library(car)
## Warning: 패키지 'car'는 R 버전 4.2.3에서 작성되었습니다
## 필요한 패키지를 로딩중입니다: carData
## Warning: 패키지 'carData'는 R 버전 4.2.3에서 작성되었습니다
library(caret)
## Warning: 패키지 'caret'는 R 버전 4.2.3에서 작성되었습니다
## 필요한 패키지를 로딩중입니다: ggplot2
## Warning: 패키지 'ggplot2'는 R 버전 4.2.3에서 작성되었습니다
## 필요한 패키지를 로딩중입니다: lattice
library(dplyr)
## Warning: 패키지 'dplyr'는 R 버전 4.2.3에서 작성되었습니다
##
## 다음의 패키지를 부착합니다: 'dplyr'
## The following object is masked from 'package:car':
##
## recode
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ISLR)
## Warning: 패키지 'ISLR'는 R 버전 4.2.3에서 작성되었습니다
getwd()
## [1] "C:/Users/cic/Desktop"
setwd("C:/Users/cic/Desktop")
rm(list=ls())
df <- read.csv("Data1.csv")
bs.out2 <- lm(Happiness~BM,data=df)
sreg.res1 <- residuals(bs.out2)
sreg.res1 %>% head(1)
## 1
## 0.3413448
shapiro.test(sreg.res1)
##
## Shapiro-Wilk normality test
##
## data: sreg.res1
## W = 0.99439, p-value = 1.148e-06
options(scipen=999)
shapiro.test(sreg.res1)
##
## Shapiro-Wilk normality test
##
## data: sreg.res1
## W = 0.99439, p-value = 0.000001148
options(scripen=-999)
shapiro.test(sreg.res1)
##
## Shapiro-Wilk normality test
##
## data: sreg.res1
## W = 0.99439, p-value = 0.000001148
summary(bs.out2)
##
## Call:
## lm(formula = Happiness ~ BM, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1591 -0.4577 0.0418 0.4409 1.9386
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.06599 0.05777 35.77 <0.0000000000000002 ***
## BM 0.49771 0.01878 26.50 <0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6404 on 1923 degrees of freedom
## Multiple R-squared: 0.2675, Adjusted R-squared: 0.2671
## F-statistic: 702.2 on 1 and 1923 DF, p-value: < 0.00000000000000022
plot(bs.out2)
par(mflow=c(2,2))
## Warning in par(mflow = c(2, 2)): "mflow"는 그래픽 매개변수가 아닙니다
bs.out3 <- lm(Happiness~BM+BF,data=df)
summary(bs.out3)
##
## Call:
## lm(formula = Happiness ~ BM + BF, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.23134 -0.40553 0.02014 0.41352 1.86210
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.60995 0.06412 25.11 <0.0000000000000002 ***
## BM 0.29054 0.02331 12.47 <0.0000000000000002 ***
## BF 0.33817 0.02435 13.89 <0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6106 on 1922 degrees of freedom
## Multiple R-squared: 0.3343, Adjusted R-squared: 0.3336
## F-statistic: 482.6 on 2 and 1922 DF, p-value: < 0.00000000000000022
vif(bs.out3)
## BM BF
## 1.693504 1.693504
set.seed(1)
idx <- createDataPartition(df$Happiness,p=0.8,list=F)
train <- df[idx,]
test <- df[-idx,]
glimpse(train)
## Rows: 1,541
## Columns: 26
## $ Q1 <int> 4, 4, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 5, 4, …
## $ Q2 <int> 4, 4, 4, 4, 4, 2, 4, 4, 4, 4, 4, 2, 2, 4, 2, 2, 3, 2, 5, 4, …
## $ Q3 <int> 2, 4, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 3, 2, 3, 3, 2, 5, 4, …
## $ Q4 <int> 3, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 2, 4, 2, 2, 4, 4, 1, 5, 4, …
## $ Q5 <int> 4, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 4, 4, 3, 1, 2, 2, 1, 5, 3, …
## $ Q6 <int> 2, 3, 4, 4, 4, 4, 1, 2, 2, 2, 4, 4, 2, 2, 1, 4, 2, 1, 5, 4, …
## $ Q7 <int> 2, 2, 4, 4, 4, 4, 3, 4, 4, 4, 5, 4, 4, 3, 4, 4, 4, 2, 5, 5, …
## $ Q8 <int> 4, 4, 4, 4, 4, 5, 2, 2, 4, 4, 4, 4, 4, 2, 4, 4, 4, 4, 5, 3, …
## $ Q9 <int> 4, 4, 4, 2, 4, 5, 3, 4, 4, 4, 2, 2, 2, 4, 2, 4, 4, 4, 5, 3, …
## $ Q10 <int> 4, 4, 4, 4, 4, 5, 2, 4, 2, 4, 4, 4, 4, 3, 2, 3, 3, 3, 5, 2, …
## $ Q11 <int> 4, 4, 4, 4, 4, 5, 4, 4, 4, 3, 4, 4, 5, 4, 3, 3, 4, 3, 5, 3, …
## $ Q12 <int> 4, 4, 4, 4, 4, 5, 3, 4, 4, 3, 4, 3, 5, 4, 4, 2, 3, 4, 5, 4, …
## $ Q13 <int> 4, 4, 4, 4, 4, 5, 4, 4, 4, 4, 2, 4, 5, 4, 4, 4, 3, 2, 5, 4, …
## $ Q14 <int> 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 3, 4, 5, 4, 4, 4, 4, 4, 5, 3, …
## $ Q15 <int> 4, 4, 4, 4, 4, 2, 3, 4, 4, 3, 1, 4, 5, 4, 4, 4, 3, 3, 4, 2, …
## $ Q16 <int> 4, 4, 4, 4, 4, 2, 4, 4, 4, 4, 4, 4, 5, 4, 4, 4, 4, 4, 4, 4, …
## $ Q17 <int> 4, 3, 4, 4, 4, 2, 4, 4, 4, 4, 3, 2, 4, 4, 3, 4, 2, 4, 4, 5, …
## $ Q18 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 4, 4, 4, 2, …
## $ Q19 <int> 4, 2, 4, 4, 4, 2, 4, 2, 4, 4, 1, 4, 5, 4, 2, 3, 3, 3, 4, 1, …
## $ Q20 <int> 4, 1, 4, 4, 4, 2, 4, 2, 4, 4, 4, 2, 5, 4, 2, 4, 3, 3, 5, 4, …
## $ Gender1 <int> 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 1, 0, 1, …
## $ EDU1 <int> 1, 1, 1, 2, 1, 1, 4, 3, 2, 1, 1, 3, 1, 1, 1, 4, 3, 2, 1, 2, …
## $ BF <dbl> 3.4, 4.0, 4.2, 4.0, 4.0, 3.6, 3.6, 3.2, 4.0, 3.2, 4.0, 3.2, …
## $ BM <dbl> 3.2, 3.4, 4.0, 3.6, 4.0, 4.6, 2.2, 3.2, 3.2, 3.6, 3.8, 3.6, …
## $ Happiness <dbl> 4.0, 4.0, 4.0, 4.0, 4.0, 4.4, 3.8, 4.0, 4.0, 3.4, 2.8, 3.8, …
## $ Peace <dbl> 4.0, 2.8, 4.0, 4.0, 4.0, 2.4, 4.0, 3.2, 4.0, 3.9, 3.2, 3.2, …
fit <- lm(Happiness~BM+BF+Peace,data=train)
summary(fit)
##
## Call:
## lm(formula = Happiness ~ BM + BF + Peace, data = train)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.81440 -0.32378 -0.00204 0.33429 2.19548
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.53856 0.08371 6.434 0.000000000166 ***
## BM 0.21065 0.02347 8.975 < 0.0000000000000002 ***
## BF 0.22207 0.02421 9.173 < 0.0000000000000002 ***
## Peace 0.47033 0.02268 20.740 < 0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5409 on 1537 degrees of freedom
## Multiple R-squared: 0.4691, Adjusted R-squared: 0.4681
## F-statistic: 452.7 on 3 and 1537 DF, p-value: < 0.00000000000000022
#Happiness=0.513888+0.230878*BM+0.24636*BF+0.45747+peace
lm_p <- predict(fit,newdata=test)
lm_p %>% head(1)
## 3
## 3.883613
round(predict(fit,newdata=test),1)
## 3 7 15 16 39 41 44 45 46 47 48 55 56 60 63 65
## 3.9 4.1 4.1 4.6 3.9 3.9 2.3 4.2 3.9 3.9 2.0 3.8 3.6 4.0 4.1 3.8
## 68 69 72 73 76 83 84 86 89 90 96 103 111 115 128 132
## 4.2 3.3 4.2 3.8 3.7 3.8 4.8 3.6 4.0 3.5 3.4 3.9 4.0 3.5 3.8 4.1
## 137 139 141 142 154 159 160 170 183 187 188 196 197 201 205 212
## 3.9 3.2 3.7 3.8 3.0 4.2 4.0 3.6 4.1 4.2 3.7 4.4 3.9 4.0 3.7 3.2
## 223 224 232 233 245 249 251 253 256 258 261 265 275 278 279 285
## 4.0 4.1 3.4 3.3 3.4 3.4 3.5 2.2 4.1 3.6 3.8 4.1 3.2 2.3 3.4 3.3
## 300 303 307 314 319 323 330 332 335 341 345 356 373 375 379 382
## 3.7 3.9 3.9 3.8 3.4 3.6 3.9 4.0 3.7 3.9 3.9 3.3 3.2 3.3 3.6 3.0
## 383 389 393 397 399 400 408 417 420 421 435 446 447 448 449 459
## 3.8 3.9 3.9 3.8 4.1 3.7 3.8 4.0 4.3 3.5 3.5 3.1 3.7 3.0 3.8 3.7
## 484 492 494 500 506 507 509 510 513 514 516 519 523 535 542 561
## 3.8 4.1 3.4 3.3 3.7 3.8 3.5 3.7 3.6 3.0 4.5 5.0 4.0 3.8 3.5 3.0
## 563 567 571 574 576 581 583 591 593 595 602 608 620 622 624 626
## 3.3 3.6 3.1 3.2 3.2 4.5 3.7 3.5 3.8 3.9 4.5 2.9 3.4 3.5 4.3 3.4
## 629 634 647 657 659 668 670 675 684 685 688 691 696 699 702 706
## 4.0 3.6 3.5 2.9 2.5 2.6 2.4 3.1 3.5 4.3 3.5 3.4 3.2 3.1 3.5 2.8
## 710 712 721 727 731 736 741 742 746 748 756 758 764 775 779 793
## 3.9 4.2 2.5 2.2 2.5 4.4 4.5 2.9 3.8 4.0 3.5 3.5 3.1 3.2 2.2 3.8
## 799 802 813 819 825 828 831 841 851 852 856 871 875 877 881 886
## 3.6 4.7 3.7 3.4 4.0 2.0 4.0 3.4 2.8 2.8 2.7 4.0 3.2 3.4 3.4 4.0
## 887 888 892 904 905 913 914 915 917 919 927 932 935 943 955 962
## 2.4 4.0 2.7 3.4 3.7 3.4 3.5 3.2 4.0 3.9 3.7 3.5 3.0 2.7 4.1 3.5
## 963 967 969 971 972 980 983 991 993 995 998 1003 1006 1007 1008 1014
## 4.0 2.5 3.3 3.4 3.5 3.9 2.7 4.0 3.4 3.7 3.3 4.1 3.0 4.5 3.1 2.5
## 1037 1042 1047 1053 1067 1070 1081 1090 1091 1093 1101 1102 1105 1115 1118 1119
## 4.1 3.6 3.9 3.8 3.4 3.0 2.9 3.9 3.3 3.7 3.7 3.2 4.1 2.6 3.2 4.0
## 1125 1127 1130 1136 1137 1138 1139 1141 1146 1150 1159 1160 1164 1166 1172 1173
## 4.2 3.1 3.7 3.6 3.8 3.3 3.0 3.1 3.5 3.5 3.0 3.9 3.0 4.1 2.5 3.0
## 1179 1181 1183 1187 1189 1191 1202 1208 1213 1219 1225 1232 1247 1253 1265 1266
## 3.3 3.3 4.4 2.8 4.0 3.5 3.2 3.5 3.0 3.1 3.2 4.4 3.3 3.5 3.9 3.5
## 1270 1276 1279 1287 1295 1298 1300 1302 1303 1304 1305 1313 1314 1316 1317 1320
## 4.2 4.2 4.2 3.9 3.6 3.9 3.7 3.6 3.3 3.8 4.2 3.4 4.0 4.1 3.5 3.7
## 1322 1329 1335 1343 1344 1356 1365 1367 1374 1376 1387 1388 1394 1395 1397 1409
## 2.7 2.9 3.2 2.8 3.9 3.9 3.5 2.9 3.3 3.9 3.1 3.1 3.8 4.2 3.4 3.2
## 1414 1419 1422 1423 1424 1426 1428 1433 1435 1450 1455 1460 1461 1463 1481 1496
## 4.0 3.2 3.1 4.2 3.8 3.4 3.3 3.0 3.4 3.8 3.6 3.2 3.2 3.6 3.8 3.3
## 1499 1500 1502 1505 1507 1508 1516 1519 1529 1535 1536 1541 1550 1553 1562 1568
## 3.9 3.4 3.4 3.6 3.9 3.5 3.3 3.1 3.9 4.0 4.3 3.4 3.6 3.2 3.7 4.0
## 1572 1596 1599 1600 1603 1611 1612 1615 1617 1636 1651 1652 1654 1656 1668 1675
## 3.0 3.9 4.2 4.1 3.8 3.9 3.4 3.4 3.1 3.3 2.8 3.0 2.8 3.6 3.9 3.4
## 1683 1687 1690 1694 1695 1696 1700 1708 1717 1719 1720 1724 1727 1730 1733 1734
## 3.5 3.4 2.9 3.5 3.4 3.0 2.9 3.4 3.5 3.2 3.5 2.7 2.7 4.1 3.4 4.1
## 1740 1743 1753 1755 1764 1774 1775 1776 1781 1787 1793 1795 1800 1807 1816 1824
## 4.0 3.9 4.7 4.3 4.2 3.5 4.6 3.6 4.4 3.4 3.5 3.8 3.7 3.7 3.1 4.2
## 1826 1839 1842 1851 1856 1857 1863 1874 1887 1892 1893 1895 1899 1902 1908 1909
## 3.5 3.6 3.4 3.3 3.2 2.6 2.5 3.5 3.5 3.5 3.1 2.4 2.4 3.3 3.2 3.6
test$Happiness1 <- round(predict(fit,newdata=test),1)
View(test)
fit1 <- lm(Happiness~BM+BF+Peace,data=train)
mean((test$Happiness-test$Happiness1)^2)
## [1] 0.3188021
mean((test$Happiness-test$Happiness2)^2)
## [1] NaN
predict(fit,newdata=test) %>% head(1)
## 3
## 3.883613
lm_p <- predict(fit1,newdata=test)
round(predict(fit1,newdata=test),1)
## 3 7 15 16 39 41 44 45 46 47 48 55 56 60 63 65
## 3.9 4.1 4.1 4.6 3.9 3.9 2.3 4.2 3.9 3.9 2.0 3.8 3.6 4.0 4.1 3.8
## 68 69 72 73 76 83 84 86 89 90 96 103 111 115 128 132
## 4.2 3.3 4.2 3.8 3.7 3.8 4.8 3.6 4.0 3.5 3.4 3.9 4.0 3.5 3.8 4.1
## 137 139 141 142 154 159 160 170 183 187 188 196 197 201 205 212
## 3.9 3.2 3.7 3.8 3.0 4.2 4.0 3.6 4.1 4.2 3.7 4.4 3.9 4.0 3.7 3.2
## 223 224 232 233 245 249 251 253 256 258 261 265 275 278 279 285
## 4.0 4.1 3.4 3.3 3.4 3.4 3.5 2.2 4.1 3.6 3.8 4.1 3.2 2.3 3.4 3.3
## 300 303 307 314 319 323 330 332 335 341 345 356 373 375 379 382
## 3.7 3.9 3.9 3.8 3.4 3.6 3.9 4.0 3.7 3.9 3.9 3.3 3.2 3.3 3.6 3.0
## 383 389 393 397 399 400 408 417 420 421 435 446 447 448 449 459
## 3.8 3.9 3.9 3.8 4.1 3.7 3.8 4.0 4.3 3.5 3.5 3.1 3.7 3.0 3.8 3.7
## 484 492 494 500 506 507 509 510 513 514 516 519 523 535 542 561
## 3.8 4.1 3.4 3.3 3.7 3.8 3.5 3.7 3.6 3.0 4.5 5.0 4.0 3.8 3.5 3.0
## 563 567 571 574 576 581 583 591 593 595 602 608 620 622 624 626
## 3.3 3.6 3.1 3.2 3.2 4.5 3.7 3.5 3.8 3.9 4.5 2.9 3.4 3.5 4.3 3.4
## 629 634 647 657 659 668 670 675 684 685 688 691 696 699 702 706
## 4.0 3.6 3.5 2.9 2.5 2.6 2.4 3.1 3.5 4.3 3.5 3.4 3.2 3.1 3.5 2.8
## 710 712 721 727 731 736 741 742 746 748 756 758 764 775 779 793
## 3.9 4.2 2.5 2.2 2.5 4.4 4.5 2.9 3.8 4.0 3.5 3.5 3.1 3.2 2.2 3.8
## 799 802 813 819 825 828 831 841 851 852 856 871 875 877 881 886
## 3.6 4.7 3.7 3.4 4.0 2.0 4.0 3.4 2.8 2.8 2.7 4.0 3.2 3.4 3.4 4.0
## 887 888 892 904 905 913 914 915 917 919 927 932 935 943 955 962
## 2.4 4.0 2.7 3.4 3.7 3.4 3.5 3.2 4.0 3.9 3.7 3.5 3.0 2.7 4.1 3.5
## 963 967 969 971 972 980 983 991 993 995 998 1003 1006 1007 1008 1014
## 4.0 2.5 3.3 3.4 3.5 3.9 2.7 4.0 3.4 3.7 3.3 4.1 3.0 4.5 3.1 2.5
## 1037 1042 1047 1053 1067 1070 1081 1090 1091 1093 1101 1102 1105 1115 1118 1119
## 4.1 3.6 3.9 3.8 3.4 3.0 2.9 3.9 3.3 3.7 3.7 3.2 4.1 2.6 3.2 4.0
## 1125 1127 1130 1136 1137 1138 1139 1141 1146 1150 1159 1160 1164 1166 1172 1173
## 4.2 3.1 3.7 3.6 3.8 3.3 3.0 3.1 3.5 3.5 3.0 3.9 3.0 4.1 2.5 3.0
## 1179 1181 1183 1187 1189 1191 1202 1208 1213 1219 1225 1232 1247 1253 1265 1266
## 3.3 3.3 4.4 2.8 4.0 3.5 3.2 3.5 3.0 3.1 3.2 4.4 3.3 3.5 3.9 3.5
## 1270 1276 1279 1287 1295 1298 1300 1302 1303 1304 1305 1313 1314 1316 1317 1320
## 4.2 4.2 4.2 3.9 3.6 3.9 3.7 3.6 3.3 3.8 4.2 3.4 4.0 4.1 3.5 3.7
## 1322 1329 1335 1343 1344 1356 1365 1367 1374 1376 1387 1388 1394 1395 1397 1409
## 2.7 2.9 3.2 2.8 3.9 3.9 3.5 2.9 3.3 3.9 3.1 3.1 3.8 4.2 3.4 3.2
## 1414 1419 1422 1423 1424 1426 1428 1433 1435 1450 1455 1460 1461 1463 1481 1496
## 4.0 3.2 3.1 4.2 3.8 3.4 3.3 3.0 3.4 3.8 3.6 3.2 3.2 3.6 3.8 3.3
## 1499 1500 1502 1505 1507 1508 1516 1519 1529 1535 1536 1541 1550 1553 1562 1568
## 3.9 3.4 3.4 3.6 3.9 3.5 3.3 3.1 3.9 4.0 4.3 3.4 3.6 3.2 3.7 4.0
## 1572 1596 1599 1600 1603 1611 1612 1615 1617 1636 1651 1652 1654 1656 1668 1675
## 3.0 3.9 4.2 4.1 3.8 3.9 3.4 3.4 3.1 3.3 2.8 3.0 2.8 3.6 3.9 3.4
## 1683 1687 1690 1694 1695 1696 1700 1708 1717 1719 1720 1724 1727 1730 1733 1734
## 3.5 3.4 2.9 3.5 3.4 3.0 2.9 3.4 3.5 3.2 3.5 2.7 2.7 4.1 3.4 4.1
## 1740 1743 1753 1755 1764 1774 1775 1776 1781 1787 1793 1795 1800 1807 1816 1824
## 4.0 3.9 4.7 4.3 4.2 3.5 4.6 3.6 4.4 3.4 3.5 3.8 3.7 3.7 3.1 4.2
## 1826 1839 1842 1851 1856 1857 1863 1874 1887 1892 1893 1895 1899 1902 1908 1909
## 3.5 3.6 3.4 3.3 3.2 2.6 2.5 3.5 3.5 3.5 3.1 2.4 2.4 3.3 3.2 3.6
test$Happiness2 <- round(predict(fit1,newdata=test),1)
x1 <- c(7,1,11,11,7,11,3,1,2,21,1,11,10)
x2 <- c(26,29,56,31,52,55,71,31,54,47,40,66,68)
x3 <- c(6,15,8,8,6,9,17,22,18,4,23,9,8)
x4 <- c(60,52,20,47,33,22,6,44,22,26,34,12,12)
y <- c(78.5,74.3,104.3,87.6,95.9,109.,102.7,72.5,93.1,115.9,83.8,113.3,109.4)
df <- data.frame(x1,x2,x3,x4,y)
step(lm(y~1,df),scope=list(lower=~1,upper=~x1+x2+x3+x4),direction="forward")
## Start: AIC=71.42
## y ~ 1
##
## Df Sum of Sq RSS AIC
## + x4 1 1829.53 880.75 58.806
## + x2 1 1807.27 903.02 59.130
## + x1 1 1447.43 1262.86 63.490
## + x3 1 774.97 1935.32 69.040
## <none> 2710.29 71.418
##
## Step: AIC=58.81
## y ~ x4
##
## Df Sum of Sq RSS AIC
## + x1 1 807.47 73.29 28.483
## + x3 1 706.84 173.91 39.717
## <none> 880.75 58.806
## + x2 1 15.04 865.72 60.582
##
## Step: AIC=28.48
## y ~ x4 + x1
##
## Df Sum of Sq RSS AIC
## + x2 1 26.841 46.449 24.554
## + x3 1 23.929 49.361 25.345
## <none> 73.289 28.483
##
## Step: AIC=24.55
## y ~ x4 + x1 + x2
##
## Df Sum of Sq RSS AIC
## <none> 46.449 24.554
## + x3 1 0.12025 46.328 26.520
##
## Call:
## lm(formula = y ~ x4 + x1 + x2, data = df)
##
## Coefficients:
## (Intercept) x4 x1 x2
## 71.6032 -0.2358 1.4505 0.4165
#y~1
#y~4
#y~x4+x1
#y~x4+x1+x2
data("attitude")
glimpse(attitude)
## Rows: 30
## Columns: 7
## $ rating <dbl> 43, 63, 71, 61, 81, 43, 58, 71, 72, 67, 64, 67, 69, 68, 77,…
## $ complaints <dbl> 51, 64, 70, 63, 78, 55, 67, 75, 82, 61, 53, 60, 62, 83, 77,…
## $ privileges <dbl> 30, 51, 68, 45, 56, 49, 42, 50, 72, 45, 53, 47, 57, 83, 54,…
## $ learning <dbl> 39, 54, 69, 47, 66, 44, 56, 55, 67, 47, 58, 39, 42, 45, 72,…
## $ raises <dbl> 61, 63, 76, 54, 71, 54, 66, 70, 71, 62, 58, 59, 55, 59, 79,…
## $ critical <dbl> 92, 73, 86, 84, 83, 49, 68, 66, 83, 80, 67, 74, 63, 77, 77,…
## $ advance <dbl> 45, 47, 48, 35, 47, 34, 35, 41, 31, 41, 34, 41, 25, 35, 46,…
step(lm(rating~.,data=attitude),direction="backward")
## Start: AIC=123.36
## rating ~ complaints + privileges + learning + raises + critical +
## advance
##
## Df Sum of Sq RSS AIC
## - critical 1 3.41 1152.4 121.45
## - raises 1 6.80 1155.8 121.54
## - privileges 1 14.47 1163.5 121.74
## - advance 1 74.11 1223.1 123.24
## <none> 1149.0 123.36
## - learning 1 180.50 1329.5 125.74
## - complaints 1 724.80 1873.8 136.04
##
## Step: AIC=121.45
## rating ~ complaints + privileges + learning + raises + advance
##
## Df Sum of Sq RSS AIC
## - raises 1 10.61 1163.0 119.73
## - privileges 1 14.16 1166.6 119.82
## - advance 1 71.27 1223.7 121.25
## <none> 1152.4 121.45
## - learning 1 177.74 1330.1 123.75
## - complaints 1 724.70 1877.1 134.09
##
## Step: AIC=119.73
## rating ~ complaints + privileges + learning + advance
##
## Df Sum of Sq RSS AIC
## - privileges 1 16.10 1179.1 118.14
## - advance 1 61.60 1224.6 119.28
## <none> 1163.0 119.73
## - learning 1 197.03 1360.0 122.42
## - complaints 1 1165.94 2328.9 138.56
##
## Step: AIC=118.14
## rating ~ complaints + learning + advance
##
## Df Sum of Sq RSS AIC
## - advance 1 75.54 1254.7 118.00
## <none> 1179.1 118.14
## - learning 1 186.12 1365.2 120.54
## - complaints 1 1259.91 2439.0 137.94
##
## Step: AIC=118
## rating ~ complaints + learning
##
## Df Sum of Sq RSS AIC
## <none> 1254.7 118.00
## - learning 1 114.73 1369.4 118.63
## - complaints 1 1370.91 2625.6 138.16
##
## Call:
## lm(formula = rating ~ complaints + learning, data = attitude)
##
## Coefficients:
## (Intercept) complaints learning
## 9.8709 0.6435 0.2112
step(lm(rating~.,data=attitude),direction="forward")
## Start: AIC=123.36
## rating ~ complaints + privileges + learning + raises + critical +
## advance
##
## Call:
## lm(formula = rating ~ complaints + privileges + learning + raises +
## critical + advance, data = attitude)
##
## Coefficients:
## (Intercept) complaints privileges learning raises critical
## 10.78708 0.61319 -0.07305 0.32033 0.08173 0.03838
## advance
## -0.21706
step(lm(rating~.,data=attitude),direction="both")
## Start: AIC=123.36
## rating ~ complaints + privileges + learning + raises + critical +
## advance
##
## Df Sum of Sq RSS AIC
## - critical 1 3.41 1152.4 121.45
## - raises 1 6.80 1155.8 121.54
## - privileges 1 14.47 1163.5 121.74
## - advance 1 74.11 1223.1 123.24
## <none> 1149.0 123.36
## - learning 1 180.50 1329.5 125.74
## - complaints 1 724.80 1873.8 136.04
##
## Step: AIC=121.45
## rating ~ complaints + privileges + learning + raises + advance
##
## Df Sum of Sq RSS AIC
## - raises 1 10.61 1163.0 119.73
## - privileges 1 14.16 1166.6 119.82
## - advance 1 71.27 1223.7 121.25
## <none> 1152.4 121.45
## + critical 1 3.41 1149.0 123.36
## - learning 1 177.74 1330.1 123.75
## - complaints 1 724.70 1877.1 134.09
##
## Step: AIC=119.73
## rating ~ complaints + privileges + learning + advance
##
## Df Sum of Sq RSS AIC
## - privileges 1 16.10 1179.1 118.14
## - advance 1 61.60 1224.6 119.28
## <none> 1163.0 119.73
## + raises 1 10.61 1152.4 121.45
## + critical 1 7.21 1155.8 121.54
## - learning 1 197.03 1360.0 122.42
## - complaints 1 1165.94 2328.9 138.56
##
## Step: AIC=118.14
## rating ~ complaints + learning + advance
##
## Df Sum of Sq RSS AIC
## - advance 1 75.54 1254.7 118.00
## <none> 1179.1 118.14
## + privileges 1 16.10 1163.0 119.73
## + raises 1 12.54 1166.6 119.82
## + critical 1 7.18 1171.9 119.96
## - learning 1 186.12 1365.2 120.54
## - complaints 1 1259.91 2439.0 137.94
##
## Step: AIC=118
## rating ~ complaints + learning
##
## Df Sum of Sq RSS AIC
## <none> 1254.7 118.00
## + advance 1 75.54 1179.1 118.14
## - learning 1 114.73 1369.4 118.63
## + privileges 1 30.03 1224.6 119.28
## + raises 1 1.19 1253.5 119.97
## + critical 1 0.00 1254.7 120.00
## - complaints 1 1370.91 2625.6 138.16
##
## Call:
## lm(formula = rating ~ complaints + learning, data = attitude)
##
## Coefficients:
## (Intercept) complaints learning
## 9.8709 0.6435 0.2112
df <- read.csv("Data1.csv")
table(df$Gender1)
##
## 0 1
## 1136 789
lmfit <- lm(Happiness~Gender1,data=df)
summary(lmfit)
##
## Call:
## lm(formula = Happiness ~ Gender1, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1659 -0.5199 0.0801 0.4801 1.4801
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.56593 0.02219 160.711 <0.0000000000000002 ***
## Gender1 -0.04603 0.03466 -1.328 0.184
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7479 on 1923 degrees of freedom
## Multiple R-squared: 0.0009166, Adjusted R-squared: 0.0003971
## F-statistic: 1.764 on 1 and 1923 DF, p-value: 0.1843
df$EDU1 <- factor(df$EDU1)
df$GENDER1 <- factor(df$Gender1)
lmfit1 <- lm(Happiness~Gender1,data=df)
summary(lmfit1)
##
## Call:
## lm(formula = Happiness ~ Gender1, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1659 -0.5199 0.0801 0.4801 1.4801
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.56593 0.02219 160.711 <0.0000000000000002 ***
## Gender1 -0.04603 0.03466 -1.328 0.184
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7479 on 1923 degrees of freedom
## Multiple R-squared: 0.0009166, Adjusted R-squared: 0.0003971
## F-statistic: 1.764 on 1 and 1923 DF, p-value: 0.1843
lmfit <- lm(Happiness~EDU1,data=df)
summary(lmfit)
##
## Call:
## lm(formula = Happiness ~ EDU1, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1512 -0.4754 0.1246 0.4488 1.5246
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.58670 0.04893 73.303 <0.0000000000000002 ***
## EDU12 -0.11127 0.05980 -1.861 0.0629 .
## EDU13 -0.03552 0.05422 -0.655 0.5125
## EDU14 0.06330 0.07219 0.877 0.3806
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7469 on 1921 degrees of freedom
## Multiple R-squared: 0.004555, Adjusted R-squared: 0.003001
## F-statistic: 2.93 on 3 and 1921 DF, p-value: 0.03247
table(df$EDU1)
##
## 1 2 3 4
## 233 472 1022 198
#1 중졸 ㅣ 2고졸 ㅣ 3대졸 ㅣ4대학원들
bs.out2 <- lm(Happiness~BM,data=df)
summary(bs.out2)
##
## Call:
## lm(formula = Happiness ~ BM, data = df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.1591 -0.4577 0.0418 0.4409 1.9386
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.06599 0.05777 35.77 <0.0000000000000002 ***
## BM 0.49771 0.01878 26.50 <0.0000000000000002 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6404 on 1923 degrees of freedom
## Multiple R-squared: 0.2675, Adjusted R-squared: 0.2671
## F-statistic: 702.2 on 1 and 1923 DF, p-value: < 0.00000000000000022
library(datasets)
data("USArrests")
head(USArrests)
## Murder Assault UrbanPop Rape
## Alabama 13.2 236 58 21.2
## Alaska 10.0 263 48 44.5
## Arizona 8.1 294 80 31.0
## Arkansas 8.8 190 50 19.5
## California 9.0 276 91 40.6
## Colorado 7.9 204 78 38.7
fit <- prcomp(USArrests,scale=T)
summary(fit)
## Importance of components:
## PC1 PC2 PC3 PC4
## Standard deviation 1.5749 0.9949 0.59713 0.41645
## Proportion of Variance 0.6201 0.2474 0.08914 0.04336
## Cumulative Proportion 0.6201 0.8675 0.95664 1.00000
Nile
## Time Series:
## Start = 1871
## End = 1970
## Frequency = 1
## [1] 1120 1160 963 1210 1160 1160 813 1230 1370 1140 995 935 1110 994 1020
## [16] 960 1180 799 958 1140 1100 1210 1150 1250 1260 1220 1030 1100 774 840
## [31] 874 694 940 833 701 916 692 1020 1050 969 831 726 456 824 702
## [46] 1120 1100 832 764 821 768 845 864 862 698 845 744 796 1040 759
## [61] 781 865 845 944 984 897 822 1010 771 676 649 846 812 742 801
## [76] 1040 860 874 848 890 744 749 838 1050 918 986 797 923 975 815
## [91] 1020 906 901 1170 912 746 919 718 714 740
plot(Nile)
Nile.diff1 <- diff(Nile,differences=1)
plot(Nile.diff1)
Nile.diff2 <- diff(Nile,differences=2)
plot(Nile.diff2)
