#Regresi Linier Sederhana Model \(X_1\)
# PACKAGES
library(stats)
library(rmarkdown)
library(car)## Loading required package: carDatalibrary(lmtest)## Loading required package: zoo##
## Attaching package: 'zoo'## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numericlibrary(zoo)# Memanggil Data
data=read.table(file.choose(),header=TRUE)
data# Regresi Linier Sederhana Model X1
reg=lm(formula=Y~X1, data=data)
summary(reg)##
## Call:
## lm(formula = Y ~ X1, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -7.7950 -2.6039 0.4453 2.0748 7.1693
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 12.27099 0.82825 14.816 <2e-16 ***
## X1 0.01493 0.04808 0.311 0.757
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.304 on 68 degrees of freedom
## Multiple R-squared: 0.001417, Adjusted R-squared: -0.01327
## F-statistic: 0.09649 on 1 and 68 DF, p-value: 0.757#Pengujian Asumsi Klasik
#Uji Heteroskedastisitas (Breusch-Pagan test & Glejser test)
# Pengujian Asumsi Klasik Model X1
# Uji Heteroskedastisitas (Breusch-Pagan test)
bptest(reg)##
## studentized Breusch-Pagan test
##
## data: reg
## BP = 0.0067713, df = 1, p-value = 0.9344# Uji Heteroskedastisitas (Glejser test)
res_X1 <- residuals(reg)
res_X1 <- abs(residuals(reg))
res_X1## 1 2 3 4 5 6 7
## 2.92487809 1.89459677 1.02487809 2.65020630 3.10994374 4.18007502 2.93939984
## 8 9 10 11 12 13 14
## 0.81448424 5.19046887 1.47422167 0.90045012 0.13073144 0.13527195 3.48097526
## 15 16 17 18 19 20 21
## 5.33981245 2.14525319 5.69459677 0.68420292 1.90086273 0.06060016 5.24071269
## 22 23 24 25 26 27 28
## 0.49459677 3.88007502 3.83527195 2.95020630 5.85928731 6.23031883 0.85433420
## 29 30 31 32 33 34 35
## 0.70409039 0.39590961 3.29500938 3.18097526 1.38915603 7.79500938 0.87058140
## 36 37 38 39 40 41 42
## 3.75433420 1.09459677 0.89913727 3.50045012 1.20953113 0.77512191 1.08420292
## 43 44 45 46 47 48 49
## 3.07058140 3.47553452 4.80045012 2.46514066 4.96472805 3.58461552 2.10086273
## 50 51 52 53 54 55 56
## 5.60994374 0.53031883 0.57058140 3.06018755 7.16926856 2.79459677 0.05474681
## 57 58 59 60 61 62 63
## 1.99954988 0.24979370 1.15020630 2.13485934 1.71084397 1.74071269 2.82487809
## 64 65 66 67 68 69 70
## 1.56926856 6.37966241 3.41992498 1.37422167 0.73485934 3.27099401 5.66968117uji_glejser <- lm(res_X1~X1, data=data)
summary(uji_glejser)##
## Call:
## lm(formula = res_X1 ~ X1, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5899 -1.6809 -0.3296 0.9164 5.1604
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.597043 0.486632 5.337 1.17e-06 ***
## X1 0.002506 0.028248 0.089 0.93
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.941 on 68 degrees of freedom
## Multiple R-squared: 0.0001158, Adjusted R-squared: -0.01459
## F-statistic: 0.007873 on 1 and 68 DF, p-value: 0.9296#Uji Autokorelasi (Durbin-Watson test & Breusch-Godfrey test)
# Uji AutoKorelasi (Durbin-Watson test dan Breusch-Godfrey test)
dwtest(reg)##
## Durbin-Watson test
##
## data: reg
## DW = 1.8252, p-value = 0.2316
## alternative hypothesis: true autocorrelation is greater than 0bgtest(reg)##
## Breusch-Godfrey test for serial correlation of order up to 1
##
## data: reg
## LM test = 0.27133, df = 1, p-value = 0.6024#Uji Normalitas Residual (Shapiro-Wilk normality test)
# Uji Normalitas Residual (Shapiro-Wilk normality test)
shapiro.test(resid(reg))##
## Shapiro-Wilk normality test
##
## data: resid(reg)
## W = 0.98955, p-value = 0.8314#Regresi Linier Sederhana Model \(X_2\)
# Regresi Linier Sederhana Model X2
reg=lm(formula=Y~X2, data=data)
summary(reg)##
## Call:
## lm(formula = Y ~ X2, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -8.1717 -2.7685 0.2307 1.9908 6.7578
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.150e+01 1.116e+00 10.312 1.53e-15 ***
## X2 5.222e-04 5.487e-04 0.952 0.345
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.285 on 68 degrees of freedom
## Multiple R-squared: 0.01314, Adjusted R-squared: -0.00137
## F-statistic: 0.9056 on 1 and 68 DF, p-value: 0.3447#Pengujian Asumsi Klasik
#Uji Heteroskedastisitas (Breusch-Pagan test & Glejser test)
# Pengujian Asumsi Klasik Model X2
# Uji Heteroskedastisitas (Breusch-Pagan test)
bptest(reg)##
## studentized Breusch-Pagan test
##
## data: reg
## BP = 0.76597, df = 1, p-value = 0.3815# Uji Heteroskedastisitas (Glejser test)
res_X2 <- residuals(reg)
res_X2 <- abs(residuals(reg))
res_X2## 1 2 3 4 5 6 7 8
## 3.1270153 2.3228640 1.1371969 2.9390260 3.6278026 4.3888947 2.4805552 0.1499816
## 9 10 11 12 13 14 15 16
## 4.5844441 0.9787052 0.7009210 0.3980319 0.6176184 3.2625380 4.8173454 2.0006613
## 17 18 19 20 21 22 23 24
## 5.3191980 0.6160701 1.4089875 0.4891572 5.6842186 0.6074551 3.8565157 3.2643408
## 25 26 27 28 29 30 31 32
## 3.1319749 5.1656476 6.1481815 0.9831742 0.8398106 1.0638554 2.9066416 3.6116327
## 33 34 35 36 37 38 39 40
## 0.6019392 8.1716648 0.7165870 3.4998793 1.1035373 0.2343392 4.0847434 1.5429674
## 41 42 43 44 45 46 47 48
## 0.4168468 0.5142358 3.3938779 4.0129186 4.6980503 2.9473838 5.1084995 2.8173427
## 49 50 51 52 53 54 55 56
## 2.6220558 5.8667026 0.2095360 0.2604492 3.4975360 6.7578408 2.8286029 0.4633332
## 57 58 59 60 61 62 63 64
## 2.2137006 0.1048232 1.4552142 1.9612365 1.9053637 1.8364333 2.5648682 1.6925738
## 65 66 67 68 69 70
## 6.0212868 3.1776845 0.6531148 0.2270284 2.9306602 6.1622678uji_glejser <- lm(res_X2~X2, data=data)
summary(uji_glejser)##
## Call:
## lm(formula = res_X2 ~ X2, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.535 -1.855 -0.091 1.020 5.522
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.465e+00 6.650e-01 3.706 0.000424 ***
## X2 7.046e-05 3.271e-04 0.215 0.830096
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.958 on 68 degrees of freedom
## Multiple R-squared: 0.0006819, Adjusted R-squared: -0.01401
## F-statistic: 0.0464 on 1 and 68 DF, p-value: 0.8301#Uji Autokorelasi (Durbin-Watson test & Breusch-Godfrey test)
# Uji AutoKorelasi (Durbin-Watson test dan Breusch-Godfrey test)
dwtest(reg)##
## Durbin-Watson test
##
## data: reg
## DW = 1.8279, p-value = 0.2373
## alternative hypothesis: true autocorrelation is greater than 0bgtest(reg)##
## Breusch-Godfrey test for serial correlation of order up to 1
##
## data: reg
## LM test = 0.22247, df = 1, p-value = 0.6372#Uji Normalitas Residual (Shapiro-Wilk normality test)
# Uji Normalitas Residual (Shapiro-Wilk normality test)
shapiro.test(resid(reg))##
## Shapiro-Wilk normality test
##
## data: resid(reg)
## W = 0.9895, p-value = 0.8289#Regresi Linier Sederhana Model \(X_3\)
# Regresi Linier Sederhana Model X3
reg=lm(formula=Y~X3, data=data)
summary(reg)##
## Call:
## lm(formula = Y ~ X3, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -7.7328 -2.6123 0.3325 2.1956 6.8539
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 12.099718 0.826542 14.639 <2e-16 ***
## X3 0.003793 0.006933 0.547 0.586
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.299 on 68 degrees of freedom
## Multiple R-squared: 0.004382, Adjusted R-squared: -0.01026
## F-statistic: 0.2993 on 1 and 68 DF, p-value: 0.5861#Pengujian Asumsi Klasik
#Uji Heteroskedastisitas (Breusch-Pagan test & Glejser test)
# Pengujian Asumsi Klasik Model X3
# Uji Heteroskedastisitas (Breusch-Pagan test dan Glejser test)
bptest(reg)##
## studentized Breusch-Pagan test
##
## data: reg
## BP = 0.011757, df = 1, p-value = 0.9137res_X3 <- residuals(reg)
res_X3 <- abs(residuals(reg))
res_X3## 1 2 3 4 5 6
## 3.178128798 2.066837705 0.894031157 2.629004298 3.434874805 3.901223700
## 7 8 9 10 11 12
## 3.141449601 1.044623284 5.080652937 1.143316309 0.864608653 0.353572405
## 13 14 15 16 17 18
## 0.382957854 3.424450566 5.386042045 2.238563994 5.439915036 0.737175020
## 19 20 21 22 23 24
## 2.308903221 0.003719152 5.746153147 0.312099295 4.231574737 3.747906060
## 25 26 27 28 29 30
## 2.838802422 5.555682083 6.143746150 0.801720479 0.358071788 0.316864202
## 31 32 33 34 35 36
## 3.528741564 3.097974154 1.079617064 7.732759548 1.039057107 3.867861865
## 37 38 39 40 41 42
## 0.804145327 0.503917736 3.253062875 1.453929171 0.918638072 0.797836930
## 43 44 45 46 47 48
## 2.981158642 3.599405761 5.144268271 2.810750166 4.706345372 3.177781833
## 49 50 51 52 53 54
## 2.133985081 5.498089862 0.369248049 0.989217481 2.926183716 6.853911879
## 55 56 57 58 59 60
## 2.442581978 0.048426268 1.796041543 0.348149031 1.132342298 2.279708308
## 61 62 63 64 65 66
## 2.055318145 1.754860174 2.562142208 1.129571362 6.564182478 3.311492386
## 67 68 69 70
## 0.926941476 1.063905241 3.746721248 5.747567463uji_glejser <- lm(res_X3~X3, data=data)
summary(uji_glejser)##
## Call:
## lm(formula = res_X3 ~ X3, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5972 -1.6556 -0.2712 1.0587 5.1142
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.5755245 0.4870612 5.288 1.42e-06 ***
## X3 0.0004906 0.0040856 0.120 0.905
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.944 on 68 degrees of freedom
## Multiple R-squared: 0.000212, Adjusted R-squared: -0.01449
## F-statistic: 0.01442 on 1 and 68 DF, p-value: 0.9048#Uji Autokorelasi (Durbin-Watson test & Breusch-Godfrey)
# Uji AutoKorelasi (Durbin-Watson test dan Breusch-Godfrey test)
dwtest(reg)##
## Durbin-Watson test
##
## data: reg
## DW = 1.8485, p-value = 0.267
## alternative hypothesis: true autocorrelation is greater than 0bgtest(reg)##
## Breusch-Godfrey test for serial correlation of order up to 1
##
## data: reg
## LM test = 0.16062, df = 1, p-value = 0.6886#Uji Normalitas Residual (Shapiro-Wilk normality test)
# Uji Normalitas Residual (Shapiro-Wilk normality test)
shapiro.test(resid(reg))##
## Shapiro-Wilk normality test
##
## data: resid(reg)
## W = 0.98699, p-value = 0.6855#Regresi Linier Berganda
# Regresi Linier Berganda
reg=lm(formula=Y~X1+X2+X3 ,data=data)
summary(reg)##
## Call:
## lm(formula = Y ~ X1 + X2 + X3, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -8.1182 -2.5398 0.3152 2.1306 6.8115
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.082e+01 1.563e+00 6.918 2.26e-09 ***
## X1 1.831e-02 4.857e-02 0.377 0.707
## X2 5.376e-04 5.574e-04 0.964 0.338
## X3 3.644e-03 6.988e-03 0.522 0.604
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.323 on 66 degrees of freedom
## Multiple R-squared: 0.01948, Adjusted R-squared: -0.02509
## F-statistic: 0.437 on 3 and 66 DF, p-value: 0.7272vif(reg)## X1 X2 X3
## 1.008704 1.007946 1.001037#Pengujian Asumsi Klasik
#Uji Heteroskedastisitas (Breusch-Pagan test & Glejser test)
# Pengujian Asumsi Klasik
# Uji Heteroskedastisitas (Breusch-Pagan test dan Glejser test)
bptest(reg)##
## studentized Breusch-Pagan test
##
## data: reg
## BP = 1.0937, df = 3, p-value = 0.7786# Uji Heteroskedastisitas (Glejser test)
res_rlb <- residuals(reg)
res_rlb <- abs(residuals(reg))
res_rlb## 1 2 3 4 5 6 7
## 3.43774270 2.70426069 1.07625953 2.82316558 3.98361303 4.08932959 2.96370952
## 8 9 10 11 12 13 14
## 0.61150840 4.22468562 1.03857490 0.43367544 0.25124906 0.73270164 2.71011526
## 15 16 17 18 19 20 21
## 4.94090494 1.95839752 5.26673471 1.06680331 1.35155670 0.13743210 5.82359056
## 22 23 24 25 26 27 28
## 0.63874072 4.15569770 3.02646637 2.92629749 5.21280912 5.90184568 1.27208910
## 29 30 31 32 33 34 35
## 0.96996306 0.54902970 3.11501542 3.05291536 0.70682743 8.11823933 0.58079178
## 36 37 38 39 40 41 42
## 3.93710844 1.02804317 0.26997666 3.63737378 2.02398485 0.48270260 0.62415573
## 43 44 45 46 47 48 49
## 3.02438624 3.87829766 4.79842125 3.22272971 5.00160410 2.59768986 2.23430397
## 50 51 52 53 54 55 56
## 5.79517852 0.11541047 0.36038713 3.28713848 6.81149025 2.69470193 0.45008706
## 57 58 59 60 61 62 63
## 2.25142569 0.08322069 1.34303812 2.16619244 1.81655995 1.49354667 2.36624037
## 64 65 66 67 68 69 70
## 1.64253448 6.35818842 3.10418689 0.59452632 0.59909278 2.87654026 6.41236267uji_glejser <- lm(res_rlb~X1+X2+X3, data=data)
summary(uji_glejser)##
## Call:
## lm(formula = res_rlb ~ X1 + X2 + X3, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5924 -1.6649 -0.0417 1.1491 5.4722
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3525742 0.9317578 2.525 0.014 *
## X1 -0.0042367 0.0289474 -0.146 0.884
## X2 0.0001024 0.0003322 0.308 0.759
## X3 0.0010098 0.0041647 0.242 0.809
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.981 on 66 degrees of freedom
## Multiple R-squared: 0.002776, Adjusted R-squared: -0.04255
## F-statistic: 0.06124 on 3 and 66 DF, p-value: 0.98#Uji Autokorelasi (Durbin-Watson test & Breusch-Godfrey test)
# Uji AutoKorelasi (Durbin-Watson test dan Breusch-Godfrey test)
dwtest(reg)##
## Durbin-Watson test
##
## data: reg
## DW = 1.8021, p-value = 0.2102
## alternative hypothesis: true autocorrelation is greater than 0bgtest(reg)##
## Breusch-Godfrey test for serial correlation of order up to 1
##
## data: reg
## LM test = 0.32003, df = 1, p-value = 0.5716#Uji Normalitas Residual (Shapiro-Wilk normality test)
#Uji Normalitas Residual (Shapiro-Wilk normality test)
shapiro.test(resid(reg))##
## Shapiro-Wilk normality test
##
## data: resid(reg)
## W = 0.99083, p-value = 0.8932