Skip to content

Instantly share code, notes, and snippets.

@vincenttzc

vincenttzc/gist:add4d9059034dddd498e16b8d61ad1bd

Created November 4, 2017 08:24
Show Gist options
  • Save vincenttzc/add4d9059034dddd498e16b8d61ad1bd to your computer and use it in GitHub Desktop.
Save vincenttzc/add4d9059034dddd498e16b8d61ad1bd to your computer and use it in GitHub Desktop.
Download ZIP
Real Estate Project - Polyclinic
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('Model1polyclinic.csv')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t3011 obs. of 14 variables:\n",
" $ month : Factor w/ 24 levels \"1997-10\",\"1997-11\",..: 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\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ block : Factor w/ 165 levels \"201\",\"202\",\"203\",..: 103 103 5 5 134 55 57 46 51 7 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 10 10 8 8 2 9 9 7 7 5 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 4 4 2 4 3 4 1 3 3 ...\n",
" $ floor_area_sqm : int 67 67 67 67 74 73 73 73 73 74 ...\n",
" $ flat_model : Factor w/ 7 levels \"APARTMENT\",\"IMPROVED\",..: 6 6 6 6 4 4 4 4 4 4 ...\n",
" $ Age : int 13 13 12 12 8 9 9 9 10 9 ...\n",
" $ lease_commence_date: int 1984 1984 1985 1985 1989 1988 1988 1988 1987 1988 ...\n",
" $ resale_price : int 180000 182500 196000 185000 190000 196000 195000 177000 225000 193000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 0 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 <- data1 %>% mutate(ln_resale_price = log(resale_price))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t3011 obs. of 15 variables:\n",
" $ month : Factor w/ 24 levels \"1997-10\",\"1997-11\",..: 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\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ block : Factor w/ 165 levels \"201\",\"202\",\"203\",..: 103 103 5 5 134 55 57 46 51 7 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 10 10 8 8 2 9 9 7 7 5 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 4 4 2 4 3 4 1 3 3 ...\n",
" $ floor_area_sqm : int 67 67 67 67 74 73 73 73 73 74 ...\n",
" $ flat_model : Factor w/ 7 levels \"APARTMENT\",\"IMPROVED\",..: 6 6 6 6 4 4 4 4 4 4 ...\n",
" $ Age : int 13 13 12 12 8 9 9 9 10 9 ...\n",
" $ lease_commence_date: int 1984 1984 1985 1985 1989 1988 1988 1988 1987 1988 ...\n",
" $ resale_price : int 180000 182500 196000 185000 190000 196000 195000 177000 225000 193000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 0 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 12.1 12.1 12.2 12.1 12.2 ...\n"
]
}
],
"source": [
"str(data1)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"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": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\n",
"t test of coefficients:\n",
"\n",
" Estimate Std. Error t value Pr(>|t|) \n",
"(Intercept) 11.52751618 0.05593668 206.0815 < 2.2e-16 ***\n",
"Treatment 0.08653005 0.03654374 2.3678 0.0179592 * \n",
"Period2 -0.15864236 0.01512671 -10.4876 < 2.2e-16 ***\n",
"Treatment_Period2 -0.00974369 0.00435448 -2.2376 0.0253235 * \n",
"Age 0.00089555 0.00590872 0.1516 0.8795419 \n",
"month1997-11 -0.01642520 0.00820685 -2.0014 0.0454452 * \n",
"month1997-12 -0.03562712 0.00811653 -4.3895 1.178e-05 ***\n",
"month1998-01 -0.05858990 0.00929460 -6.3036 3.365e-10 ***\n",
"month1998-02 -0.07771234 0.00935745 -8.3049 < 2.2e-16 ***\n",
"month1998-03 -0.09766045 0.00962254 -10.1491 < 2.2e-16 ***\n",
"month1998-04 -0.13720592 0.00904116 -15.1757 < 2.2e-16 ***\n",
"month1998-05 -0.14701180 0.00943576 -15.5803 < 2.2e-16 ***\n",
"month1998-06 -0.15369773 0.00899621 -17.0847 < 2.2e-16 ***\n",
"month1998-07 -0.16768465 0.00908482 -18.4577 < 2.2e-16 ***\n",
"month1998-08 -0.18302266 0.00957048 -19.1237 < 2.2e-16 ***\n",
"month1998-09 -0.18844825 0.00905533 -20.8108 < 2.2e-16 ***\n",
"month1998-10 -0.04042860 0.00980638 -4.1227 3.853e-05 ***\n",
"month1998-11 -0.05825358 0.00955459 -6.0969 1.229e-09 ***\n",
"month1998-12 -0.06875384 0.00983997 -6.9872 3.488e-12 ***\n",
"month1999-01 -0.07634351 0.00755590 -10.1038 < 2.2e-16 ***\n",
"month1999-02 -0.08337995 0.00767498 -10.8639 < 2.2e-16 ***\n",
"month1999-03 -0.09515700 0.00755462 -12.5959 < 2.2e-16 ***\n",
"month1999-04 -0.09434438 0.00764627 -12.3386 < 2.2e-16 ***\n",
"month1999-05 -0.08885657 0.00794162 -11.1887 < 2.2e-16 ***\n",
"month1999-06 -0.07878138 0.00792706 -9.9383 < 2.2e-16 ***\n",
"month1999-07 -0.07209248 0.00852392 -8.4577 < 2.2e-16 ***\n",
"month1999-08 -0.02739142 0.00955472 -2.8668 0.0041774 ** \n",
"flat_type4 ROOM 0.31627785 0.01411696 22.4041 < 2.2e-16 ***\n",
"flat_type5 ROOM 0.50825044 0.03053170 16.6466 < 2.2e-16 ***\n",
"flat_typeEXECUTIVE 0.80381204 0.04901274 16.4001 < 2.2e-16 ***\n",
"flat_typeMULTI GENERATION 0.79232060 0.04728827 16.7551 < 2.2e-16 ***\n",
"block202 0.02031461 0.01212923 1.6748 0.0940756 . \n",
"block203 0.01535320 0.01126712 1.3627 0.1731005 \n",
"block204 0.01598661 0.01834303 0.8715 0.3835360 \n",
"block208 0.00614220 0.01095902 0.5605 0.5752038 \n",
"block302 -0.00644919 0.01282367 -0.5029 0.6150646 \n",
"block303 -0.02924451 0.01206636 -2.4236 0.0154287 * \n",
"block304 -0.03938258 0.00950634 -4.1428 3.533e-05 ***\n",
"block305 -0.04151404 0.01151816 -3.6042 0.0003185 ***\n",
"block306 -0.04260098 0.01185180 -3.5945 0.0003306 ***\n",
"block320 -0.03611676 0.00993713 -3.6345 0.0002835 ***\n",
"block321 -0.04245646 0.01136517 -3.7357 0.0001909 ***\n",
"block322 0.00896655 0.01723755 0.5202 0.6029822 \n",
"block323 -0.02667414 0.01270702 -2.0992 0.0358914 * \n",
"block324 0.01297639 0.02230700 0.5817 0.5608032 \n",
"block325 0.01110774 0.01979416 0.5612 0.5747313 \n",
"block326 -0.00540503 0.01994240 -0.2710 0.7863865 \n",
"block327 -0.04285597 0.01086335 -3.9450 8.175e-05 ***\n",
"block345 -0.06167299 0.01183595 -5.2106 2.018e-07 ***\n",
"block346 -0.04104331 0.01092467 -3.7569 0.0001755 ***\n",
"block349 -0.05107037 0.01101614 -4.6360 3.715e-06 ***\n",
"block350 -0.04710351 0.00997882 -4.7203 2.470e-06 ***\n",
"block350A 0.04485397 0.02671782 1.6788 0.0933016 . \n",
"block351 0.02020711 0.02220032 0.9102 0.3627860 \n",
"block352 0.02343275 0.02234203 1.0488 0.2943515 \n",
"block353 -0.04941693 0.01449032 -3.4103 0.0006580 ***\n",
"block354 -0.06576848 0.01622982 -4.0523 5.209e-05 ***\n",
"block355 0.02410229 0.02606920 0.9246 0.3552792 \n",
"block355A 0.02274732 0.02726953 0.8342 0.4042584 \n",
"block356 0.03191751 0.02020065 1.5800 0.1142139 \n",
"block415 0.00838724 0.03486385 0.2406 0.8099050 \n",
"block416 0.00474722 0.03598392 0.1319 0.8950522 \n",
"block602 -0.10274229 0.03822042 -2.6882 0.0072273 ** \n",
"block603 -0.11315161 0.03914736 -2.8904 0.0038770 ** \n",
"block604 -0.04414522 0.02007513 -2.1990 0.0279591 * \n",
"block605 -0.08952829 0.03300177 -2.7128 0.0067118 ** \n",
"block607 -0.01886439 0.01216833 -1.5503 0.1211854 \n",
"block609 -0.02400298 0.01408103 -1.7046 0.0883736 . \n",
"block610 -0.02070475 0.01275452 -1.6233 0.1046318 \n",
"block611 0.02378349 0.02101231 1.1319 0.2577800 \n",
"block612 -0.00801292 0.01272354 -0.6298 0.5288952 \n",
"block613 -0.02264233 0.01238811 -1.8277 0.0676934 . \n",
"block614 0.02906888 0.01789468 1.6244 0.1043935 \n",
"block615 -0.02476604 0.01220163 -2.0297 0.0424780 * \n",
"block616 0.02723425 0.03437070 0.7924 0.4282129 \n",
"block617 -0.01687995 0.01031241 -1.6369 0.1017721 \n",
"block618 0.02690804 0.04053970 0.6637 0.5069078 \n",
"block619 0.00501309 0.01540015 0.3255 0.7448103 \n",
"block620 0.00041034 0.01159280 0.0354 0.9717663 \n",
"block621 -0.00204494 0.01133643 -0.1804 0.8568621 \n",
"block622 0.00878156 0.01046442 0.8392 0.4014383 \n",
"block624 -0.00932081 0.01076383 -0.8659 0.3865980 \n",
"block625 0.00317996 0.01112893 0.2857 0.7751000 \n",
"block626 -0.00111355 0.01294530 -0.0860 0.9314570 \n",
"block627 -0.01283129 0.01023120 -1.2541 0.2098978 \n",
"block628 -0.01001587 0.00980420 -1.0216 0.3070627 \n",
"block629 -0.00262521 0.01258483 -0.2086 0.8347750 \n",
"block630 -0.02649918 0.01059341 -2.5015 0.0124241 * \n",
"block631 0.00699961 0.06190409 0.1131 0.9099817 \n",
"block632 -0.00558772 0.01275502 -0.4381 0.6613622 \n",
"block633 -0.01108867 0.01896720 -0.5846 0.5588480 \n",
"block633A 0.01848661 0.03455311 0.5350 0.5926783 \n",
"block634 -0.04831848 0.01073513 -4.5010 7.040e-06 ***\n",
"block635 -0.02191911 0.01340481 -1.6352 0.1021259 \n",
"block636 -0.02639167 0.01096283 -2.4074 0.0161317 * \n",
"block636A -0.04627734 0.03460688 -1.3372 0.1812560 \n",
"block637 -0.04812069 0.01269266 -3.7912 0.0001531 ***\n",
"block637A 0.04052747 0.04209593 0.9627 0.3357604 \n",
"block638 -0.02799849 0.01261434 -2.2196 0.0265271 * \n",
"block639 -0.12227256 0.03915420 -3.1228 0.0018093 ** \n",
"block640 -0.04902009 0.01498289 -3.2717 0.0010818 ** \n",
"block640A -0.07611266 0.01485612 -5.1233 3.205e-07 ***\n",
"block641 -0.06110844 0.01886223 -3.2397 0.0012104 ** \n",
"block642 -0.11551603 0.04383908 -2.6350 0.0084599 ** \n",
"block643 -0.06297704 0.03958961 -1.5907 0.1117792 \n",
"block644 -0.11386855 0.03351088 -3.3980 0.0006884 ***\n",
"block645 -0.06519372 0.01708347 -3.8162 0.0001385 ***\n",
"block645A -0.02536091 0.02897721 -0.8752 0.3815388 \n",
"block646 -0.10436484 0.03854230 -2.7078 0.0068141 ** \n",
"block647 -0.09633290 0.03865283 -2.4923 0.0127505 * \n",
"block650 -0.14998908 0.01764589 -8.4999 < 2.2e-16 ***\n",
"block651 -0.12175498 0.03981197 -3.0583 0.0022473 ** \n",
"block652 -0.05450395 0.02541735 -2.1444 0.0320896 * \n",
"block653 -0.11536278 0.03878626 -2.9743 0.0029614 ** \n",
"block654 -0.07846971 0.01941671 -4.0413 5.457e-05 ***\n",
"block655 -0.12148139 0.03869231 -3.1397 0.0017089 ** \n",
"block656 -0.15687540 0.05013332 -3.1292 0.0017710 ** \n",
"block657 -0.12477417 0.03862558 -3.2304 0.0012507 ** \n",
"block658 -0.12608075 0.03838816 -3.2844 0.0010347 ** \n",
"block659 -0.09806072 0.03895902 -2.5170 0.0118904 * \n",
"block660 -0.12567482 0.03844069 -3.2693 0.0010911 ** \n",
"block661 -0.09572901 0.02375281 -4.0302 5.721e-05 ***\n",
"block662 -0.04351739 0.01300829 -3.3454 0.0008326 ***\n",
"block663 -0.03240276 0.01231453 -2.6313 0.0085533 ** \n",
"block663A 0.04654718 0.06218649 0.7485 0.4542155 \n",
"block664 -0.00051020 0.03816038 -0.0134 0.9893336 \n",
"block664A -0.01538315 0.03578340 -0.4299 0.6673042 \n",
"block665 0.03005437 0.04058117 0.7406 0.4589987 \n",
"block666 0.02941191 0.02276970 1.2917 0.1965630 \n",
"block666A -0.04984724 0.02476586 -2.0127 0.0442372 * \n",
"block744 0.02097597 0.02174832 0.9645 0.3348849 \n",
"block745 0.03276006 0.01217269 2.6913 0.0071601 ** \n",
"block746 0.01294204 0.01557910 0.8307 0.4061964 \n",
"block747 -0.06005406 0.02643344 -2.2719 0.0231680 * \n",
"block748 0.03358536 0.02407348 1.3951 0.1630904 \n",
"block749 0.04734899 0.01796074 2.6362 0.0084289 ** \n",
"block750 0.02245568 0.01356962 1.6548 0.0980668 . \n",
"block751 0.02385857 0.01454810 1.6400 0.1011215 \n",
"block752 0.01015594 0.01463055 0.6942 0.4876394 \n",
"block753 -0.00655239 0.02557239 -0.2562 0.7977927 \n",
"block754 -0.01539714 0.01719041 -0.8957 0.3704992 \n",
"block755 -0.01812056 0.01294566 -1.3997 0.1617016 \n",
"block756 -0.02276020 0.01777397 -1.2805 0.2004626 \n",
"block757 -0.03045267 0.01432078 -2.1265 0.0335513 * \n",
"block758 -0.04242758 0.01359989 -3.1197 0.0018287 ** \n",
"block759 -0.01544778 0.01798425 -0.8590 0.3904352 \n",
"block760 -0.02598575 0.01004961 -2.5857 0.0097667 ** \n",
"block761 -0.01650259 0.01516914 -1.0879 0.2767300 \n",
"block762 -0.02775797 0.01978450 -1.4030 0.1607226 \n",
"block763 -0.01137593 0.01904323 -0.5974 0.5503060 \n",
"block764 -0.02325742 0.01847523 -1.2588 0.2081916 \n",
"block765 -0.02636226 0.01734033 -1.5203 0.1285517 \n",
"block766 -0.03038549 0.01674867 -1.8142 0.0697531 . \n",
"block767 0.03714258 0.02119047 1.7528 0.0797460 . \n",
"block768 -0.01195614 0.01921888 -0.6221 0.5339239 \n",
"block769 -0.09263373 0.01277097 -7.2535 5.230e-13 ***\n",
"block770 -0.02815907 0.01227979 -2.2931 0.0219145 * \n",
"block771 -0.03577295 0.01682829 -2.1258 0.0336100 * \n",
"block772 -0.03399701 0.01775566 -1.9147 0.0556304 . \n",
"block773 0.00561946 0.01614190 0.3481 0.7277696 \n",
"block775 -0.05145174 0.01279072 -4.0226 5.908e-05 ***\n",
"block776 -0.04592189 0.01639436 -2.8011 0.0051281 ** \n",
"block777 -0.00650341 0.04677470 -0.1390 0.8894309 \n",
"block778 -0.03486750 0.01388304 -2.5115 0.0120770 * \n",
"block780 -0.03342303 0.02055737 -1.6258 0.1040955 \n",
"block781 -0.05125349 0.01032417 -4.9644 7.303e-07 ***\n",
"block782 -0.04260611 0.01765090 -2.4138 0.0158498 * \n",
"block783 -0.03189247 0.00983978 -3.2412 0.0012043 ** \n",
"block784 -0.03580119 0.01363308 -2.6261 0.0086850 ** \n",
"block785 -0.02579473 0.01412949 -1.8256 0.0680173 . \n",
"block786 -0.00393058 0.01385428 -0.2837 0.7766546 \n",
"block787 -0.00450113 0.01228899 -0.3663 0.7141887 \n",
"block788 -0.01456026 0.01423716 -1.0227 0.3065404 \n",
"block789 -0.00218717 0.03370193 -0.0649 0.9482602 \n",
"block790 -0.01472747 0.01262647 -1.1664 0.2435530 \n",
"block791 -0.01227903 0.02078773 -0.5907 0.5547781 \n",
"block792 0.03304550 0.02238123 1.4765 0.1399263 \n",
"block796 -0.00634685 0.01148208 -0.5528 0.5804710 \n",
"block796A -0.01746783 0.02855328 -0.6118 0.5407443 \n",
"block797 0.08491103 0.03391199 2.5039 0.0123408 * \n",
"block855 0.00207455 0.01652797 0.1255 0.9001231 \n",
"block858 -0.00088158 0.01065577 -0.0827 0.9340703 \n",
"block859 -0.02004783 0.01249807 -1.6041 0.1088103 \n",
"block860 -0.01330932 0.01187130 -1.1211 0.2623268 \n",
"block861 -0.04652004 0.01340654 -3.4700 0.0005284 ***\n",
"block862 -0.03209800 0.01104890 -2.9051 0.0037002 ** \n",
"block863 -0.00994981 0.00989218 -1.0058 0.3145861 \n",
"block926 0.00748749 0.01407109 0.5321 0.5946860 \n",
"block927 -0.00772744 0.03495671 -0.2211 0.8250638 \n",
"block928 0.00976303 0.01941476 0.5029 0.6150979 \n",
"block930 -0.00900058 0.02345485 -0.3837 0.7011997 \n",
"block931 -0.01667097 0.02028361 -0.8219 0.4112072 \n",
"block932 0.02426514 0.02550875 0.9512 0.3415605 \n",
"storey_range04 TO 06 0.02769985 0.00244403 11.3337 < 2.2e-16 ***\n",
"storey_range07 TO 09 0.03955470 0.00245959 16.0818 < 2.2e-16 ***\n",
"storey_range10 TO 12 0.04753662 0.00264133 17.9972 < 2.2e-16 ***\n",
"storey_range13 TO 15 0.05055155 0.00816972 6.1877 6.995e-10 ***\n",
"floor_area_sqm 0.00544719 0.00045885 11.8715 < 2.2e-16 ***\n",
"flat_modelIMPROVED 0.19505368 0.01728779 11.2827 < 2.2e-16 ***\n",
"flat_modelMAISONETTE -0.01454225 0.00791668 -1.8369 0.0663285 . \n",
"flat_modelMODEL A 0.19167339 0.00960490 19.9558 < 2.2e-16 ***\n",
"flat_modelNEW GENERATION 0.13687462 0.01214363 11.2713 < 2.2e-16 ***\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": 9,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 619, 2713\"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 619, 2713\"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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\nJJNJQf8HX3dPD5sjM6oAAAAASUVORK5CYII=",
"text/plain": [
"Plot with title \"\""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"par(mfrow = c(2, 2))\n",
"plot(fit1)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"## Model 2"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data2 <- read.csv('Model2polyclinic.csv')"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t3011 obs. of 16 variables:\n",
" $ month : Factor w/ 24 levels \"1997-10\",\"1997-11\",..: 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\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ block : Factor w/ 165 levels \"201\",\"202\",\"203\",..: 103 103 5 5 134 55 57 46 51 7 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 10 10 8 8 2 9 9 7 7 5 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 4 4 2 4 3 4 1 3 3 ...\n",
" $ floor_area_sqm : int 67 67 67 67 74 73 73 73 73 74 ...\n",
" $ flat_model : Factor w/ 7 levels \"APARTMENT\",\"IMPROVED\",..: 6 6 6 6 4 4 4 4 4 4 ...\n",
" $ Age : int 13 13 12 12 8 9 9 9 10 9 ...\n",
" $ lease_commence_date: int 1984 1984 1985 1985 1989 1988 1988 1988 1987 1988 ...\n",
" $ resale_price : int 180000 182500 196000 185000 190000 196000 195000 177000 225000 193000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 0 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",
" $ Period3 : 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": 13,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data2 <- data2 %>% mutate(ln_resale_price = log(resale_price))"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t3011 obs. of 17 variables:\n",
" $ month : Factor w/ 24 levels \"1997-10\",\"1997-11\",..: 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\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ block : Factor w/ 165 levels \"201\",\"202\",\"203\",..: 103 103 5 5 134 55 57 46 51 7 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 10 10 8 8 2 9 9 7 7 5 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 4 4 2 4 3 4 1 3 3 ...\n",
" $ floor_area_sqm : int 67 67 67 67 74 73 73 73 73 74 ...\n",
" $ flat_model : Factor w/ 7 levels \"APARTMENT\",\"IMPROVED\",..: 6 6 6 6 4 4 4 4 4 4 ...\n",
" $ Age : int 13 13 12 12 8 9 9 9 10 9 ...\n",
" $ lease_commence_date: int 1984 1984 1985 1985 1989 1988 1988 1988 1987 1988 ...\n",
" $ resale_price : int 180000 182500 196000 185000 190000 196000 195000 177000 225000 193000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 0 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",
" $ Period3 : 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 12.1 12.1 12.2 12.1 12.2 ...\n"
]
}
],
"source": [
"str(data2)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\n",
"t test of coefficients:\n",
"\n",
" Estimate Std. Error t value Pr(>|t|) \n",
"(Intercept) 11.53007149 0.05622288 205.0779 < 2.2e-16 ***\n",
"Treatment 0.08585780 0.03677011 2.3350 0.0196141 * \n",
"Period2 -0.25464655 0.01385528 -18.3790 < 2.2e-16 ***\n",
"Treatment_Period2 -0.00477451 0.00485459 -0.9835 0.3254442 \n",
"Period3 -0.15732076 0.01521089 -10.3426 < 2.2e-16 ***\n",
"Treatment_Period3 -0.01707854 0.00590034 -2.8945 0.0038269 ** \n",
"Age 0.00077307 0.00594334 0.1301 0.8965179 \n",
"month1997-11 -0.01644933 0.00820909 -2.0038 0.0451879 * \n",
"month1997-12 -0.03566521 0.00812119 -4.3916 1.167e-05 ***\n",
"month1998-01 -0.05852711 0.00932158 -6.2787 3.944e-10 ***\n",
"month1998-02 -0.07762658 0.00938327 -8.2729 < 2.2e-16 ***\n",
"month1998-03 -0.09752280 0.00964267 -10.1137 < 2.2e-16 ***\n",
"month1998-04 -0.13712619 0.00906661 -15.1243 < 2.2e-16 ***\n",
"month1998-05 -0.14698890 0.00946066 -15.5369 < 2.2e-16 ***\n",
"month1998-06 -0.15362641 0.00902442 -17.0234 < 2.2e-16 ***\n",
"month1998-07 -0.16762872 0.00911224 -18.3960 < 2.2e-16 ***\n",
"month1998-08 -0.18291535 0.00959611 -19.0614 < 2.2e-16 ***\n",
"month1998-09 -0.18828300 0.00908230 -20.7308 < 2.2e-16 ***\n",
"month1998-10 0.05483322 0.00772223 7.1007 1.566e-12 ***\n",
"month1998-11 0.03742879 0.00722709 5.1790 2.389e-07 ***\n",
"month1998-12 0.02668800 0.00771541 3.4591 0.0005502 ***\n",
"month1999-01 0.01924288 0.00418906 4.5936 4.549e-06 ***\n",
"month1999-02 0.01194247 0.00444008 2.6897 0.0071940 ** \n",
"month1999-04 -0.09432721 0.00763320 -12.3575 < 2.2e-16 ***\n",
"month1999-05 -0.08917010 0.00792471 -11.2522 < 2.2e-16 ***\n",
"month1999-06 -0.07891816 0.00790675 -9.9811 < 2.2e-16 ***\n",
"month1999-07 -0.07206102 0.00851433 -8.4635 < 2.2e-16 ***\n",
"month1999-08 -0.02741423 0.00952367 -2.8785 0.0040255 ** \n",
"flat_type4 ROOM 0.31716783 0.01412984 22.4467 < 2.2e-16 ***\n",
"flat_type5 ROOM 0.51004876 0.03055394 16.6934 < 2.2e-16 ***\n",
"flat_typeEXECUTIVE 0.80679739 0.04894770 16.4828 < 2.2e-16 ***\n",
"flat_typeMULTI GENERATION 0.79336416 0.04728787 16.7773 < 2.2e-16 ***\n",
"block202 0.02019867 0.01211468 1.6673 0.0955684 . \n",
"block203 0.01555392 0.01122984 1.3851 0.1661462 \n",
"block204 0.01608217 0.01831929 0.8779 0.3800828 \n",
"block208 0.00615189 0.01096100 0.5613 0.5746702 \n",
"block302 -0.00684354 0.01288106 -0.5313 0.5952617 \n",
"block303 -0.02932932 0.01205627 -2.4327 0.0150487 * \n",
"block304 -0.03936823 0.00953209 -4.1301 3.732e-05 ***\n",
"block305 -0.04154729 0.01157643 -3.5890 0.0003377 ***\n",
"block306 -0.04249747 0.01189473 -3.5728 0.0003591 ***\n",
"block320 -0.03602541 0.00996310 -3.6159 0.0003046 ***\n",
"block321 -0.04258635 0.01140184 -3.7350 0.0001914 ***\n",
"block322 0.00940610 0.01723784 0.5457 0.5853389 \n",
"block323 -0.02652639 0.01274585 -2.0812 0.0375080 * \n",
"block324 0.01245460 0.02236290 0.5569 0.5776188 \n",
"block325 0.01036272 0.01983041 0.5226 0.6013168 \n",
"block326 -0.00626203 0.01998679 -0.3133 0.7540695 \n",
"block327 -0.04284442 0.01089711 -3.9317 8.638e-05 ***\n",
"block345 -0.06172887 0.01182321 -5.2210 1.910e-07 ***\n",
"block346 -0.04132696 0.01098327 -3.7627 0.0001715 ***\n",
"block349 -0.05119339 0.01101542 -4.6474 3.516e-06 ***\n",
"block350 -0.04715678 0.01000399 -4.7138 2.550e-06 ***\n",
"block350A 0.04445017 0.02667648 1.6663 0.0957716 . \n",
"block351 0.01962437 0.02226673 0.8813 0.3782139 \n",
"block352 0.02292121 0.02239561 1.0235 0.3061745 \n",
"block353 -0.04950976 0.01453909 -3.4053 0.0006702 ***\n",
"block354 -0.06597271 0.01628431 -4.0513 5.231e-05 ***\n",
"block355 0.02342070 0.02609505 0.8975 0.3695212 \n",
"block355A 0.02231423 0.02736862 0.8153 0.4149573 \n",
"block356 0.03131791 0.02022789 1.5483 0.1216738 \n",
"block415 0.00767831 0.03505094 0.2191 0.8266181 \n",
"block416 0.00439189 0.03617151 0.1214 0.9033682 \n",
"block602 -0.10253118 0.03845528 -2.6662 0.0077144 ** \n",
"block603 -0.11366393 0.03928472 -2.8933 0.0038411 ** \n",
"block604 -0.04454290 0.01995785 -2.2318 0.0257035 * \n",
"block605 -0.08826660 0.03327429 -2.6527 0.0080301 ** \n",
"block607 -0.01909847 0.01217833 -1.5682 0.1169392 \n",
"block609 -0.02373101 0.01412867 -1.6796 0.0931396 . \n",
"block610 -0.02046699 0.01281011 -1.5977 0.1102175 \n",
"block611 0.02313316 0.02102226 1.1004 0.2712468 \n",
"block612 -0.00752242 0.01280098 -0.5876 0.5568185 \n",
"block613 -0.02278773 0.01239828 -1.8380 0.0661717 . \n",
"block614 0.02869071 0.01784688 1.6076 0.1080344 \n",
"block615 -0.02476997 0.01224373 -2.0231 0.0431601 * \n",
"block616 0.02652452 0.03457330 0.7672 0.4430291 \n",
"block617 -0.01674980 0.01034953 -1.6184 0.1056863 \n",
"block618 0.02634628 0.04075550 0.6464 0.5180427 \n",
"block619 0.00513088 0.01536560 0.3339 0.7384649 \n",
"block620 0.00038443 0.01163026 0.0331 0.9736334 \n",
"block621 -0.00214820 0.01135467 -0.1892 0.8499567 \n",
"block622 0.00888253 0.01050956 0.8452 0.3980790 \n",
"block624 -0.00924184 0.01078641 -0.8568 0.3916263 \n",
"block625 0.00305483 0.01110845 0.2750 0.7833358 \n",
"block626 -0.00114694 0.01295629 -0.0885 0.9294666 \n",
"block627 -0.01281390 0.01027546 -1.2470 0.2124874 \n",
"block628 -0.01005920 0.00984517 -1.0217 0.3069923 \n",
"block629 -0.00270219 0.01258056 -0.2148 0.8299459 \n",
"block630 -0.02651723 0.01060266 -2.5010 0.0124409 * \n",
"block631 0.00578124 0.06225917 0.0929 0.9260233 \n",
"block632 -0.00506104 0.01268638 -0.3989 0.6899717 \n",
"block633 -0.00918873 0.01893059 -0.4854 0.6274371 \n",
"block633A 0.01794201 0.03482085 0.5153 0.6064076 \n",
"block634 -0.04837270 0.01074211 -4.5031 6.970e-06 ***\n",
"block635 -0.02181574 0.01340540 -1.6274 0.1037678 \n",
"block636 -0.02655058 0.01092203 -2.4309 0.0151227 * \n",
"block636A -0.04607989 0.03475712 -1.3258 0.1850243 \n",
"block637 -0.04807921 0.01270423 -3.7845 0.0001572 ***\n",
"block637A 0.03947553 0.04242939 0.9304 0.3522534 \n",
"block638 -0.02782891 0.01260587 -2.2076 0.0273517 * \n",
"block639 -0.12100207 0.03927689 -3.0807 0.0020848 ** \n",
"block640 -0.04879272 0.01512646 -3.2257 0.0012713 ** \n",
"block640A -0.07558578 0.01500816 -5.0363 5.046e-07 ***\n",
"block641 -0.06101855 0.01900556 -3.2106 0.0013397 ** \n",
"block642 -0.11543633 0.04409228 -2.6181 0.0088906 ** \n",
"block643 -0.06451461 0.03959534 -1.6293 0.1033514 \n",
"block644 -0.11257005 0.03376306 -3.3341 0.0008668 ***\n",
"block645 -0.06626030 0.01717452 -3.8581 0.0001169 ***\n",
"block645A -0.02796328 0.03053091 -0.9159 0.3597978 \n",
"block646 -0.10329226 0.03879342 -2.6626 0.0077977 ** \n",
"block647 -0.09561180 0.03889412 -2.4583 0.0140212 * \n",
"block650 -0.14341487 0.01784144 -8.0383 1.329e-15 ***\n",
"block651 -0.12176484 0.04014647 -3.0330 0.0024434 ** \n",
"block652 -0.05284376 0.02583840 -2.0452 0.0409318 * \n",
"block653 -0.11394895 0.03908308 -2.9156 0.0035787 ** \n",
"block654 -0.07796733 0.02010509 -3.8780 0.0001077 ***\n",
"block655 -0.12071121 0.03893699 -3.1002 0.0019533 ** \n",
"block656 -0.15387143 0.05033096 -3.0572 0.0022553 ** \n",
"block657 -0.12332392 0.03883205 -3.1758 0.0015103 ** \n",
"block658 -0.12486567 0.03854790 -3.2392 0.0012125 ** \n",
"block659 -0.09393700 0.03939864 -2.3843 0.0171791 * \n",
"block660 -0.12484766 0.03869655 -3.2263 0.0012683 ** \n",
"block661 -0.09631141 0.02345276 -4.1066 4.130e-05 ***\n",
"block662 -0.04347344 0.01304897 -3.3316 0.0008748 ***\n",
"block663 -0.03210805 0.01238517 -2.5925 0.0095787 ** \n",
"block663A 0.04476655 0.06260635 0.7150 0.4746388 \n",
"block664 -0.00106149 0.03838675 -0.0277 0.9779412 \n",
"block664A -0.01681603 0.03613185 -0.4654 0.6416757 \n",
"block665 0.02980511 0.04081872 0.7302 0.4653397 \n",
"block666 0.03148864 0.02281070 1.3804 0.1675633 \n",
"block666A -0.04992648 0.02504985 -1.9931 0.0463488 * \n",
"block744 0.02162163 0.02172652 0.9952 0.3197383 \n",
"block745 0.03291940 0.01216551 2.7060 0.0068519 ** \n",
"block746 0.01317568 0.01557054 0.8462 0.3975174 \n",
"block747 -0.05986274 0.02661620 -2.2491 0.0245828 * \n",
"block748 0.03436688 0.02405389 1.4287 0.1531886 \n",
"block749 0.04742528 0.01793474 2.6443 0.0082310 ** \n",
"block750 0.02251538 0.01356340 1.6600 0.0970242 . \n",
"block751 0.02381557 0.01453607 1.6384 0.1014550 \n",
"block752 0.01035505 0.01465738 0.7065 0.4799521 \n",
"block753 -0.00566669 0.02552463 -0.2220 0.8243234 \n",
"block754 -0.01504480 0.01727082 -0.8711 0.3837683 \n",
"block755 -0.01794388 0.01299131 -1.3812 0.1673205 \n",
"block756 -0.02253579 0.01785005 -1.2625 0.2068718 \n",
"block757 -0.03022345 0.01435838 -2.1049 0.0353856 * \n",
"block758 -0.04197002 0.01362584 -3.0802 0.0020888 ** \n",
"block759 -0.01496163 0.01805318 -0.8288 0.4073147 \n",
"block760 -0.02581012 0.01008651 -2.5589 0.0105531 * \n",
"block761 -0.01611045 0.01527344 -1.0548 0.2916069 \n",
"block762 -0.02758545 0.01985122 -1.3896 0.1647576 \n",
"block763 -0.01106098 0.01909249 -0.5793 0.5624086 \n",
"block764 -0.02303155 0.01853343 -1.2427 0.2140811 \n",
"block765 -0.02616614 0.01741742 -1.5023 0.1331328 \n",
"block766 -0.03018068 0.01682715 -1.7936 0.0729894 . \n",
"block767 0.03802998 0.02118459 1.7952 0.0727338 . \n",
"block768 -0.01148565 0.01931215 -0.5947 0.5520673 \n",
"block769 -0.09196401 0.01275018 -7.2128 7.020e-13 ***\n",
"block770 -0.02790471 0.01233261 -2.2627 0.0237318 * \n",
"block771 -0.03539370 0.01690318 -2.0939 0.0363577 * \n",
"block772 -0.03362818 0.01781339 -1.8878 0.0591554 . \n",
"block773 0.00584635 0.01615516 0.3619 0.7174635 \n",
"block775 -0.05109159 0.01285253 -3.9752 7.209e-05 ***\n",
"block776 -0.04548456 0.01647565 -2.7607 0.0058050 ** \n",
"block777 -0.00642598 0.04675525 -0.1374 0.8906940 \n",
"block778 -0.03495536 0.01395373 -2.5051 0.0122982 * \n",
"block780 -0.03324175 0.02051877 -1.6201 0.1053304 \n",
"block781 -0.05121039 0.01035710 -4.9445 8.084e-07 ***\n",
"block782 -0.04249706 0.01771863 -2.3984 0.0165300 * \n",
"block783 -0.03179694 0.00985984 -3.2249 0.0012746 ** \n",
"block784 -0.03574733 0.01361780 -2.6250 0.0087107 ** \n",
"block785 -0.02572109 0.01413581 -1.8196 0.0689310 . \n",
"block786 -0.00369753 0.01382521 -0.2674 0.7891434 \n",
"block787 -0.00433314 0.01232586 -0.3515 0.7252032 \n",
"block788 -0.01428399 0.01428681 -0.9998 0.3174920 \n",
"block789 -0.00192584 0.03390368 -0.0568 0.9547060 \n",
"block790 -0.01450152 0.01265617 -1.1458 0.2519728 \n",
"block791 -0.01302713 0.02074906 -0.6278 0.5301584 \n",
"block792 0.03286213 0.02235778 1.4698 0.1417198 \n",
"block796 -0.00579833 0.01146802 -0.5056 0.6131709 \n",
"block796A -0.01710035 0.02832024 -0.6038 0.5460115 \n",
"block797 0.08453696 0.03405184 2.4826 0.0131009 * \n",
"block855 0.00226586 0.01653678 0.1370 0.8910252 \n",
"block858 -0.00068589 0.01074023 -0.0639 0.9490852 \n",
"block859 -0.02009328 0.01256078 -1.5997 0.1097811 \n",
"block860 -0.01356864 0.01189685 -1.1405 0.2541657 \n",
"block861 -0.04652770 0.01344804 -3.4598 0.0005486 ***\n",
"block862 -0.03214605 0.01108760 -2.8993 0.0037692 ** \n",
"block863 -0.00975893 0.00990936 -0.9848 0.3247973 \n",
"block926 0.00758736 0.01424438 0.5327 0.5943137 \n",
"block927 -0.00756174 0.03504053 -0.2158 0.8291594 \n",
"block928 0.01239653 0.02020935 0.6134 0.5396577 \n",
"block930 -0.00597114 0.02355293 -0.2535 0.7998850 \n",
"block931 -0.01804468 0.02023401 -0.8918 0.3725769 \n",
"block932 0.02676639 0.02544002 1.0521 0.2928271 \n",
"storey_range04 TO 06 0.02769956 0.00244126 11.3464 < 2.2e-16 ***\n",
"storey_range07 TO 09 0.03964574 0.00245696 16.1361 < 2.2e-16 ***\n",
"storey_range10 TO 12 0.04754808 0.00263994 18.0111 < 2.2e-16 ***\n",
"storey_range13 TO 15 0.04955306 0.00821532 6.0318 1.834e-09 ***\n",
"floor_area_sqm 0.00542015 0.00045909 11.8064 < 2.2e-16 ***\n",
"flat_modelIMPROVED 0.19504663 0.01734573 11.2446 < 2.2e-16 ***\n",
"flat_modelMAISONETTE -0.01426104 0.00791859 -1.8010 0.0718169 . \n",
"flat_modelMODEL A 0.19218992 0.00961946 19.9793 < 2.2e-16 ***\n",
"flat_modelNEW GENERATION 0.13750732 0.01223248 11.2412 < 2.2e-16 ***\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": 16,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 619, 2713, 2720\"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 619, 2713, 2720\"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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\nSUEGksmkoP8DHaBNgMkT8lgAAAAASUVORK5CYII=",
"text/plain": [
"Plot with title \"\""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"par(mfrow = c(2, 2))\n",
"plot(fit2)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"## Model 3"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data3 <- read.csv('Model3polyclinic.csv')\n"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t3182 obs. of 16 variables:\n",
" $ month : Factor w/ 27 levels \"1997-10\",\"1997-11\",..: 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/ 6 levels \"3 ROOM\",\"4 ROOM\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ block : Factor w/ 166 levels \"201\",\"202\",\"203\",..: 103 103 5 5 134 55 57 46 51 7 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 10 10 8 8 2 9 9 7 7 5 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 4 4 2 4 3 4 1 3 3 ...\n",
" $ floor_area_sqm : int 67 67 67 67 74 73 73 73 73 74 ...\n",
" $ flat_model : Factor w/ 14 levels \"Apartment\",\"APARTMENT\",..: 12 12 12 12 8 8 8 8 8 8 ...\n",
" $ Age : int 13 13 12 12 8 9 9 9 10 9 ...\n",
" $ lease_commence_date: int 1984 1984 1985 1985 1989 1988 1988 1988 1987 1988 ...\n",
" $ resale_price : int 180000 182500 196000 185000 190000 196000 195000 177000 225000 193000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 0 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",
" $ Period3 : 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": 20,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"data3 <- data3 %>% mutate(ln_resale_price = log(resale_price))"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"'data.frame':\t3182 obs. of 17 variables:\n",
" $ month : Factor w/ 27 levels \"1997-10\",\"1997-11\",..: 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/ 6 levels \"3 ROOM\",\"4 ROOM\",..: 1 1 1 1 1 1 1 1 1 1 ...\n",
" $ block : Factor w/ 166 levels \"201\",\"202\",\"203\",..: 103 103 5 5 134 55 57 46 51 7 ...\n",
" $ street_name : Factor w/ 10 levels \"YISHUN AVE 11\",..: 10 10 8 8 2 9 9 7 7 5 ...\n",
" $ storey_range : Factor w/ 5 levels \"01 TO 03\",\"04 TO 06\",..: 4 4 4 2 4 3 4 1 3 3 ...\n",
" $ floor_area_sqm : int 67 67 67 67 74 73 73 73 73 74 ...\n",
" $ flat_model : Factor w/ 14 levels \"Apartment\",\"APARTMENT\",..: 12 12 12 12 8 8 8 8 8 8 ...\n",
" $ Age : int 13 13 12 12 8 9 9 9 10 9 ...\n",
" $ lease_commence_date: int 1984 1984 1985 1985 1989 1988 1988 1988 1987 1988 ...\n",
" $ resale_price : int 180000 182500 196000 185000 190000 196000 195000 177000 225000 193000 ...\n",
" $ Treatment : int 0 0 0 0 0 0 0 0 0 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",
" $ Period3 : 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 12.1 12.1 12.2 12.1 12.2 ...\n"
]
}
],
"source": [
"str(data3)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\n",
"t test of coefficients:\n",
"\n",
" Estimate Std. Error t value Pr(>|t|) \n",
"(Intercept) 11.53667707 0.05497587 209.8498 < 2.2e-16 ***\n",
"Treatment 0.08191121 0.03565610 2.2973 0.0216734 * \n",
"Period2 -0.15481970 0.01496063 -10.3485 < 2.2e-16 ***\n",
"Treatment_Period2 -0.00994018 0.00435916 -2.2803 0.0226606 * \n",
"Period3 -0.10365940 0.02094670 -4.9487 7.887e-07 ***\n",
"Treatment_Period3 0.00571412 0.00829664 0.6887 0.4910491 \n",
"Age -0.00065076 0.00582194 -0.1118 0.9110071 \n",
"month1997-11 -0.01591471 0.00819477 -1.9421 0.0522247 . \n",
"month1997-12 -0.03580654 0.00809300 -4.4244 1.002e-05 ***\n",
"month1998-01 -0.05674118 0.00918998 -6.1742 7.553e-10 ***\n",
"month1998-02 -0.07583302 0.00921032 -8.2335 2.692e-16 ***\n",
"month1998-03 -0.09604211 0.00950973 -10.0994 < 2.2e-16 ***\n",
"month1998-04 -0.13519717 0.00893448 -15.1321 < 2.2e-16 ***\n",
"month1998-05 -0.14489609 0.00934097 -15.5119 < 2.2e-16 ***\n",
"month1998-06 -0.15188519 0.00888470 -17.0951 < 2.2e-16 ***\n",
"month1998-07 -0.16558083 0.00897855 -18.4418 < 2.2e-16 ***\n",
"month1998-08 -0.18100036 0.00947460 -19.1037 < 2.2e-16 ***\n",
"month1998-09 -0.18617418 0.00894832 -20.8055 < 2.2e-16 ***\n",
"month1998-10 -0.04214896 0.00976092 -4.3181 1.625e-05 ***\n",
"month1998-11 -0.05992711 0.00949331 -6.3126 3.154e-10 ***\n",
"month1998-12 -0.07037343 0.00980283 -7.1789 8.842e-13 ***\n",
"month1999-01 -0.07663178 0.00754983 -10.1501 < 2.2e-16 ***\n",
"month1999-02 -0.08381724 0.00767077 -10.9268 < 2.2e-16 ***\n",
"month1999-03 -0.09536649 0.00755976 -12.6150 < 2.2e-16 ***\n",
"month1999-04 -0.09434192 0.00761342 -12.3915 < 2.2e-16 ***\n",
"month1999-05 -0.08890295 0.00794028 -11.1965 < 2.2e-16 ***\n",
"month1999-06 -0.07912543 0.00791461 -9.9974 < 2.2e-16 ***\n",
"month1999-07 -0.07210263 0.00853275 -8.4501 < 2.2e-16 ***\n",
"month1999-08 -0.02759635 0.00956789 -2.8843 0.0039515 ** \n",
"month2000-01 -0.01402232 0.00897464 -1.5624 0.1182914 \n",
"month2000-02 -0.01915194 0.00976516 -1.9613 0.0499429 * \n",
"flat_type4 ROOM 0.31141322 0.01394114 22.3377 < 2.2e-16 ***\n",
"flat_type5 ROOM 0.49754161 0.02998172 16.5948 < 2.2e-16 ***\n",
"flat_typeEXECUTIVE 0.70373654 0.05179618 13.5867 < 2.2e-16 ***\n",
"flat_typeMULTI-GENERATION 0.58928381 0.06252830 9.4243 < 2.2e-16 ***\n",
"flat_typeMULTI GENERATION 0.77981743 0.04668013 16.7056 < 2.2e-16 ***\n",
"block202 0.01817819 0.01206328 1.5069 0.1319420 \n",
"block203 0.01508635 0.01135831 1.3282 0.1842070 \n",
"block204 0.01551104 0.01682660 0.9218 0.3566993 \n",
"block208 0.00639536 0.01097287 0.5828 0.5600495 \n",
"block302 -0.00597626 0.01224185 -0.4882 0.6254568 \n",
"block303 -0.02242202 0.01252971 -1.7895 0.0736348 . \n",
"block304 -0.03986649 0.00927885 -4.2965 1.791e-05 ***\n",
"block305 -0.04098202 0.01113545 -3.6803 0.0002371 ***\n",
"block306 -0.04178454 0.01146392 -3.6449 0.0002721 ***\n",
"block320 -0.03491035 0.00960933 -3.6330 0.0002849 ***\n",
"block321 -0.04265722 0.01118457 -3.8139 0.0001396 ***\n",
"block322 0.00983703 0.01715893 0.5733 0.5664925 \n",
"block323 -0.02131644 0.01246755 -1.7098 0.0874157 . \n",
"block324 0.01197459 0.02215001 0.5406 0.5888148 \n",
"block325 0.00986353 0.01955572 0.5044 0.6140311 \n",
"block326 -0.00657778 0.01970490 -0.3338 0.7385430 \n",
"block327 -0.04462483 0.01058785 -4.2147 2.575e-05 ***\n",
"block345 -0.06243464 0.01138892 -5.4821 4.557e-08 ***\n",
"block346 -0.04160659 0.01063687 -3.9115 9.376e-05 ***\n",
"block349 -0.05031789 0.01054673 -4.7709 1.922e-06 ***\n",
"block350 -0.05132439 0.01010566 -5.0788 4.033e-07 ***\n",
"block350A 0.04352754 0.02650782 1.6421 0.1006827 \n",
"block351 0.01877628 0.02199973 0.8535 0.3934632 \n",
"block352 0.02219872 0.02206632 1.0060 0.3144977 \n",
"block353 -0.05126166 0.01419668 -3.6108 0.0003103 ***\n",
"block354 -0.06759702 0.01600026 -4.2247 2.464e-05 ***\n",
"block355 0.02296826 0.02590877 0.8865 0.3754172 \n",
"block355A 0.02148297 0.02707697 0.7934 0.4276059 \n",
"block356 0.03061214 0.01997597 1.5324 0.1255183 \n",
"block415 0.00085088 0.03420340 0.0249 0.9801548 \n",
"block416 0.00050187 0.03535810 0.0142 0.9886762 \n",
"block602 -0.09602884 0.03753043 -2.5587 0.0105558 * \n",
"block603 -0.10523498 0.03822300 -2.7532 0.0059378 ** \n",
"block604 -0.05131787 0.01910778 -2.6857 0.0072780 ** \n",
"block605 -0.08693576 0.03235705 -2.6868 0.0072550 ** \n",
"block607 -0.02049852 0.01219705 -1.6806 0.0929433 . \n",
"block609 -0.02125244 0.01374863 -1.5458 0.1222629 \n",
"block610 -0.02049616 0.01266751 -1.6180 0.1057667 \n",
"block611 0.02432610 0.02082892 1.1679 0.2429409 \n",
"block612 -0.00791654 0.01216179 -0.6509 0.5151386 \n",
"block613 -0.02075568 0.01220272 -1.7009 0.0890653 . \n",
"block614 0.02958700 0.01770350 1.6713 0.0947774 . \n",
"block615 -0.01702918 0.01237988 -1.3756 0.1690639 \n",
"block616 0.02185433 0.03384524 0.6457 0.5185148 \n",
"block617 -0.01723554 0.01012177 -1.7028 0.0887066 . \n",
"block618 0.01810383 0.03978619 0.4550 0.6491224 \n",
"block619 0.00717750 0.01522953 0.4713 0.6374693 \n",
"block620 0.00216585 0.01153682 0.1877 0.8510984 \n",
"block621 -0.00225474 0.01113066 -0.2026 0.8394846 \n",
"block622 0.01142256 0.01030826 1.1081 0.2679095 \n",
"block624 -0.00479944 0.01069052 -0.4489 0.6535055 \n",
"block625 0.00499289 0.01090274 0.4579 0.6470231 \n",
"block626 0.00078555 0.01284593 0.0612 0.9512427 \n",
"block627 -0.01311022 0.00989681 -1.3247 0.1853754 \n",
"block628 -0.00845406 0.00966966 -0.8743 0.3820326 \n",
"block629 -0.00288752 0.01180139 -0.2447 0.8067239 \n",
"block630 -0.02657752 0.01028951 -2.5830 0.0098427 ** \n",
"block631 -0.00031155 0.06048683 -0.0052 0.9958907 \n",
"block632 -0.00612920 0.01262252 -0.4856 0.6273034 \n",
"block633 -0.00863392 0.01886483 -0.4577 0.6472211 \n",
"block633A 0.00969235 0.03393807 0.2856 0.7752126 \n",
"block634 -0.04781406 0.01039905 -4.5979 4.446e-06 ***\n",
"block635 -0.02088544 0.01300884 -1.6055 0.1084944 \n",
"block636 -0.02781364 0.01042590 -2.6677 0.0076777 ** \n",
"block636A -0.05532348 0.03408349 -1.6232 0.1046580 \n",
"block637 -0.04110705 0.01247054 -3.2963 0.0009911 ***\n",
"block637A 0.03145228 0.04146666 0.7585 0.4482145 \n",
"block638 -0.03819755 0.01251067 -3.0532 0.0022842 ** \n",
"block639 -0.11621783 0.03836347 -3.0294 0.0024716 ** \n",
"block640 -0.05396967 0.01438706 -3.7513 0.0001793 ***\n",
"block640A -0.08024121 0.01416818 -5.6635 1.625e-08 ***\n",
"block641 -0.06576722 0.01827002 -3.5997 0.0003238 ***\n",
"block642 -0.10795661 0.04306016 -2.5071 0.0122252 * \n",
"block643 -0.05772845 0.03885786 -1.4856 0.1374829 \n",
"block644 -0.10851607 0.03286561 -3.3018 0.0009720 ***\n",
"block645 -0.06992345 0.01653683 -4.2283 2.425e-05 ***\n",
"block645A -0.02954960 0.02896938 -1.0200 0.3077980 \n",
"block646 -0.09827431 0.03783556 -2.5974 0.0094395 ** \n",
"block647 -0.09088721 0.03789731 -2.3982 0.0165350 * \n",
"block650 -0.15438945 0.01704274 -9.0590 < 2.2e-16 ***\n",
"block651 -0.11375954 0.03880831 -2.9313 0.0034010 ** \n",
"block652 -0.06343465 0.02456807 -2.5820 0.0098706 ** \n",
"block653 -0.10952115 0.03806386 -2.8773 0.0040396 ** \n",
"block654 -0.08278365 0.01891190 -4.3773 1.243e-05 ***\n",
"block655 -0.11738471 0.03781862 -3.1039 0.0019280 ** \n",
"block656 -0.15243492 0.04972127 -3.0658 0.0021905 ** \n",
"block657 -0.11788459 0.03791807 -3.1089 0.0018955 ** \n",
"block658 -0.11942466 0.03766702 -3.1705 0.0015371 ** \n",
"block659 -0.09765667 0.03745568 -2.6073 0.0091727 ** \n",
"block660 -0.11965369 0.03774314 -3.1702 0.0015388 ** \n",
"block661 -0.09593377 0.02217025 -4.3271 1.560e-05 ***\n",
"block662 -0.04233652 0.01248462 -3.3911 0.0007052 ***\n",
"block663 -0.03289088 0.01204672 -2.7303 0.0063655 ** \n",
"block663A 0.03699338 0.06163684 0.6002 0.5484301 \n",
"block664 -0.00936363 0.03743938 -0.2501 0.8025265 \n",
"block664A -0.02459885 0.03518133 -0.6992 0.4844808 \n",
"block665 0.01965215 0.03754371 0.5234 0.6007021 \n",
"block666 0.02545374 0.02257745 1.1274 0.2596659 \n",
"block666A -0.04772990 0.02451640 -1.9469 0.0516461 . \n",
"block744 0.02253319 0.02151126 1.0475 0.2949512 \n",
"block745 0.03234249 0.01186698 2.7254 0.0064597 ** \n",
"block746 0.02080334 0.01576190 1.3198 0.1869871 \n",
"block747 -0.05869756 0.02647902 -2.2168 0.0267152 * \n",
"block748 0.03423396 0.02381937 1.4372 0.1507575 \n",
"block749 0.04818509 0.01700641 2.8333 0.0046374 ** \n",
"block750 0.02392677 0.01342583 1.7821 0.0748279 . \n",
"block751 0.02688529 0.01450900 1.8530 0.0639804 . \n",
"block752 0.01112774 0.01454574 0.7650 0.4443221 \n",
"block753 -0.00710998 0.02545239 -0.2793 0.7800001 \n",
"block754 -0.00974854 0.01701802 -0.5728 0.5667991 \n",
"block755 -0.01454489 0.01297846 -1.1207 0.2625082 \n",
"block756 -0.01852585 0.01739340 -1.0651 0.2869137 \n",
"block757 -0.02677400 0.01402538 -1.9090 0.0563625 . \n",
"block758 -0.03810230 0.01338471 -2.8467 0.0044478 ** \n",
"block759 -0.01207133 0.01766080 -0.6835 0.4943383 \n",
"block760 -0.02498825 0.00978431 -2.5539 0.0107016 * \n",
"block761 -0.01563352 0.01522695 -1.0267 0.3046451 \n",
"block762 -0.02235810 0.01917982 -1.1657 0.2438255 \n",
"block763 -0.01316304 0.01885407 -0.6982 0.4851355 \n",
"block764 -0.01944983 0.01748469 -1.1124 0.2660597 \n",
"block765 -0.02280564 0.01712004 -1.3321 0.1829291 \n",
"block766 -0.02413351 0.01657448 -1.4561 0.1454806 \n",
"block767 0.03458741 0.02114003 1.6361 0.1019225 \n",
"block768 -0.00961539 0.01879332 -0.5116 0.6089419 \n",
"block769 -0.09176077 0.01277331 -7.1838 8.536e-13 ***\n",
"block770 -0.02454775 0.01207949 -2.0322 0.0422238 * \n",
"block771 -0.03626565 0.01679098 -2.1598 0.0308657 * \n",
"block772 -0.02928780 0.01748827 -1.6747 0.0940962 . \n",
"block773 0.00340093 0.01519534 0.2238 0.8229175 \n",
"block775 -0.04789852 0.01270779 -3.7692 0.0001669 ***\n",
"block776 -0.04254621 0.01561906 -2.7240 0.0064876 ** \n",
"block777 -0.00867784 0.04660244 -0.1862 0.8522929 \n",
"block778 -0.03967751 0.01380480 -2.8742 0.0040796 ** \n",
"block779 -0.11004661 0.01160994 -9.4787 < 2.2e-16 ***\n",
"block780 -0.03573016 0.02053271 -1.7402 0.0819348 . \n",
"block781 -0.04973608 0.00997936 -4.9839 6.589e-07 ***\n",
"block782 -0.04429643 0.01770821 -2.5015 0.0124216 * \n",
"block783 -0.03071578 0.00950141 -3.2328 0.0012394 ** \n",
"block784 -0.03727844 0.01258890 -2.9612 0.0030886 ** \n",
"block785 -0.02197968 0.01372957 -1.6009 0.1095053 \n",
"block786 -0.00248100 0.01320363 -0.1879 0.8509656 \n",
"block787 -0.00266394 0.01191387 -0.2236 0.8230843 \n",
"block788 -0.00532282 0.01508077 -0.3530 0.7241476 \n",
"block789 -0.00745683 0.03353632 -0.2224 0.8240560 \n",
"block790 -0.01199831 0.01224181 -0.9801 0.3271119 \n",
"block791 -0.01188263 0.02060708 -0.5766 0.5642340 \n",
"block792 0.03347237 0.02068832 1.6179 0.1057827 \n",
"block796 0.00105046 0.01137120 0.0924 0.9264034 \n",
"block796A -0.01660975 0.02863751 -0.5800 0.5619589 \n",
"block797 0.06592337 0.03270607 2.0156 0.0439285 * \n",
"block855 0.00779844 0.01673988 0.4659 0.6413498 \n",
"block858 -0.00209713 0.01048067 -0.2001 0.8414199 \n",
"block859 -0.01958082 0.01236046 -1.5841 0.1132663 \n",
"block860 -0.01476911 0.01166538 -1.2661 0.2055895 \n",
"block861 -0.04865154 0.01304393 -3.7298 0.0001952 ***\n",
"block862 -0.03430819 0.01081285 -3.1729 0.0015246 ** \n",
"block863 -0.01226709 0.00960729 -1.2769 0.2017542 \n",
"block926 0.01335360 0.01364177 0.9789 0.3277211 \n",
"block927 -0.00994671 0.03478592 -0.2859 0.7749436 \n",
"block928 0.00990957 0.01634062 0.6064 0.5442703 \n",
"block930 -0.01010567 0.01975544 -0.5115 0.6090121 \n",
"block931 -0.01863415 0.01978274 -0.9419 0.3463002 \n",
"block932 0.02176586 0.02521294 0.8633 0.3880525 \n",
"storey_range04 TO 06 0.02693075 0.00238583 11.2878 < 2.2e-16 ***\n",
"storey_range07 TO 09 0.03966193 0.00238039 16.6619 < 2.2e-16 ***\n",
"storey_range10 TO 12 0.04772492 0.00258090 18.4916 < 2.2e-16 ***\n",
"storey_range13 TO 15 0.04950638 0.00822705 6.0175 1.988e-09 ***\n",
"floor_area_sqm 0.00556484 0.00045256 12.2963 < 2.2e-16 ***\n",
"flat_modelAPARTMENT 0.08895024 0.01569618 5.6670 1.593e-08 ***\n",
"flat_modelImproved 0.13925235 0.01987866 7.0051 3.040e-12 ***\n",
"flat_modelIMPROVED 0.19482354 0.01684185 11.5678 < 2.2e-16 ***\n",
"flat_modelMaisonette -0.03899516 0.02199563 -1.7729 0.0763545 . \n",
"flat_modelMAISONETTE 0.07395606 0.01683771 4.3923 1.161e-05 ***\n",
"flat_modelModel A 0.17886504 0.01303728 13.7195 < 2.2e-16 ***\n",
"flat_modelMODEL A 0.18824374 0.00947146 19.8748 < 2.2e-16 ***\n",
"flat_modelNew Generation 0.15620039 0.02043782 7.6427 2.852e-14 ***\n",
"flat_modelNEW GENERATION 0.13855659 0.01199219 11.5539 < 2.2e-16 ***\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": 23,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 1012, 2720, 3067\"Warning message:\n",
"\"not plotting observations with leverage one:\n",
" 1012, 2720, 3067\"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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\nTAoykEwmBRlIJpOCDCSTSUH/B5KoE8hTSzS8AAAAAElFTkSuQmCC",
"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