXhHLCyAktCtVzQqCg8u13mQXPSzVy45zpbofGIb3K3sNsz8AQsu\nQueTegJctQAAH49JREFUAIIshkKSYAUexonVHE4RiEMDXXQuZly8q9TEZLhKhWSKzpWVaUEu\nHTlffkWI08SWSWLhIki+lCPOXO/R9fUnIaYLpIPOr1U9SOiPHG0GrklYPAUjEUZ0T0CZgwSO\nYEF9mCO5mXlAjWQ+JP4qanZXlyTlNJbia0FCg+wGCba2Y4hI7CU5JQEk72pB4q7/eglPW/s8\n0mHUUqUYpLzdYa/zFoEhgGkn0R2e4J0fjthY00kUXRB3S1Aj1sbn1TMxsBpIe3x0zJEvA3do\n0R6mI+6JQmd6OnElOaMaHIYVx904J0jH4qFdzbRxWCL/kF9logvw6P3ZaZKA2rejV+E8+Uzd\nGkTn1OugzwIQyXeM/qqssrZLNEAi/XRQW5G4SmuO6MGdHuLzhQbGuJDpr7Lu2ziK1QtSmKfP\niOcv+HQ6EhQ4YvFQIH7xwA/HF0weJ0xA0oWJHOMUGGzi3xhDGKwj4qf6RJy8R4iMaAVImVeE\nXOg2urFJZqdc/CLdKfZkXLncuDPO/4RUQaInOuWETxmQyFIHnQK1XBfMH0tCSmCcIdpg98Qi\nEAYKzKs+GngoEwqJaC/ddrHjpKvDzIXcz1GK/BoJx8ex3g6Tkjy55H1vZTdOphMgaXukQpnc\nIRGQPB1JbCkPzkLo7YiPYgUTDKGWSEIg4pzQpOPVo+hzyhpnUMmY7p/IjR8VQHqNeXHc9qFr\n16jm1PnGEcasir1SD0haEuao+FSoFA+Y1ZJTe36Mr9l2ARndKCp3kIKOvefrZiyGF+Diao85\nEUzk0Fw7en7MZJe7Tnbq9lhu77WtL6WwXXZTjqYt1H1XUPeQ/DsZJgIp7R2pN9kaCc4EFLZ2\nEvsmxs9jDowJmddh8cluEQ5HOLIINmW79FT2plOvmOuDOHWlcOI5J5I//88oYLEKsxbGA35n\nKWmMNG/Sr1I3dnh1NWV+t0kzSDh9K6+RctcF3IiV7H4EjJ2cDanDd/ApML6ODjxbIVFqgCGY\naYFS3ryq4U1uip2Qi+jySMdBZk3xRyB55nkYUXDVC3fts/NmRS/KhnGRtEBSVB9ILAUdO/I/\nycbCMxJ+eDonBMRI6BZf4DMtWA1noqaPYkNxme9JkiZxCz5O23NtT4EzmYcYL/awVaa/BEi5\n31q3OkhsgQO2TvwQISI4Fhq9weKJf99HFPwdEBbsgiapvV2MJnN3qQtSiHKr0nZcgwSh//fu\nkfLUQL0SSImaQXJEJ9tUN0iHJdCwDe0eAi/wKnRHAZhAb0M4wqve0au8VE9KE1c26N6KN4PM\na4NUOftVglS5RsoUyLtINp5qN1rray9Ul0eqmxEOcasLG0pX6BxG3Ay4nnBMGgPeyeN5xAVi\nOOdpQVgs21WCIiWLjawC+yy5KSwxYyH9IGl6pIrf2ZBYBtxrxFGm1mjuKTRLPz46qR6Q6gYp\nSX6ibjGr8xQY4jEAjf08pIz8qQt3xQGEUIX4Kk/L3VtAg8GUpDhOge+CEZEUsm/r76izOpwt\nPelbH/qCXWUHpNDZUGiQEN8NA8mJhz11C7ZFfUyYz4Pv2I9xngciiFui7oS4LGFxBVBRewnN\ngjjRYfc4R0zHsc8BrfjWjwxrYpB8uHd0zLGhBLJgrNYF6U/0k2h+kNIZPMx6uO5hviNEb44l\nYcIBZ4RxvwZXgvMjWwx7MxiHvLkhqQsZEOv0hg66o9Xk6E03Zi1Unf/3SCT69bTOyAuDt1oV\npAJHXSBVdYQWSGldYZZHd7CvaWJWmLNJEwZDDw7OB88VmIFPnhZIQMJTnnIUk0Rm5EzfpZNF\ne0eN0TFIEB745OYoSPT/o/udVeogwTxcTH9YRQtIWJ8LjXGUiJgj4CYRLJ9COJKm8aRInN6j\naR68FJ7yzJRCXfDZM0Pid1nszjlAKqahCLn0CgaA2DfL6U9yQNQHUmUGZmKddfMpHk84tiaC\n2phrSvAKU4CLQaJmj6VQL0KIwxglmop9ZEpw98zU2o2ot+eLva9YNZ9HnHSFTk+rqviPX3tA\n0uqKunLk+Y44CBJ7g4eQFkaOXfaesQH8kE9kkRQbZ3BqWGDaXBIxxq3fr0dmnjX7ng5Pq+sS\nKSAX2vH08aYLLQnnn9fT/CDxed1jiMSJ4RsG3O7ZCSkQpKWABSBiPhDjwWsFN+jpKihko7cX\ntZ7cczJ7Z7uko8Nd9LNXrSCxjMk8kZ0q1tcCIHlqhI5aOgJFAkli8QwtdD7IC1v4UAi3G6b1\nOFIKRpMeQEpNJCYnMq18EHiio5Isl4R22Xwt1rUMYpm/MVGd33GTaJA0MTXOTi7+Cq6Cmjd8\ndBEgGfnoOzLIlz7B9aQ5EFLpNuOb53cc+6m3BinvjadRcauh0yO1g3CybkKOp0Ye7B4WKjIr\n5U8+ugAbGR4HmAR7AFDoE+gJKU7L3yPJs99Wtk96OrrVJRSLeaoptGurXqmxI3XAUZ9HUlL9\nfEWXHXxP2acg7TlEctiSKtlAIFcwYkMrD5MHggbVhtZxpspzTeyG8tx19Xxo7TlVgCRX0+Rj\nDKRTapmv0FR92DJDuKLwLHgrAkoa6AkXSZbAK4IRrnskDr1I7CnrLIPND8SzdXfUAB1XnSOm\nBeP5QTr6e5adayQ0pTOSFxWZZGDQ6C08MXkXHAXxCszZeM6SZz+ITwrxoudLn71CqI2DFPBm\n4WCDKR1M3x0drWWUh+XoMNDkv6ZUD0hO6cZd/KEU2GDEtrclWD3hmnEVOSGygPIkCowAw524\nkInihcmBTdKy4JoALii+oisOg8BGDQAp/0/NNWxBP+C5VidAKudl5nlcd2E8qEsItsucCYnD\nmOuJWWK4EOeD36OCHamVQEcCyWT5hu2li6tSR1XoDUBaXp0gVbikuuiaH+ddErNQCkPkcDx+\nRf6DIsBiPXRAHKU4FgT3R8JLj8SEPnKk1f12xv6Ub4+ZKpl23Si+D0fZ14TGgVQbXtPjTCQU\nrDp82Gw6425il5MgAbsKPo33sC62BxFw8xt0YRkFneEwM+ulVpD+gNp6MhXe6zmdDktfQH8y\nx0w9INUukpquhxWIkC/ySJ4QkJKSYSd+yITARFD69IBbZfzBB0fkojAOAtHjnhDxqe/IgToM\n7V5fVRz1gVS9hj4oMSrfeXECD6sPMNTDxU9MEonkfAjOPDgmcj4tLoryQkMDYSTK45vg7I6E\nnvrDJPRN1N13qRUkBbOYTSNB0pFQYAEksuBhTgRdTbQgykDmeRq6foq8FmMJc4ba6Q8PrDsX\n9VRsWkXfw++50FGHouifUGP+F1ww/cl+YFoHJB8cALFZSggDglzlDsx7F332+IN6G6Qs2pSA\nHBxuzCV2VW71I/eqk5ZbTaqMvmvKaU79YiTVqRkkNl1r1+2cNPqwDAlcUPPmHIneCHxaKVG0\nhOKwEmi2BsWxHAMbQCoGb3Bn0nm400xHHSpkVxyjitDOQKpJGYca+rMdOIakajrXR6bv0Z5L\n4l4K47skJ5DhxZzMP9KlFbBKvQ8lJb2zbD+iw8ulqOnbapdUSPTmIB3/RdigHpBOjG+xbjoM\nidUFK+YOCXcQyKolMf8Up3gPQUy6F8tcE5JEtiK2diE/IS+/o/SOc3bHPJ6YoqpvlUFqqfZF\n9Kf4kWlCkNCICU+OxH1h5ocoiqzyM/AcOSwOFrEHh5Wx4A4/En4gXSCEkCJBkwWJNENOUdW5\nh1bNeiBbTFu1+kvp+9TA0YwgkSM4jgIquuDZ2kaDLAGRlgsBJMpISXuGsDXho/YXQMqZutsB\nznVUlVyFVTv2o5Diobd7jhSDow7S2DUS1kWsEj7vNubBQ0TzagEY9DppKkzEGQE3yBPR9tIm\nkAt7+6LeSuYOydRdDMG4ST5snuQT4OHbgRSpvF7qAskzq+kWKWHf1grFyiChVRM4fMm1cFKE\nhLKDCUVTVKQ4KFxNOwOjTp64tl94/46Mltj2oNgW06YRIOmIFVgVQsHuM5ozR6QElVwo3UjY\nSyCBWpiwhZI9BJywOqOdlRpoiluxX06AJDBfrC4NDVrymx6aBiR2FkMq4ozqVix5lT0XBmmw\n1ieRD+E08OXgiufRmCO7Df0d46LPPWVU5iyN7PuGdvU730/1rZF0ZqtMfsdrgqRkU9kBar4U\n3cnLp3RVFQoI9+Y9PUPWR3AIAO0F4rahRwCrOzfpyuhER0e76Gev3hakRo5O7dqdlRRRFJKS\npysuxFue+RB0JAIxnCx6DUI5D76QuSWkhHLng19CrnCrDXxWbT8U0w4GqZTmXUO7lKMDsmYC\nqWBQEUghfCLUMJTSc9TvREyRDJ7mhUU/y+MxS1hd7ORtjaMrt5ZuULZmA+mUmjmaCaSCQRFH\n44PxQpwH0VjidthHAS/GSfA1xBtBBClQSUBibLWujlxFjtFrpLpr7xTavShIDBPquRyiFDjL\nrJfis8TFcA8FVbHdOJ42eR4cXBAGiA19ADsatR1VWTI0r6INNdfeCKR2jjo3G6oztdSdBQmX\nHWjpdONBDuVyDii3cAo1YDyHCXgcuEdw4csHEBwu2oSbkM/CnTV0lLaUGK7l9jXV5ZGITWnW\nnZvLASRwR2TbLHFB0c5DxfPazJoqpigARvwToO2pHUk9k7k3CA2bOupCNfnWd11RPdTlkUbV\nnTEojKg844mubGSO6uQxVCNl4nlcovHNCPEeZIvKJa5byXStkWgr+1Ud2lWs9BbxWK0b35um\nAkmoE2OfZF8MPu9rGWblIi9Z2HCBRcGkgLkQz2Eg6LltcLRawtbDfujoea3B0gNpFY8lcVTB\nVt8aSX22yycISyBYPeMGM2kLbq/lWcKLPj5PFz3xPh4jEFdpe1QJN0EXS/gd4r7sDdd04xwg\n1STM302d771fnRz1rZGUppe6iMbhgYPv8BP8CLiP4oJH9Fl0Pw63xB34IXKZbddRtPbvnlkM\nnwj6O2wFkPBmSwVND5LIzGCQynnRX3TXnYDk0SAxsgO/EOIySgR+LiEGjsjHuR24ObYM8wQb\nDPEcbyLnv9QRyY1HaecA6Wj7O7Ta8c/hh2qzLlXVoqkTpGOX5Pi3yrqZCREHwlODPaMvwe2I\nPDDpeXAkWNxORDB8iOEoc6ESkgCqJjcBJ4u9IPeLi0+0SslkG0CKYGHTnRfuahndDxLp0rq6\nY2Bw6SPM0bANgAuX3U9kQMoRxnANs2gKkmcF4+6H31EKzocS5KpBwjtM0/d4JLy5U2rKn7Sc\nGcD5xoxW337dph6Q2ERTKrgVpHQgAA0+DmFkwDWgcxGBIW5KCN4gJ5Tpwt6Dd6Qi4voCOTGJ\nkNFBq+uCmqS7ToKkpbaqY6s4MIDJdIajPpBiu84VfB4kMuPTKzDFgasI4ZlMCfwHEKQIBXCQ\noaQocI/ASaiUlk8WRQ5grOBI+l7uwAtEqq55RYhbBc53S0gGqRKvPpCqkh/OxS0eiV/CT3TL\nLVg0OgnqRCTCwPVgURQ+8p2Ee3BAnSBkYU4RPNphYEdvLwGvxxLx9k6pESQ58xokneKoC6Ta\n/sH5uLbuJDTAQIm4jpAQLoQQz5MlUzDmjJOiGLFPLKMnO4L8JLuH/QoP/0KjqxTNE8KKsFEu\n7cwunSkgMZgVNQNIHXVzEwIzh+UQtTUwc+6SGBoevEhi4kKMB/sDGNZFQSX5TKaJ3T+Fn2RJ\n1dQX9a67qjzXmfVs1TyrCs73qXrd1AxSZHpnVOfRwirJgeWS84QY0jYfOSNHyEC/Qh1PuJk9\nxOOhIm0qtAL8lCfUMIzjOyx3WOlqH0gqNtwf2uHktDBHA0FqynOqbjr7U5DQEXgS/HEXQygD\nOhhRjkZi3kOG7U5JaXQlFurDWcWzQNLDT3RL7G4bwGroqFyWe0F6M/WAdK6OWo8GzsGDncNi\nyHlm8biCij0K1s+31dBnIEjEjXkW3jEeKdQk0CSXiF9KOsHxE5Vd2tPzrqkG1aoX1Kmd76c6\nQMKFwNC6WTVkjUQRIanA2MP/gBuPAeM9iEAiI434FXB5aJtOjPjgozxRxCAlYHV3VD6TwiAN\nAUnDeFR1nqMOkDCqGls3tzTieHyI77AhBAC6RgHz5u7IYzru1YAZ2MXYUhOviJUyUpjr8wTi\nzO1cAJKORoR2KsajqRxHLXw1gxSZzBkd5Of9DUE/bK+F84mD4a6GRl0IUpQHinQBHDxPw0sP\nKSOXA43lSbO388Ygtdz5JdLgaCRIUoDTVDfP64ilwzGL2rxnoVl8Kk7NznrqSgA+6okgyCS7\nEI41D0sRJ92oKxrm5Q6jc9HPXg2w9+lAyukCkGr6wiUH/XWzTNHkT4GldAhkUQqRB0QmuCPM\ngzxGOwcpKxBF5kBK7mT0rl1n1rNVp9npvLcOSG0Lp2EgJVHMmbp5Lj4gDumAHT3gAFY+3G/t\nt0Pd014WxI6esIY2T3iNPVL4jm5JTa1F8dvVqrojtMOBIh2j3TvnlMfl1UHCnTwfAiohXEs3\nIKLdNMdE1j+JCDEhhUenRFrlIIHyvtQJj6RYdc+7djE4zEPNIIX9uk3NIKFZVUZ26iCR7MQX\nRSSxlRE748lmAV4LzeHwBToQPgQosgYsh507d4t4p3dJI7RLQJpHahx1gITbW5UlZxN292ri\nZYilx+4k2l7wdOET7UN4QIUsp2Dd5HEPQghOkFA8oRbCtBcioS4lIy5Wq2qhHdU2c7VKHF3x\nZ11qM4DBnq07zRdMgFUTPiVhnaDI+eB+wzbsLiyxIFLDE8z2AsKRQaLxdN5kfMPtGSo4ZsuW\no6p7tr9DKDerR8rrij/roqXjAkUMcXJjbiVeMCEL0aMjFp2Ga94jIVAKKduHNJGfCZ+i886H\nFcIdIJHQu5i1IuZSAem4mvk0GKR4Vj+lw/yyIZIowUX/cRIIYrzlGJ2RFLLz8kifwAvy6MLz\nJ9pyl6ya+jQHSD2irlEt0lVSEZXmxdPMHinEBU44TddE1DPBKVjkeMYDgBTRxueJaPEU8nr0\nSVETQ+0MtbDwOq0ukAhNpXQXgET3auZRGZXXA4ltm8F5xGc7AZ9jh0LhIPFaxFHwN5Ccb1Gw\njHETaT0k1AOwL+goMX0FSOPXSPNKb79uUwtI2ijVgOSoaZKmeBo38agTdwg8uhPCDeSMmaMR\nkcNoxNGGJO4R+CKxHU0p8teoYSDRnRrpNLvyUiBpc9QCkofp+qq6cWXCk3PC6PKFBmMeD8k6\nid4DyUJAIvTttYFv4UA7LNvx9rDv0SzQoebcfFa4tOpFdDNI+5ESTscguRBcRw3wEUh0fUR3\n2jx9asRCtsQfCaghbg72I0g7EHGMPVkKbOZJg2zPTPvtlF4VpKJ6KOsBaf98epiqQjsMk0og\n+RDqOfifxC3hi4R6PLbjexcQsFFKXARL7Hyob4R2RgFjrwZbc6n4Vw3tSuryVr0gabikfAnU\nAndAWGpHvuAz2zigPyD4InEeOCyGTCAGqdyJddCMGCQ4sx8kHRPPAh0ykHR1QMqFIOmsk7KF\n8JgIfRJtAN/JQ58ReaFo0xqWQ4gX+KMoUCRghiocBToK6nJzSzoLtGsOkF5GIzjqBamrrtq6\nyVyfW2Qwo2UOBT2GA4RclIS5IIdlkRrBiYXTBD+SmrWKXyaJrt61Uyz+BUEawlFvaDfUI0Fk\n5enqI87p+IewHxDMP2wg0GCPOSOfQhoWZHSnLxTlUiQSmgXfo7BCmgWkFwnt1PfrNk0JErH5\nkE6o3cUfHDtGpwJxHAsT0X2xCDGsjhwtzgGW+XuJgkja1IPo71A3uoXXA2mQOkEaWjeAhCd4\n0JSCxLZ7A0jM85DUcTzGP0GGKAgkH8Rbcch+RBKcSiqv1BwgdWTWWUsvoSlBwgCNJuWrEwYS\nuC5IB97BgXfakxdwwGITXwgRYjZTeKgb04JFdYd5i4IEHj/f5S76mVxNvPs5HcZ13YHfnCDF\nV/mZaEMZ1yYYDSJf8a51Cmm+dursSv6I+D32qCkqcHGQWkO7cLul2z4EqfCxQ+M4mhIkIf6i\n6YkL2k+EdX5pL4/Hdkck0QqrAjI+8xpIkDXaEs0Ufw1Ix5i8GEjpYyP6PXnAGYIx8XywYIjs\n8Pth7ZzEsihDggG4zLWqdcQcIPVl5ZMYbICy4cL3TEhuB2838ocWuIwlU6XnB7JGcjQpSGJS\nnOFI7Ey8QDzh03UOzosFkDJPgYopakopjXS1u7tJcdV/Hir8jPPSjSOyT+rCFayDEkdSkSuO\nJuOL2Ow81abXB4lM+Cw2w40ytqm9lx7voJH8Qun0QjLZQYN1uyGGv5TqFpGqO34dV/Aqu53D\nJLadjGKFtNp4UOILmYNbtApIJA9MR+hfgCX29Ef2DpJbcPCaEH5PWzdgpF4bJCiAsuJwzuOx\nRVqtANJeQsKPHzI8DRoIknPx85+zJfrg8rFLPX7G9w/IObFZUplpgCEw2NvqrFYC6UQBHCR2\ngKNBbYVjQhdUjvHHQCqb26A3GqD2ASmj9NmMYoBVUyzpO8wH75iGaKI2EEse5ka0Ru3Vteqq\nRr4wSI5XwZ1P5G9ceiH1SDkN5mgcSE48LJVYafjR3s7miXxgB71L9UvXnMa9Jc57mSRto15n\n167zFSGHX5JH8qKpNINEDyQN3bEr1HsqZZy8DqS++Z44oc2PsICApIrOsIqhBEfS49Ak5Vyt\npUHyOCRs1w65iGIB+CTt2nEEfVLOXRwtDxLkjh4ysLLIhJghiQNCF1tD3FCj5gCpvwx8Jp57\njhSSsUx0StwHdz/m/qf2OVJR04JUEbtqgvTMyxerUQOklw6EjDBMcSxxoxYHaQWdXkKNA6l5\n10516qf1HoIUtWFrCDz9OM41WnOAtOw/o6iBZGaQmks88MzdjrseJCFeMJCCVgVp9H7dpplA\nOk59gqTCGilukWMJbY20tq7haB2QTnmG4q6dUEmy7L1XBlK/LuLoEpCiTQVUeyGjx3UC9yNo\nDpBWDe0qpEDbe3ikhmpudz+CDKSx0vBay4A0qbO4RHOAtKDqCFGJ/tYBaU5ncYkMpD5dyNFM\nz5FMOc0B0nKh3VX7DE/N82aDKSsDqUeXcjQOJCceninxfTUHSKvJQDJFMpA6VMmRFm4G0gKa\nA6TVQrsqqbmtW9dIpko1dr2iSCP+d9vtD9QftZLqu7R3DPRLb38A9dKJL9KpV4Yt29m6RpRu\nIN2hBWx0iWwG0qyJL9ICNrpENgNp1sQXaQEbXSKbgTRr4ou0gI0ukc1AmjXxRVrARpfIZiDN\nmvgiLWCjS2QzkGZNfJEWsNElshlIsya+SAvY6BLZDKRZE1+kBWx0iWwzjq3JtJwMJJNJQQaS\nyaQgA8lkUpCBZDIpyEAymRRkIJlMCjKQTCYFGUgmk4IMJJNJQQaSyaQgA8lkUpCBZDIpyEAy\nmRQ0AKS9SP7L73K/Ck9MnG1WrmjNxL4/8cEdSqfvUt2NHmery9d581qNrMvGm9XyyyHjvDoi\nfzccC+efDhLD6fqihfTn2zEucfYOr1Jd28dkq775unGuyVZVHSu9IRtmUJXbikTzST8dJIbT\n+kXXJHZ+eOLsHV6lul4Zk6365q9tJG9WQzaWQ08uspdiXbnEck/LqTM3UEpcbscRG3LiTGNy\niV8BJC98qsp2AqTObJWObCaQfGQvR3VJiV22WSIbByuZuOict0ty5TtTSCx/ziXO3+E1uhWk\n2puPG1m5aklrq+7raUGq6HIpcQ1I2FHHbDATrt8/OAQpKavUDBdF4C8CUuVcT1N2glRLROL/\nejYbXgKkQo9lUh85O37U0o76knNpG+/wGt0JUvXN6zTyFTxSTQyQJnb5xFLRFebelLhm6ITE\nuaRS4tIdXiM1kNqJqL95lUY2ETEpSDUcCYlLf4BJKPrY3JsSJ/nqQTr0omBLrX/ESl1aINXd\nAgep+uYNJKnkXD1i4iOjTOfEgrk3JK4dAyHxwR12zuWjpARSk32ec2TvC1IdR7kWF0FKiy64\nr5bE0YK2OXG+zelS+VaQfOWNHmfrqK06p1ojaxsa+dqmIRoFEjpwxz5VJC40S0xd3IhrSoyX\nmxMf3GFc8t0gVd5oMVtDgNp58wqNbMjGp977XxEymd5QBpLJpCADyWRSkIFkMinIQDKZFGQg\nmUwKMpBMJgUZSCaTggwkk0lBBpLJpCADyWRSkIFkMinIQDKZFGQgmUwKMpBMJgUZSCaTggwk\nk0lBBpLJpCADyWRSkIFkMinIQDKZFGQgmUwKMpBMJgUZSCaTggwkk0lBBpLJpCADyWRSkIFk\nMiloXZDwD+3Ar+oXEuUyD2yYSdKr9/i691f191oMpFn06j2+7v0ZSEvp1Xt83ftjf0uK/EFF\n+MM2jwNH04Y/6rNnwSvwB3Vu/XuUry36R7zo36uCzx+HMID4J4rY+Mys+VuYU/pH2ZxPDmKQ\nHP50SV7HizVpKhkuNiZksNgoOjY2M2v6BmYV/U1ATzucOxwvDl6act2+WECOHzhxTOLLwkjO\nqtnbl5fskcogPQ+dgXSDakF6fnAG0nXKgET3xFOQCEU4UHR5tW5/TC4EKXpqEY2YMNHV/63a\nGzV7+/IqeSQfg+Rd4q8yjmjdDplbLjlgY+L5iK0XKKzRSklNod0xSNR3mfQl8JKOifjRQrux\nkkGKDnii/RsBKdmsWLhD5lY6XJwpdg6HJYk0ZtX0DcwqGhlHHkPsp/E5EiR3+0lHjjHLAqH4\nsiIrHcefSuBzJEiIw8IzTKz5W2h6Zy1jn8s01PRmWizQXqelpjfTWoH2Qk01meaVgWQyKchA\nMpkUZCCZTAoykEwmBRlIJpOCDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoykEwmBRlI\nJpOCDCSTSUEGksmkIAPJZFKQgWQyKchAMpkUZCCZTAoykEwmBRlIJpOC/g8rnuwfEZClmQAA\nAABJRU5ErkJggg==",
"text/plain": [
"Plot with title \"\""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"par(mfrow = c(2, 2))\n",
"plot(fit3)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "R",
"language": "R",
"name": "ir"
},
"language_info": {
"codemirror_mode": "r",
"file_extension": ".r",
"mimetype": "text/x-r-source",
"name": "R",
"pygments_lexer": "r",
"version": "3.4.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment