SKENARIO
Y: Keputusan menolak/menerima pelamar kerja pada PT A posisi B
X1: Lama pengalaman kerja sebelumnya (bulan)
X2: Status pekerjaan saat ini (0: Bekerja, 1: Tidak Bekerja)
X3: Tingkat pendidikan (0: Lulusan Sekolah Menengah, 1: Lulusan Perguruan Tinggi)
X4: IPK (skala 4)
MEMBANGKITKAN DATA X1
X1: Lama pengalaman kerja sebelumnya (bulan). Membangkitkan variabel X1 dengan lama pekerjaan 0-60 bulan dengan nilai tengah 12 dan banyak pelamar adalah 100
set.seed(1234)
n <- 100
u <- runif(n)
X1 <- round(60*(-(log(1-u)/12)))
X1## [1] 1 5 5 5 10 5 0 1 5 4 6 4 2 13 2 9 2 2 1 1 2 2 1 0 1
## [26] 8 4 12 9 0 3 2 2 4 1 7 1 1 24 8 4 5 2 5 2 3 6 3 1 7
## [51] 0 2 6 4 1 4 3 7 1 9 10 0 2 0 1 6 2 4 0 4 1 11 0 8 0
## [76] 4 2 0 2 6 13 3 1 4 1 11 2 2 1 11 1 12 1 1 1 4 2 0 2 7MEMBANGKITKAN DATA X2
X2: Status pekerjaan. Keterangan yang digunakan (0: Tidak Bekerja) dan (1: Bekerja)
set.seed(12345)
X2 <- round(runif(n))
X2## [1] 1 1 1 1 0 0 0 1 1 1 0 0 1 0 0 0 0 0 0 1 0 0 1 1 1 0 1 1 0 0 1 0 0 1 0 0 1
## [38] 1 1 0 1 0 1 1 0 0 0 0 0 1 1 1 0 0 1 0 1 0 0 0 1 0 1 1 1 0 1 0 1 1 1 1 0 0
## [75] 0 1 1 1 1 0 1 1 0 0 0 0 1 1 1 0 1 1 0 1 1 1 1 1 0 0MEMBANGKITKAN DATA X3
X3: Tingkat pendidikan. Keterangan yang digunakan adalah (0: Lulusan Sekolah Menengah) dan (1: Lulusan Perguruan Tinggi)
set.seed(123)
X3 <- round(runif(n))
X3## [1] 0 1 0 1 1 0 1 1 1 0 1 0 1 1 0 1 0 0 0 1 1 1 1 1 1 1 1 1 0 0 1 1 1 1 0 0 1
## [38] 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 1 0 1 0 0 1 1 0 1 0 0 0 1 0 1 1 1 0 1 1 1 0
## [75] 0 0 0 1 0 0 0 1 0 1 0 0 1 1 1 0 0 1 0 1 0 0 1 0 0 1MEMBANGKITKAN DATA X4
X4: Data IPK pelamar dengan skala 4
set.seed(134)
X4 <- round(rnorm(n,3,0.5),2)
X4## [1] 2.58 3.59 3.14 2.82 2.36 3.31 3.97 2.97 3.13 3.69 3.59 2.00 3.28 3.18 3.64
## [16] 3.51 2.48 2.93 2.64 1.93 3.32 2.25 3.73 2.67 2.92 2.42 3.08 3.07 3.73 3.65
## [31] 3.04 2.53 2.67 2.43 2.94 3.58 2.49 2.60 2.88 3.33 2.88 2.22 2.29 2.63 2.85
## [46] 2.90 3.82 2.08 2.06 2.46 2.50 3.80 3.56 3.01 2.66 2.65 2.84 3.01 2.88 3.24
## [61] 3.43 3.75 4.04 2.60 2.76 2.09 3.23 2.98 2.39 2.21 2.94 2.08 2.40 3.72 3.08
## [76] 4.04 3.17 3.74 2.57 1.98 2.06 3.31 2.91 3.14 2.37 2.41 2.74 2.93 3.82 3.83
## [91] 2.67 2.11 2.43 2.78 2.37 2.93 2.66 3.83 3.12 4.23set.seed(165)
X44 <- round(rnorm(n,2.7,0.5),2)
X44## [1] 2.10 4.01 2.85 2.92 3.10 3.47 1.69 2.99 1.93 2.84 2.49 2.20 2.95 2.39 2.88
## [16] 2.57 2.35 2.64 2.77 2.83 3.46 2.92 2.62 1.93 2.74 2.07 2.84 2.65 2.19 3.50
## [31] 3.94 2.60 2.54 2.59 3.25 2.91 3.34 2.73 2.75 2.70 2.93 3.18 2.70 2.88 2.87
## [46] 2.92 2.08 2.80 2.67 2.78 3.37 3.12 2.73 1.74 2.79 2.55 3.16 1.87 1.42 2.44
## [61] 2.82 3.24 3.67 2.30 2.97 2.94 2.98 3.00 2.56 1.72 2.65 2.57 2.92 3.31 3.45
## [76] 2.45 2.00 2.76 3.30 2.80 2.82 2.95 3.13 3.23 2.52 2.46 2.47 3.19 3.43 2.89
## [91] 2.84 2.50 3.30 2.89 2.70 3.46 3.71 2.77 3.41 2.99summary(X44)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1.420 2.558 2.820 2.793 3.025 4.010MEMBANGKITKAN DATA Y
Menentukan koef
b0 <- -11
b1 <- 3.5
b2 <- 0.5
b3 <- 2.7
b4 <- 2.2
set.seed(1)
datapendukung <- b0+(b1*X1)+(b2*X2)+(b3*X3)+(b4*X4)
datapendukung## [1] -1.324 17.598 13.908 15.904 31.892 13.782 0.434 2.234 16.586 11.618
## [11] 20.598 7.400 6.416 44.196 4.008 30.922 1.456 2.446 -1.692 -0.054
## [21] 6.004 3.650 3.906 -1.926 2.124 25.024 12.976 40.954 28.706 -2.970
## [31] 9.388 4.266 4.574 11.546 -1.032 21.376 1.178 -1.280 79.836 24.326
## [41] 9.836 11.384 1.538 12.786 2.270 5.880 18.404 4.076 -2.968 22.112
## [51] -5.000 4.860 20.532 9.622 1.552 8.830 6.248 22.822 1.536 27.628
## [61] 34.746 -2.750 5.388 -4.780 1.772 14.598 6.306 12.256 -2.542 8.362
## [71] 2.168 35.276 -3.020 25.184 -4.224 12.388 3.474 0.428 2.154 14.356
## [81] 39.532 9.982 -1.098 12.608 -2.286 32.802 5.228 5.646 4.104 35.926
## [91] -1.126 38.842 -2.154 1.816 -1.786 9.946 5.052 -2.074 2.864 25.506p <- exp(datapendukung)/(1+exp(datapendukung))
p## [1] 0.210153568 0.999999977 0.999999088 0.999999876 1.000000000 0.999998966
## [7] 0.606828426 0.903261444 0.999999937 0.999990998 0.999999999 0.999389121
## [13] 0.998367486 1.000000000 0.982154548 1.000000000 0.810920123 0.920268446
## [19] 0.155513002 0.486503280 0.997537223 0.974667297 0.980276039 0.127193981
## [25] 0.893214061 1.000000000 0.999997685 1.000000000 1.000000000 0.048799723
## [31] 0.999916284 0.986156510 0.989788735 0.999990325 0.262696546 0.999999999
## [37] 0.764588008 0.217550224 1.000000000 1.000000000 0.999946512 0.999988624
## [43] 0.823173796 0.999997200 0.906361788 0.997213004 0.999999990 0.983308118
## [49] 0.048892643 1.000000000 0.006692851 0.992309124 0.999999999 0.999933749
## [55] 0.825202406 0.999853743 0.998069415 1.000000000 0.822882490 1.000000000
## [61] 1.000000000 0.060086650 0.995449694 0.008326093 0.854706214 0.999999543
## [67] 0.998178006 0.999995244 0.072965774 0.999766478 0.897338869 1.000000000
## [73] 0.046530475 1.000000000 0.014428731 0.999995832 0.969938868 0.605395986
## [79] 0.896041971 0.999999418 1.000000000 0.999953778 0.250114822 0.999996655
## [85] 0.092289091 1.000000000 0.994664379 0.996480813 0.983761524 1.000000000
## [91] 0.244900042 1.000000000 0.103958029 0.860085466 0.143563836 0.999952083
## [97] 0.993644128 0.111649686 0.946037865 1.000000000set.seed(2)
y <- rbinom(n,1,p)
y## [1] 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 1 1 1 0 1 1 1 1 1 0 1 1 1 1 1 1 1
## [38] 0 1 1 1 1 1 1 1 1 1 1 0 1 0 1 1 1 1 1 1 1 1 1 1 0 1 0 0 1 1 1 0 1 1 1 0 1
## [75] 0 1 1 1 1 1 1 1 0 1 0 1 1 1 1 1 1 1 0 1 0 1 1 0 1 1datagab <- data.frame(y,X1,X2,X3,X4)
datagab## y X1 X2 X3 X4
## 1 0 1 1 0 2.58
## 2 1 5 1 1 3.59
## 3 1 5 1 0 3.14
## 4 1 5 1 1 2.82
## 5 1 10 0 1 2.36
## 6 1 5 0 0 3.31
## 7 1 0 0 1 3.97
## 8 1 1 1 1 2.97
## 9 1 5 1 1 3.13
## 10 1 4 1 0 3.69
## 11 1 6 0 1 3.59
## 12 1 4 0 0 2.00
## 13 1 2 1 1 3.28
## 14 1 13 0 1 3.18
## 15 1 2 0 0 3.64
## 16 1 9 0 1 3.51
## 17 0 2 0 0 2.48
## 18 0 2 0 0 2.93
## 19 0 1 0 0 2.64
## 20 0 1 1 1 1.93
## 21 1 2 0 1 3.32
## 22 1 2 0 1 2.25
## 23 1 1 1 1 3.73
## 24 0 0 1 1 2.67
## 25 1 1 1 1 2.92
## 26 1 8 0 1 2.42
## 27 1 4 1 1 3.08
## 28 1 12 1 1 3.07
## 29 1 9 0 0 3.73
## 30 0 0 0 0 3.65
## 31 1 3 1 1 3.04
## 32 1 2 0 1 2.53
## 33 1 2 0 1 2.67
## 34 1 4 1 1 2.43
## 35 1 1 0 0 2.94
## 36 1 7 0 0 3.58
## 37 1 1 1 1 2.49
## 38 0 1 1 0 2.60
## 39 1 24 1 0 2.88
## 40 1 8 0 0 3.33
## 41 1 4 1 0 2.88
## 42 1 5 0 0 2.22
## 43 1 2 1 0 2.29
## 44 1 5 1 0 2.63
## 45 1 2 0 0 2.85
## 46 1 3 0 0 2.90
## 47 1 6 0 0 3.82
## 48 1 3 0 0 2.08
## 49 0 1 0 0 2.06
## 50 1 7 1 1 2.46
## 51 0 0 1 0 2.50
## 52 1 2 1 0 3.80
## 53 1 6 0 1 3.56
## 54 1 4 0 0 3.01
## 55 1 1 1 1 2.66
## 56 1 4 0 0 2.65
## 57 1 3 1 0 2.84
## 58 1 7 0 1 3.01
## 59 1 1 0 1 2.88
## 60 1 9 0 0 3.24
## 61 1 10 1 1 3.43
## 62 0 0 0 0 3.75
## 63 1 2 1 0 4.04
## 64 0 0 1 0 2.60
## 65 0 1 1 1 2.76
## 66 1 6 0 0 2.09
## 67 1 2 1 1 3.23
## 68 1 4 0 1 2.98
## 69 0 0 1 1 2.39
## 70 1 4 1 0 2.21
## 71 1 1 1 1 2.94
## 72 1 11 1 1 2.08
## 73 0 0 0 1 2.40
## 74 1 8 0 0 3.72
## 75 0 0 0 0 3.08
## 76 1 4 1 0 4.04
## 77 1 2 1 0 3.17
## 78 1 0 1 1 3.74
## 79 1 2 1 0 2.57
## 80 1 6 0 0 1.98
## 81 1 13 1 0 2.06
## 82 1 3 1 1 3.31
## 83 0 1 0 0 2.91
## 84 1 4 0 1 3.14
## 85 0 1 0 0 2.37
## 86 1 11 0 0 2.41
## 87 1 2 1 1 2.74
## 88 1 2 1 1 2.93
## 89 1 1 1 1 3.82
## 90 1 11 0 0 3.83
## 91 1 1 1 0 2.67
## 92 1 12 1 1 2.11
## 93 0 1 0 0 2.43
## 94 1 1 1 1 2.78
## 95 0 1 1 0 2.37
## 96 1 4 1 0 2.93
## 97 1 2 1 1 2.66
## 98 0 0 1 0 3.83
## 99 1 2 0 0 3.12
## 100 1 7 0 1 4.23ANALISIS REGRESI LOGISTIK
modelreglog <- glm(y~X1+X2+X3+X4, family = binomial(link = "logit"), data = datagab)## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredsummary(modelreglog)##
## Call:
## glm(formula = y ~ X1 + X2 + X3 + X4, family = binomial(link = "logit"),
## data = datagab)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -17.062 5.597 -3.049 0.002300 **
## X1 3.773 1.088 3.470 0.000521 ***
## X2 1.485 1.229 1.208 0.226928
## X3 3.214 1.180 2.723 0.006460 **
## X4 3.887 1.459 2.664 0.007714 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 102.791 on 99 degrees of freedom
## Residual deviance: 25.257 on 95 degrees of freedom
## AIC: 35.257
##
## Number of Fisher Scoring iterations: 9