Tugas PSD Sesi UTS

Data

library(rio)
data.areg <- import("https://raw.githubusercontent.com/akmalbasisjkusumah/MPDW/main/Data/datapsd.csv")
data.areg <- data.areg[,-c(1,13,14)]
colnames(data.areg)
##  [1] "Y"   "X1"  "X2"  "X3"  "X4"  "X5"  "X6"  "X7"  "X8"  "X9"  "X10"
colnames(data.areg) <- c("PPM", "x1", "x2", "x3", "x4", "x5", "x6", "x7", "x8", "x9", "x10")
str(data.areg)
## 'data.frame':    34 obs. of  11 variables:
##  $ PPM: num  14.7 8.38 5.98 6.81 7.66 ...
##  $ x1 : num  99.7 98.7 98.8 95.2 98.4 ...
##  $ x2 : num  6.07 5.82 6.22 4.38 4.64 ...
##  $ x3 : num  3.17 2.52 2.51 2.94 2.7 ...
##  $ x4 : num  77.5 82.3 69.3 84.1 79.5 ...
##  $ x5 : num  4.21 4.73 4.36 4.55 5.13 5.23 4.31 4.28 4.4 5.09 ...
##  $ x6 : num  99.4 99.5 99.5 99.6 99.3 ...
##  $ x7 : num  98 96.8 96.5 95.7 96.2 ...
##  $ x8 : num  83.1 78.7 83.7 77.3 72.5 ...
##  $ x9 : num  99.6 99.6 99.9 99.9 99.5 ...
##  $ x10: num  44.3 47.6 47.7 47.9 49.5 ...
head(data.areg,10)
##       PPM    x1    x2       x3    x4   x5    x6    x7    x8    x9      x10
## 1  14.695 99.69 6.070 3.166460 77.48 4.21 99.44 97.96 83.10 99.62 44.28695
## 2   8.375 98.70 5.815 2.522610 82.30 4.73 99.50 96.78 78.66 99.57 47.61680
## 3   5.980 98.82 6.225 2.512539 69.27 4.36 99.55 96.52 83.71 99.86 47.65741
## 4   6.810 95.20 4.385 2.938564 84.06 4.55 99.61 95.72 77.32 99.92 47.90955
## 5   7.660 98.39 4.645 2.698941 79.54 5.13 99.33 96.20 72.53 99.52 49.51169
## 6  11.925 96.55 4.685 3.144446 78.62 5.23 99.38 95.06 70.93 99.50 49.55185
## 7  14.480 99.21 3.490 2.238094 79.58 4.31 99.49 97.73 79.31 99.49 50.36144
## 8  11.505 98.66 4.415 2.440486 83.65 4.28 99.56 95.63 71.14 99.32 47.81690
## 9   4.530 99.53 4.475 3.264884 91.63 4.40 99.41 93.00 68.42 99.18 48.90753
## 10  6.135 97.96 8.125 3.050172 87.74 5.09 99.28 99.01 84.54 99.72 53.03225

Eksplorasi Data

library(corrplot)
## corrplot 0.92 loaded
kor <- cor(data.areg)
corrplot(kor, method = "square", type = "lower", diag = TRUE)
corrplot(kor, add=TRUE, method = 'number', type='upper',
         tl.pos = "lt", 
         tl.col = "black")

Dari plot korelasi berikut didapatkan bahwa beberapa peubah penjelas (x) tidak mempengaruhi peubah responnya. Yang tidak berpengaruh adalah peubah x3, x5, x8, dan x10. Sehingga peubah-peubah tersebut tidak disertakan pada model awal regresi.

Model Awal

fit <- lm(PPM ~ x1+x2+x4+x6+x7+x9, data = data.areg)
summary(fit)
## 
## Call:
## lm(formula = PPM ~ x1 + x2 + x4 + x6 + x7 + x9, data = data.areg)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -6.5844 -2.3450  0.1494  1.7711  7.8937 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)  
## (Intercept) 37.87218   56.47300   0.671   0.5082  
## x1          -0.06177    0.19422  -0.318   0.7529  
## x2          -0.99761    0.52026  -1.918   0.0658 .
## x4          -0.27149    0.11827  -2.295   0.0297 *
## x6           0.15040    1.10607   0.136   0.8928  
## x7           0.63230    0.35366   1.788   0.0850 .
## x9          -0.71149    0.57004  -1.248   0.2227  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.809 on 27 degrees of freedom
## Multiple R-squared:  0.572,  Adjusted R-squared:  0.4768 
## F-statistic: 6.013 on 6 and 27 DF,  p-value: 0.0004317
model1 <- summary(fit)
anova(fit)
## Analysis of Variance Table
## 
## Response: PPM
##           Df Sum Sq Mean Sq F value    Pr(>F)    
## x1         1 357.58  357.58 24.6420 3.354e-05 ***
## x2         1  42.89   42.89  2.9556   0.09703 .  
## x4         1  51.98   51.98  3.5823   0.06917 .  
## x6         1   1.21    1.21  0.0832   0.77523    
## x7         1  47.25   47.25  3.2564   0.08231 .  
## x9         1  22.61   22.61  1.5579   0.22269    
## Residuals 27 391.80   14.51                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Didapatkan model awal seperti diatas dengan peubah yang signifikan pada model hanya x4. Dapat diketahui juga bahwa nilai Adj. R-Squared 47,68%. Intersep merupakan nilai dari peubah respon ketika semua nilai peubah penjelasnya 0. Estimate merupakan koefisien dari peubah penjelasnya dengan makna bahwa setiap penambahan satu satuan peubah penjelas akan meningkatkan/menurunkan(Tergantung pada tanda koefisien) nilai peubah respon.

Deteksi Pencilan dan Leverage

library(olsrr)
## 
## Attaching package: 'olsrr'
## The following object is masked from 'package:datasets':
## 
##     rivers
#titik pencilan
sisaan<-residuals(fit)
stdr.sisaan<-rstandard(fit)
mut.stdr.sisaan<-abs(stdr.sisaan)
pencilll <- data.frame(sort(mut.stdr.sisaan))
pencilan <- data.frame(pencilll, pencilll>2)
pencilan
##    sort.mut.stdr.sisaan. sort.mut.stdr.sisaan..1
## 11            0.03208269                   FALSE
## 10            0.10076922                   FALSE
## 12            0.12838322                   FALSE
## 2             0.15340447                   FALSE
## 16            0.20680181                   FALSE
## 26            0.28563803                   FALSE
## 25            0.29641059                   FALSE
## 9             0.30375081                   FALSE
## 30            0.35358166                   FALSE
## 13            0.38640749                   FALSE
## 23            0.38802062                   FALSE
## 15            0.39814576                   FALSE
## 28            0.44583283                   FALSE
## 6             0.47976960                   FALSE
## 7             0.54088472                   FALSE
## 8             0.55589352                   FALSE
## 27            0.55934396                   FALSE
## 4             0.65304697                   FALSE
## 17            0.76400329                   FALSE
## 5             0.78143176                   FALSE
## 14            0.82555857                   FALSE
## 18            0.97996913                   FALSE
## 22            1.07770049                   FALSE
## 1             1.13939545                   FALSE
## 20            1.19738001                   FALSE
## 24            1.21748879                   FALSE
## 34            1.49325346                   FALSE
## 31            1.54650308                   FALSE
## 32            1.58183014                   FALSE
## 19            1.60760194                   FALSE
## 29            1.69126476                   FALSE
## 3             1.73105128                   FALSE
## 21            2.06896331                    TRUE
## 33            2.40649777                    TRUE
#titik leverage
hi<-hatvalues(fit, infl = influence(fit))
ambang_batas<-2*(10/34) #2p/n, p=10, n=34
leveragee <- data.frame(hi, hi>ambang_batas)
leveragee
##            hi hi...ambang_batas
## 1  0.12734347             FALSE
## 2  0.04584987             FALSE
## 3  0.24657847             FALSE
## 4  0.07077431             FALSE
## 5  0.07382134             FALSE
## 6  0.05592525             FALSE
## 7  0.19237301             FALSE
## 8  0.04738742             FALSE
## 9  0.18879108             FALSE
## 10 0.19074472             FALSE
## 11 0.19833398             FALSE
## 12 0.30339477             FALSE
## 13 0.07680496             FALSE
## 14 0.27102365             FALSE
## 15 0.13135635             FALSE
## 16 0.19671686             FALSE
## 17 0.17997014             FALSE
## 18 0.65711832              TRUE
## 19 0.22034887             FALSE
## 20 0.20612615             FALSE
## 21 0.30206125             FALSE
## 22 0.07969125             FALSE
## 23 0.14465533             FALSE
## 24 0.06275433             FALSE
## 25 0.10842827             FALSE
## 26 0.20949065             FALSE
## 27 0.31991966             FALSE
## 28 0.08470056             FALSE
## 29 0.21237887             FALSE
## 30 0.28101722             FALSE
## 31 0.13424305             FALSE
## 32 0.13588044             FALSE
## 33 0.25853616             FALSE
## 34 0.98545997              TRUE
#titik pencilan dan leverage
ols_plot_resid_lev(fit)

Dapat diketahui dari plot tersebut terdapat pencilan pada amatan ke 33 dan 21. sementara untuk leverage terdeteksi pada amatan ke 18 dan 34.

Deteksi Amatan Berpengaruh

#============Deteksi amatan berpengaruh =============
#Cook's Distance
di<-cooks.distance(fit)
f<-qf(0.05,10,24, lower.tail = F) # qf(p,db1,db2, lower.tail=F). db1=n-p, db2=n-p, lower.tail=F untuk p=taraf nyata(alpha) dan sebaliknya untuk p= (1-alpha)
data.frame(di, di>f)
##              di di...f
## 1  2.706352e-02  FALSE
## 2  1.615472e-04  FALSE
## 3  1.401003e-01  FALSE
## 4  4.640291e-03  FALSE
## 5  6.952984e-03  FALSE
## 6  1.947910e-03  FALSE
## 7  9.955078e-03  FALSE
## 8  2.195998e-03  FALSE
## 9  3.067507e-03  FALSE
## 10 3.419202e-04  FALSE
## 11 3.637871e-05  FALSE
## 12 1.025510e-03  FALSE
## 13 1.774552e-03  FALSE
## 14 3.619858e-02  FALSE
## 15 3.424487e-03  FALSE
## 16 1.496179e-03  FALSE
## 17 1.830051e-02  FALSE
## 18 2.629215e-01  FALSE
## 19 1.043445e-01  FALSE
## 20 5.317991e-02  FALSE
## 21 2.646581e-01  FALSE
## 22 1.436730e-02  FALSE
## 23 3.637516e-03  FALSE
## 24 1.417823e-02  FALSE
## 25 1.526425e-03  FALSE
## 26 3.088813e-03  FALSE
## 27 2.102522e-02  FALSE
## 28 2.627660e-03  FALSE
## 29 1.101841e-01  FALSE
## 30 6.980650e-03  FALSE
## 31 5.297847e-02  FALSE
## 32 5.620886e-02  FALSE
## 33 2.884724e-01  FALSE
## 34 2.158950e+01   TRUE
library(ggplot2)
cooks_crit = f
model_cooks <- cooks.distance(fit)
df <- data.frame(obs = names(model_cooks),
                 cooks = model_cooks)
ggplot(df, aes(y = cooks, x = obs)) +
  geom_point() +
  geom_hline(yintercept = cooks_crit, linetype="dashed") +
  labs(title = "Cook's Distance",
       subtitle = "Influential Observation ",
       x = "Observation Number",
       y = "Cook's")

ols_plot_cooksd_bar(fit)

#Deteksi amatan berpengaruh (dfbetas)
ols_plot_dfbetas(fit)

#Deteksi amatan berpengaruh (dffits)
ols_plot_dffits(fit)

Penanganan amatan tak berpengaruh

data.areg1 <- data.areg[-c(3,18,32),]
fit2 <- lm(PPM ~ x1+x2+x4+x6+x7+x9, data = data.areg1)
summary(fit2)
## 
## Call:
## lm(formula = PPM ~ x1 + x2 + x4 + x6 + x7 + x9, data = data.areg1)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -6.598 -1.760  0.410  1.537  6.904 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)   
## (Intercept) 14.00906   53.11994   0.264  0.79424   
## x1           0.02149    0.19292   0.111  0.91221   
## x2          -1.15536    0.49163  -2.350  0.02733 * 
## x4          -0.42336    0.12870  -3.289  0.00309 **
## x6           0.69755    1.15090   0.606  0.55014   
## x7           0.95692    0.36556   2.618  0.01509 * 
## x9          -1.27448    0.81635  -1.561  0.13157   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.504 on 24 degrees of freedom
## Multiple R-squared:  0.6606, Adjusted R-squared:  0.5758 
## F-statistic: 7.786 on 6 and 24 DF,  p-value: 0.0001003
model1 <- summary(fit2)
anova(fit2)
## Analysis of Variance Table
## 
## Response: PPM
##           Df Sum Sq Mean Sq F value    Pr(>F)    
## x1         1 372.66  372.66 30.3501 1.152e-05 ***
## x2         1  30.46   30.46  2.4805   0.12836    
## x4         1  77.51   77.51  6.3123   0.01912 *  
## x6         1   0.36    0.36  0.0293   0.86542    
## x7         1  62.70   62.70  5.1062   0.03320 *  
## x9         1  29.93   29.93  2.4373   0.13157    
## Residuals 24 294.69   12.28                      
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
data.areg2 <- data.areg[-c(18,32,34),]
fit3 <- lm(PPM ~ x1+x2+x4+x6+x7+x9, data = data.areg2)
summary(fit3)
## 
## Call:
## lm(formula = PPM ~ x1 + x2 + x4 + x6 + x7 + x9, data = data.areg2)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -6.096 -2.173  0.222  2.036  6.099 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)  
## (Intercept) 372.3404   223.3122   1.667   0.1084  
## x1            0.0282     0.2016   0.140   0.8899  
## x2           -1.0342     0.5139  -2.012   0.0555 .
## x4           -0.2747     0.1190  -2.309   0.0299 *
## x6           -3.2287     2.6280  -1.229   0.2311  
## x7            1.0376     0.3844   2.699   0.0125 *
## x9           -1.1754     0.8351  -1.407   0.1721  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.592 on 24 degrees of freedom
## Multiple R-squared:  0.4923, Adjusted R-squared:  0.3654 
## F-statistic: 3.879 on 6 and 24 DF,  p-value: 0.00757
model1 <- summary(fit3)
anova(fit3)
## Analysis of Variance Table
## 
## Response: PPM
##           Df  Sum Sq Mean Sq F value   Pr(>F)   
## x1         1 110.942 110.942  8.5970 0.007289 **
## x2         1  30.758  30.758  2.3834 0.135713   
## x4         1  46.548  46.548  3.6071 0.069620 . 
## x6         1  12.177  12.177  0.9436 0.341049   
## x7         1  74.335  74.335  5.7603 0.024507 * 
## x9         1  25.563  25.563  1.9809 0.172116   
## Residuals 24 309.714  12.905                    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
data.areg3 <- data.areg[-c(3,18,32,34),]
fit4 <- lm(PPM ~ x1+x2+x4+x6+x7+x9, data = data.areg3)
summary(fit4)
## 
## Call:
## lm(formula = PPM ~ x1 + x2 + x4 + x6 + x7 + x9, data = data.areg3)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -6.0313 -1.4163  0.2792  2.2636  5.5154 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)   
## (Intercept) 293.76578  219.38103   1.339  0.19363   
## x1            0.08906    0.19691   0.452  0.65530   
## x2           -1.02859    0.49390  -2.083  0.04860 * 
## x4           -0.38315    0.13045  -2.937  0.00740 **
## x6           -2.34161    2.57729  -0.909  0.37301   
## x7            1.06747    0.36988   2.886  0.00834 **
## x9           -1.26689    0.80432  -1.575  0.12889   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.452 on 23 degrees of freedom
## Multiple R-squared:  0.5395, Adjusted R-squared:  0.4194 
## F-statistic: 4.491 on 6 and 23 DF,  p-value: 0.00377
model1 <- summary(fit4)
anova(fit4)
## Analysis of Variance Table
## 
## Response: PPM
##           Df  Sum Sq Mean Sq F value   Pr(>F)   
## x1         1 104.074 104.074  8.7317 0.007102 **
## x2         1  27.892  27.892  2.3401 0.139718   
## x4         1  77.362  77.362  6.4906 0.017992 * 
## x6         1   5.112   5.112  0.4289 0.519026   
## x7         1  77.138  77.138  6.4718 0.018140 * 
## x9         1  29.571  29.571  2.4809 0.128889   
## Residuals 23 274.139  11.919                    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Didapatkan model terbaik adalah setelah menghapus amatan ke-3, 18, dan 32.

Seleksi Peubah

library(olsrr)
ols_step_backward_p(fit2)
## 
## 
##                           Elimination Summary                            
## ------------------------------------------------------------------------
##         Variable                  Adj.                                      
## Step    Removed     R-Square    R-Square     C(p)       AIC        RMSE     
## ------------------------------------------------------------------------
##    1    x1            0.6604      0.5925    5.0124    171.8004    3.4342    
##    2    x6            0.6533       0.600    3.5151    170.4427    3.4026    
## ------------------------------------------------------------------------
ols_step_forward_p(fit2)
## 
##                            Selection Summary                             
## ------------------------------------------------------------------------
##         Variable                  Adj.                                      
## Step    Entered     R-Square    R-Square     C(p)       AIC        RMSE     
## ------------------------------------------------------------------------
##    1    x4            0.5063      0.4893    7.9125    175.4029    3.8448    
##    2    x2            0.5491      0.5169    6.8855    174.5914    3.7393    
##    3    x7            0.5932      0.5480    5.7681    173.4019    3.6170    
##    4    x9            0.6533      0.6000    3.5151    170.4427    3.4026    
## ------------------------------------------------------------------------
ols_step_both_p(fit2)
## 
##                              Stepwise Selection Summary                              
## ------------------------------------------------------------------------------------
##                      Added/                   Adj.                                      
## Step    Variable    Removed     R-Square    R-Square     C(p)       AIC        RMSE     
## ------------------------------------------------------------------------------------
##    1       x4       addition       0.506       0.489    7.9130    175.4029    3.8448    
## ------------------------------------------------------------------------------------

Setelah dilakukan seleksi peubah didapatkan model baru yang memiliki aic dan R-Square lebih baik yaitu model yang menyertakan peubah x2, x4, x7, dan x9.

Model Baru

fit2new <- lm(PPM ~ x2+x4+x7+x9, data = data.areg1)
summary(fit2new)
## 
## Call:
## lm(formula = PPM ~ x2 + x4 + x7 + x9, data = data.areg1)
## 
## Residuals:
##    Min     1Q Median     3Q    Max 
## -7.018 -2.099  0.129  1.661  6.707 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 30.77689   25.03273   1.229 0.229908    
## x2          -1.20288    0.46226  -2.602 0.015093 *  
## x4          -0.37555    0.09508  -3.950 0.000533 ***
## x7           0.94536    0.34809   2.716 0.011592 *  
## x9          -0.74992    0.35310  -2.124 0.043362 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 3.403 on 26 degrees of freedom
## Multiple R-squared:  0.6533, Adjusted R-squared:    0.6 
## F-statistic: 12.25 on 4 and 26 DF,  p-value: 9.916e-06

Pengujian Asumsi Pada Sisaan

Asumsi Secara Ekslporatif

par(mfrow = c(2,2))
qqnorm(fit2new$residuals)
qqline(fit2new$residuals, col = "maroon", lwd = 2)
plot(fit2new$fitted.values, fit2new$residuals, col = "maroon", pch = 20, xlab = "Sisaan", ylab = "Fitted Values", main = "Sisaan vs Fitted Values")
abline(a = 0, b = 0, lwd = 2)
hist(fit2new$residuals, col = "maroon")
plot(fit2new$residuals, type="o", col = "maroon",
     ylab = "Sisaan", xlab = "Order", main = "Sisaan vs Order")

Berdasarkan uji asumsi secara eksploratif dapat diamati bahwa semua asumsi terpenuhi, untuk melihat kebenarannya dilakukan uji secara formal.

Uji Asumsi Formal

# Asumsi GAUSS MARKOV
# 1 Nilai harapan sisaan sama dengan nol
t.test(fit2new$residuals,
       mu = 0,
       conf.level = 0.95) #asumsi nilai harapan sama dengan 0 terpenuhi
## 
##  One Sample t-test
## 
## data:  fit2new$residuals
## t = 1.5721e-16, df = 30, p-value = 1
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
##  -1.161896  1.161896
## sample estimates:
##    mean of x 
## 8.944318e-17
# 2 Sisaan saling bebas
library(lmtest)
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
library(randtests)
runs.test(fit2new$residuals) #asumsi sisaan saling bebas terpenuhi
## 
##  Runs Test
## 
## data:  fit2new$residuals
## statistic = 0, runs = 16, n1 = 15, n2 = 15, n = 30, p-value = 1
## alternative hypothesis: nonrandomness
# 3 Ragam sisaan homogen
library(lmtest)
bptest(fit2new)
## 
##  studentized Breusch-Pagan test
## 
## data:  fit2new
## BP = 7.4709, df = 4, p-value = 0.113
# ASUMSI NORMALITAS SISAAN
shapiro.test(fit2new$residuals)
## 
##  Shapiro-Wilk normality test
## 
## data:  fit2new$residuals
## W = 0.98997, p-value = 0.9898
nortest::ad.test(fit2new$residuals)
## 
##  Anderson-Darling normality test
## 
## data:  fit2new$residuals
## A = 0.16852, p-value = 0.9283
ks.test(fit2new$residuals, "pnorm", mean=mean(fit2new$residuals), sd=sd(fit2new$residuals)) #asumsi normalitas terpenuhi
## 
##  Exact one-sample Kolmogorov-Smirnov test
## 
## data:  fit2new$residuals
## D = 0.081377, p-value = 0.9759
## alternative hypothesis: two-sided

Setelah dilakukan uji secara formal didapatkan nilai p-value untuk semua uji lebih besar dari 0,05. Artinya semua asumsi pada sisaan model terpenuhi.

Mendeteksi Multikolinearitas

library(car)
## Loading required package: carData
car::vif(fit2new)
##       x2       x4       x7       x9 
## 1.356330 2.351274 3.651151 3.486138

Tidak terdapat multikolinearitas pada model karena semua nilai vif < 10

Regresi Ridge (glmnet)

Library

lapply(c("glmnet","lmridge"),library,character.only=T)[[1]]
## Loading required package: Matrix
## Loaded glmnet 4.1-8
## 
## Attaching package: 'lmridge'
## The following object is masked from 'package:car':
## 
##     vif
##  [1] "glmnet"    "Matrix"    "car"       "carData"   "randtests" "lmtest"   
##  [7] "zoo"       "ggplot2"   "olsrr"     "corrplot"  "rio"       "stats"    
## [13] "graphics"  "grDevices" "utils"     "datasets"  "methods"   "base"

Cross validation (CV)

x <- data.matrix(data.areg1[,c('x2','x4','x7','x9')])
y <- data.areg1$PPM
cv.r<-cv.glmnet(x,y,alpha=0);plot(cv.r)

Best Model

best.lr<-cv.r$lambda.min
bestridge<-glmnet(x,y,alpha=0,lambda=best.lr);coef(bestridge)
## 5 x 1 sparse Matrix of class "dgCMatrix"
##                     s0
## (Intercept) 46.7799833
## x2          -0.8320764
## x4          -0.2849838
## x7           0.4196707
## x9          -0.4974478

R-Squared

rsq<-function(bestmodel,bestlambda,x,y){
 #y duga
 y.duga <- predict(bestmodel, s = bestlambda, newx = x)

 #JKG dan JKT
 jkt <- sum((y - mean(y))^2)
 jkg <- sum((y.duga- y)^2)

#find R-Squared
rsq <- 1 - jkg/jkt
return(rsq) 
}
rsq(bestridge,best.lr,x,y)
## [1] 0.6157579

Regresi Ridge (lmridge)

lmr<-lmridge(y~x,data.areg1,scaling="centered");plot(lmr);vif(lmr)

##         xx2     xx4     xx7     xx9
## k=0 0.01846 0.00078 0.01047 0.01077
summary(lmr)
## 
## Call:
## lmridge.default(formula = y ~ x, data = data.areg1, scaling = "centered")
## 
## 
## Coefficients: for Ridge parameter K= 0 
##           Estimate Estimate (Sc) StdErr (Sc) t-value (Sc) Pr(>|t|)    
## Intercept  30.7769       30.7769     47.7981       0.6439   0.5253    
## xx2        -1.2029       -1.2029      0.4536      -2.6518   0.0135 *  
## xx4        -0.3756       -0.3755      0.0933      -4.0248   0.0004 ***
## xx7         0.9454        0.9454      0.3416       2.7676   0.0103 *  
## xx9        -0.7499       -0.7499      0.3465      -2.1643   0.0398 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Ridge Summary
##        R2    adj-R2  DF ridge         F       AIC       BIC 
##   0.65330   0.61480   3.99999  12.72090  78.46849 190.65803 
## Ridge minimum MSE= 0.4512104 at K= 0 
## P-value for F-test ( 3.99999 , 27.00004 ) = 6.03948e-06 
## -------------------------------------------------------------------
rsq(lmr,best.lr,as.matrix(data.areg1[,-1]),data.areg1$PPM)
## [1] 0.6533285

Regresi Lasso

Cross validation (CV)

cv.l<-cv.glmnet(x,y,alpha=1);plot(cv.l)

Best model

best.ll<-cv.l$lambda.min
bestlasso<-glmnet(x,y,alpha=1,lambda=best.ll);coef(bestlasso)
## 5 x 1 sparse Matrix of class "dgCMatrix"
##                     s0
## (Intercept) 37.9165268
## x2          -0.1301254
## x4          -0.2463224
## x7           .        
## x9          -0.0690297

R-Squared

rsq(bestlasso,best.ll,x,y)
## [1] 0.480572

Perbandingan Model

RSE Model Regresi Lasso

# Prediksi model Lasso pada data pelatihan
train_predictionsLasso <- predict(bestlasso,newx = x)

# Hitung residu (selisih antara prediksi dan nilai sebenarnya)
residualsLasso <- y - train_predictionsLasso

# Hitung varian residu
dfLasso <- length(y) - length(bestlasso$beta)
residual_varianceLasso <- sum(residualsLasso^2) / dfLasso

# Hitung RSE
rseLasso <- sqrt(residual_varianceLasso)

# Tampilkan hasil RSE
print(paste("Residual Standard Error (RSE):",rseLasso))
## [1] "Residual Standard Error (RSE): 4.08711509567627"

RSE Model Regresi Ridge

# Prediksi model ridge pada data pelatihan
train_predictionsridge <- predict(bestridge,newx = x)

# Hitung residu (selisih antara prediksi dan nilai sebenarnya)
residualsridge <- y - train_predictionsridge

# Hitung varian residu
dfridge <- length(y) - length(bestridge$beta)
residual_varianceridge <- sum(residualsridge^2) / dfridge

# Hitung RSE
rseridge <- sqrt(residual_varianceridge)

# Tampilkan hasil RSE
print(paste("Residual Standard Error (RSE):",rseridge))
## [1] "Residual Standard Error (RSE): 3.51525330870488"

Diakhir kita akan membandingkan nilai setiap RSE dan R-Square diperoleh :

Model Regresi R-Square RSE
fit 47.68% 3.8090
fit2new 60% 3.4030
Model Ridge 61.48% 3.8013
Model Lasso 53.07% 3.8852

INTEPRETASI

Dari residual standard error (RSE) yang diperoleh pada setiap model yang dicobakan maka kita akan memilih yang memiliki RSE terkecil. Pada analisis kali ini didapatkan model terbaiknya adalah pada model fit2new atau model setelah dilakukannya seleksi peubah menggunakan forward stepwise. Sementara metode penyusutan tidak begitu berpengaruh karena dari awal tidak terjadi multikolinearitas.