Transformasi
Muayyad
May 26, 2021
Transformasi
Data 1
#=========================================DATA WINDMILL=======================================
#read excel
library(readxl)
windmill=read_excel("E:\\praktikum 12.xlsx",sheet="Sheet1")
windmill## # A tibble: 25 x 2
## x y
## <dbl> <dbl>
## 1 5 1.58
## 2 6 1.82
## 3 3.4 1.06
## 4 2.7 0.5
## 5 10 2.24
## 6 9.7 2.39
## 7 9.55 2.29
## 8 3.05 0.558
## 9 8.15 2.17
## 10 6.2 1.87
## # ... with 15 more rowsmodel regresi
windmill_mod=lm(y~x,data=windmill)
summary(windmill_mod)##
## Call:
## lm(formula = y ~ x, data = windmill)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.59869 -0.14099 0.06059 0.17262 0.32184
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.13088 0.12599 1.039 0.31
## x 0.24115 0.01905 12.659 7.55e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2361 on 23 degrees of freedom
## Multiple R-squared: 0.8745, Adjusted R-squared: 0.869
## F-statistic: 160.3 on 1 and 23 DF, p-value: 7.546e-12anova(windmill_mod)## Analysis of Variance Table
##
## Response: y
## Df Sum Sq Mean Sq F value Pr(>F)
## x 1 8.9296 8.9296 160.26 7.546e-12 ***
## Residuals 23 1.2816 0.0557
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1plot x dan y
plot(y~x,data=windmill, main="Kecepatan Angin (X) dan keluaran DC (Y)",
xlab="Kecepatan Angin (X)",ylab="keluaran DC (Y)",col="steelblue",pch=1)
abline(windmill_mod,col="red")
cek residual
plot(predict(windmill_mod),residuals(windmill_mod),xlab="y duga",
ylab="sisaan",pch=19,main="Plot Sisaan vs Y duga")
abline(c(0,0),lty=2,col="red")
transformasi x
c=1/(windmill$x)
windmill1=data.frame(windmill$y,c)
colnames(windmill1)=c("Y","X")
windmill1## Y X
## 1 1.582 0.20000000
## 2 1.822 0.16666667
## 3 1.057 0.29411765
## 4 0.500 0.37037037
## 5 2.236 0.10000000
## 6 2.386 0.10309278
## 7 2.294 0.10471204
## 8 0.558 0.32786885
## 9 2.166 0.12269939
## 10 1.866 0.16129032
## 11 0.653 0.34482759
## 12 1.930 0.15748031
## 13 1.562 0.21739130
## 14 1.737 0.17241379
## 15 2.088 0.13513514
## 16 1.137 0.27777778
## 17 2.179 0.12738854
## 18 2.112 0.11363636
## 19 1.800 0.14285714
## 20 1.501 0.18348624
## 21 2.303 0.10989011
## 22 2.310 0.09803922
## 23 1.194 0.24390244
## 24 1.144 0.25316456
## 25 0.123 0.40816327model regresi setelah tranformasi
windmill_trans_mod=lm(Y~X,data=windmill1)
summary(windmill_trans_mod)##
## Call:
## lm(formula = Y ~ X, data = windmill1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.20547 -0.04940 0.01100 0.08352 0.12204
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.9789 0.0449 66.34 <2e-16 ***
## X -6.9345 0.2064 -33.59 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.09417 on 23 degrees of freedom
## Multiple R-squared: 0.98, Adjusted R-squared: 0.9792
## F-statistic: 1128 on 1 and 23 DF, p-value: < 2.2e-16anova(windmill_trans_mod)## Analysis of Variance Table
##
## Response: Y
## Df Sum Sq Mean Sq F value Pr(>F)
## X 1 10.007 10.0072 1128.4 < 2.2e-16 ***
## Residuals 23 0.204 0.0089
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1plot(Y~X,data=windmill1,main="Kecepatan Angin (1/X) dan keluaran DC (Y)",
xlab="Kecepatan Angin (1/X)",ylab="keluaran DC (Y)",col="steelblue",pch=1)
abline(windmill_trans_mod,col="red")
cek residual
plot(predict(windmill_trans_mod),residuals(windmill_trans_mod),xlab="y duga",
ylab="sisaan",pch=19,main="Plot Sisaan vs Y duga")
abline(c(0,0),lty=2,col="red")
Data 2
#===================================INITECH======================================
#Data format csv
initech=read.csv("E:\\initech.csv")
initech## years salary
## 1 1 41504
## 2 1 32619
## 3 1 44322
## 4 2 40038
## 5 2 46147
## 6 2 38447
## 7 2 38163
## 8 3 42104
## 9 3 25597
## 10 3 39599
## 11 3 55698
## 12 4 47220
## 13 4 65929
## 14 4 55794
## 15 4 45959
## 16 5 52460
## 17 5 60308
## 18 5 61458
## 19 5 56951
## 20 6 56174
## 21 6 59363
## 22 6 57642
## 23 6 69792
## 24 7 59321
## 25 7 66379
## 26 7 64282
## 27 7 48901
## 28 8 100711
## 29 8 59324
## 30 8 54752
## 31 8 73619
## 32 9 65382
## 33 9 58823
## 34 9 65717
## 35 9 92816
## 36 9 72550
## 37 10 71365
## 38 10 88888
## 39 10 62969
## 40 10 45298
## 41 11 111292
## 42 11 91491
## 43 11 106345
## 44 11 99009
## 45 12 73981
## 46 12 72547
## 47 12 74991
## 48 12 139249
## 49 13 119948
## 50 13 128962
## 51 13 98112
## 52 13 97159
## 53 14 125246
## 54 14 89694
## 55 14 73333
## 56 14 108710
## 57 15 97567
## 58 15 90359
## 59 15 119806
## 60 15 101343
## 61 16 147406
## 62 16 153020
## 63 16 143200
## 64 16 97327
## 65 17 184807
## 66 17 146263
## 67 17 127925
## 68 17 159785
## 69 17 174822
## 70 18 177610
## 71 18 210984
## 72 18 160044
## 73 18 137044
## 74 19 182996
## 75 19 184183
## 76 19 168666
## 77 19 121350
## 78 20 193627
## 79 20 142611
## 80 20 170131
## 81 20 134140
## 82 21 129446
## 83 21 201469
## 84 21 202104
## 85 21 220556
## 86 22 166419
## 87 22 149044
## 88 22 247017
## 89 22 247730
## 90 23 252917
## 91 23 235517
## 92 23 241276
## 93 23 197229
## 94 24 175879
## 95 24 253682
## 96 24 262578
## 97 24 207715
## 98 25 221179
## 99 25 212028
## 100 25 312549plot(salary ~ years, data = initech, col = "grey", pch = 20, cex = 1.5,
main = "Salaries at Initech, By Seniority")
model regresi
initech_mod=lm(salary ~ years,data=initech)
summary(initech_mod)##
## Call:
## lm(formula = salary ~ years, data = initech)
##
## Residuals:
## Min 1Q Median 3Q Max
## -57225 -18104 241 15589 91332
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5302 5750 0.922 0.359
## years 8637 389 22.200 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 27360 on 98 degrees of freedom
## Multiple R-squared: 0.8341, Adjusted R-squared: 0.8324
## F-statistic: 492.8 on 1 and 98 DF, p-value: < 2.2e-16anova(initech_mod)## Analysis of Variance Table
##
## Response: salary
## Df Sum Sq Mean Sq F value Pr(>F)
## years 1 3.6878e+11 3.6878e+11 492.82 < 2.2e-16 ***
## Residuals 98 7.3334e+10 7.4830e+08
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1plot x dan y
plot(salary ~ years, data = initech, col = "grey", pch = 20, cex = 1.5,
main = "Salaries at Initech, By Seniority")
abline(initech_mod,col="red")
cek residual
plot(predict(initech_mod),residuals(initech_mod),xlab="y duga",
ylab="sisaan",pch=19,main="Plot Sisaan vs Y duga")
abline(c(0,0),lty=2,col="red")
transformasi y
y1=log(initech$salary)
initech1=data.frame(initech$years,y1)
colnames(initech1)=c("years","salary1")
initech1## years salary1
## 1 1 10.63355
## 2 1 10.39265
## 3 1 10.69924
## 4 2 10.59758
## 5 2 10.73959
## 6 2 10.55704
## 7 2 10.54962
## 8 3 10.64790
## 9 3 10.15023
## 10 3 10.58656
## 11 3 10.92770
## 12 4 10.76257
## 13 4 11.09633
## 14 4 10.92942
## 15 4 10.73550
## 16 5 10.86781
## 17 5 11.00722
## 18 5 11.02611
## 19 5 10.94995
## 20 6 10.93621
## 21 6 10.99143
## 22 6 10.96201
## 23 6 11.15327
## 24 7 10.99072
## 25 7 11.10314
## 26 7 11.07103
## 27 7 10.79755
## 28 8 11.52001
## 29 8 10.99077
## 30 8 10.91057
## 31 8 11.20666
## 32 9 11.08800
## 33 9 10.98229
## 34 9 11.09311
## 35 9 11.43837
## 36 9 11.19203
## 37 10 11.17556
## 38 10 11.39513
## 39 10 11.05040
## 40 10 10.72102
## 41 11 11.61991
## 42 11 11.42400
## 43 11 11.57444
## 44 11 11.50297
## 45 12 11.21156
## 46 12 11.19199
## 47 12 11.22512
## 48 12 11.84402
## 49 13 11.69481
## 50 13 11.76727
## 51 13 11.49386
## 52 13 11.48410
## 53 14 11.73804
## 54 14 11.40416
## 55 14 11.20277
## 56 14 11.59644
## 57 15 11.48829
## 58 15 11.41155
## 59 15 11.69363
## 60 15 11.52627
## 61 16 11.90095
## 62 16 11.93832
## 63 16 11.87200
## 64 16 11.48583
## 65 17 12.12707
## 66 17 11.89316
## 67 17 11.75920
## 68 17 11.98158
## 69 17 12.07152
## 70 18 12.08735
## 71 18 12.25954
## 72 18 11.98320
## 73 18 11.82806
## 74 19 12.11722
## 75 19 12.12369
## 76 19 12.03568
## 77 19 11.70643
## 78 20 12.17369
## 79 20 11.86788
## 80 20 12.04432
## 81 20 11.80664
## 82 21 11.77102
## 83 21 12.21339
## 84 21 12.21654
## 85 21 12.30391
## 86 22 12.02226
## 87 22 11.91200
## 88 22 12.41721
## 89 22 12.42009
## 90 23 12.44082
## 91 23 12.36954
## 92 23 12.39370
## 93 23 12.19212
## 94 24 12.07755
## 95 24 12.44384
## 96 24 12.47830
## 97 24 12.24392
## 98 25 12.30673
## 99 25 12.26447
## 100 25 12.65252model regresi setelah tranformasi
initech_trans_mod=lm(salary1~years,data=initech1)
summary(initech_trans_mod)##
## Call:
## lm(formula = salary1 ~ years, data = initech1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.57022 -0.13560 0.03048 0.14157 0.41366
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 10.48381 0.04108 255.18 <2e-16 ***
## years 0.07888 0.00278 28.38 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.1955 on 98 degrees of freedom
## Multiple R-squared: 0.8915, Adjusted R-squared: 0.8904
## F-statistic: 805.2 on 1 and 98 DF, p-value: < 2.2e-16anova(initech_trans_mod)## Analysis of Variance Table
##
## Response: salary1
## Df Sum Sq Mean Sq F value Pr(>F)
## years 1 30.7616 30.7616 805.22 < 2.2e-16 ***
## Residuals 98 3.7439 0.0382
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1plot(salary1~years,data=initech1,main="Salaries at Initech, By Seniority",
xlab="years (X)",ylab="Salary ln(Y)",col="steelblue",pch=1)
abline(initech_trans_mod,col="red")
cek residual
plot(predict(initech_trans_mod),residuals(initech_trans_mod),xlab="y duga",
ylab="sisaan",pch=19,main="Plot Sisaan vs Y duga")
abline(c(0,0),lty=2,col="red")