Membangkitkan Data

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: Lulusah 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 banyaknya pelamar adalah 100

set.seed(100)
n <- 100
u <- runif(n)

X1 <- round(60*(-log(1-u)/12))
X1
##   [1]  2  1  4  0  3  3  8  2  4  1  5 11  2  3  7  6  1  2  2  6  4  6  4  7  3
##  [26]  1  7 11  4  2  3 13  2 15  6 11  1  5 23  1  2 10  8  9  5  3  8 11  1  2
##  [51]  2  1  1  2  4  1  1  1  5  1  3  5 16  6  3  2  3  3  1  6  3  2  4 17  5
##  [76]  5 10  7  9  0  3  5 13 20  0  4  7  1  2  7 12  1  2  3 12  2  4  1  0  7

Membangkitkan Data X2

X2 :Status pekerjaan saat ini (0: Bekerja, 1: Tidak bekerja)

set.seed(101)
X2 <- round(runif(n))
X2
##   [1] 0 0 1 1 0 0 1 0 1 1 1 1 1 1 0 1 1 0 0 0 1 1 0 1 1 1 0 0 0 1 0 0 0 0 1 1 0
##  [38] 1 0 1 0 0 1 0 0 0 0 1 1 0 0 0 1 1 0 1 1 1 1 1 1 1 1 1 1 1 0 0 1 1 0 1 1 1
##  [75] 1 0 0 0 1 1 1 1 1 1 0 1 0 0 0 0 1 1 1 0 0 1 0 0 0 0

Membangkitkan Data X3

X3 :Tingkat pendidikan (0: Lulusah Sekolah Menengah, 1: Lulusan Perguruan Tinggi)

set.seed(102)
X3 <- round(runif(n))
X3
##   [1] 1 0 1 1 0 0 1 0 1 0 1 1 1 0 1 1 1 0 1 1 1 1 1 1 0 0 0 0 0 0 0 1 0 1 1 0 0
##  [38] 1 1 0 1 1 0 0 0 0 0 0 0 1 0 1 1 0 1 0 1 0 1 1 1 0 0 1 0 1 0 0 1 1 1 1 1 0
##  [75] 0 0 1 0 1 0 1 0 1 1 0 0 0 1 1 0 0 0 1 1 0 0 1 0 0 0

Membangkitkan Data X4

X4 :IPK (skala 4)

set.seed(103)
X4 <- round(rnorm(n,3,0.5),2)
X4
##   [1] 2.61 3.03 2.41 2.92 2.07 2.94 3.41 3.60 2.45 2.81 2.53 3.02 3.06 4.29 2.87
##  [16] 2.56 3.23 3.06 2.88 3.40 3.46 3.13 2.88 2.26 2.40 3.37 2.75 3.59 3.48 3.07
##  [31] 2.49 3.35 3.30 3.22 2.99 2.68 3.17 3.64 1.93 3.13 3.16 3.52 3.07 2.76 3.10
##  [46] 2.98 3.54 3.04 2.50 3.24 2.92 2.34 3.47 3.14 3.43 2.77 2.77 3.15 3.87 2.93
##  [61] 4.00 3.51 3.27 2.31 2.76 3.23 3.06 2.98 2.53 2.70 2.39 2.78 2.47 3.45 2.97
##  [76] 2.49 3.44 3.46 2.52 3.02 3.88 3.76 3.41 3.86 2.31 3.32 2.75 2.31 3.08 3.02
##  [91] 3.33 2.64 3.67 2.34 2.75 2.52 2.34 3.86 2.24 2.61

Membangkitkan Data Y

Menentukan Koef

b0 <- -10
b1 <- 3.5
b2 <- 0.5
b3 <- 2.7
b4 <- 3.2
set.seed(104)
datapendukung <- b0+(b1*X1)+(b2*X2)+(b3*X3)+(b4*X4)
datapendukung
##   [1]  8.052  3.196 14.912  2.544  7.124  9.908 32.112  8.520 15.040  2.992
##  [11] 18.796 41.364  9.992 14.728 26.384 22.392  7.036  6.792  8.916 24.580
##  [21] 18.272 24.216 15.916 24.932  8.680  4.784 23.300 39.988 15.136  7.324
##  [31]  8.468 48.920  7.560 55.504 23.768 37.576  3.644 22.348 79.376  4.016
##  [41]  9.812 38.964 28.324 30.332 17.420 10.036 29.328 38.728  2.000 10.068
##  [51]  6.344  3.688  7.804  7.548 17.676  2.864  5.564  4.080 23.084  6.076
##  [61] 16.500 19.232 56.964 21.592  9.832 10.536 10.292 10.036  4.796 22.840
##  [71] 10.848  9.096 15.104 61.040 17.504 15.468 38.708 25.572 32.764  0.164
##  [81] 16.116 20.032 49.612 75.552 -2.608 15.124 23.300  3.592  9.556 24.164
##  [91] 43.156  2.448 11.944 10.688 40.800  5.564 14.188  5.852 -2.832 22.852
p <- exp(datapendukung)/(1+exp(datapendukung))
p
##   [1] 0.99968164 0.96068347 0.99999967 0.92716939 0.99919511 0.99995023
##   [7] 1.00000000 0.99980060 0.99999971 0.95221140 0.99999999 1.00000000
##  [13] 0.99995424 0.99999960 1.00000000 1.00000000 0.99912113 0.99887854
##  [19] 0.99986579 1.00000000 0.99999999 1.00000000 0.99999988 1.00000000
##  [25] 0.99983008 0.99170687 1.00000000 1.00000000 0.99999973 0.99934092
##  [31] 0.99978996 1.00000000 0.99947940 1.00000000 1.00000000 1.00000000
##  [37] 0.97451873 1.00000000 1.00000000 0.98229422 0.99994521 1.00000000
##  [43] 1.00000000 1.00000000 0.99999997 0.99995621 1.00000000 1.00000000
##  [49] 0.88079708 0.99995759 0.99824582 0.97558882 0.99959207 0.99947311
##  [55] 0.99999998 0.94603787 0.99618123 0.98337364 1.00000000 0.99770792
##  [61] 0.99999993 1.00000000 1.00000000 1.00000000 0.99994630 0.99997344
##  [67] 0.99996610 0.99995621 0.99180498 1.00000000 0.99998056 0.99988790
##  [73] 0.99999972 1.00000000 0.99999997 0.99999981 1.00000000 1.00000000
##  [79] 1.00000000 0.54090835 0.99999990 1.00000000 1.00000000 1.00000000
##  [85] 0.06862533 0.99999973 1.00000000 0.97319510 0.99992923 1.00000000
##  [91] 1.00000000 0.92041507 0.99999350 0.99997718 1.00000000 0.99618123
##  [97] 0.99999931 0.99713409 0.05561925 1.00000000
set.seed(105)
Y <- rbinom(n,1,p)
Y
##   [1] 1 0 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##  [38] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
##  [75] 1 1 1 1 1 1 1 1 1 1 0 1 1 1 1 1 1 1 1 1 1 1 1 1 0 1
datagab <- data.frame(Y,X1,X2,X3,X4)
datagab
##     Y X1 X2 X3   X4
## 1   1  2  0  1 2.61
## 2   0  1  0  0 3.03
## 3   1  4  1  1 2.41
## 4   1  0  1  1 2.92
## 5   1  3  0  0 2.07
## 6   1  3  0  0 2.94
## 7   1  8  1  1 3.41
## 8   1  2  0  0 3.60
## 9   1  4  1  1 2.45
## 10  1  1  1  0 2.81
## 11  1  5  1  1 2.53
## 12  1 11  1  1 3.02
## 13  1  2  1  1 3.06
## 14  1  3  1  0 4.29
## 15  1  7  0  1 2.87
## 16  1  6  1  1 2.56
## 17  1  1  1  1 3.23
## 18  1  2  0  0 3.06
## 19  1  2  0  1 2.88
## 20  1  6  0  1 3.40
## 21  1  4  1  1 3.46
## 22  1  6  1  1 3.13
## 23  1  4  0  1 2.88
## 24  1  7  1  1 2.26
## 25  1  3  1  0 2.40
## 26  1  1  1  0 3.37
## 27  1  7  0  0 2.75
## 28  1 11  0  0 3.59
## 29  1  4  0  0 3.48
## 30  1  2  1  0 3.07
## 31  1  3  0  0 2.49
## 32  1 13  0  1 3.35
## 33  1  2  0  0 3.30
## 34  1 15  0  1 3.22
## 35  1  6  1  1 2.99
## 36  1 11  1  0 2.68
## 37  1  1  0  0 3.17
## 38  1  5  1  1 3.64
## 39  1 23  0  1 1.93
## 40  1  1  1  0 3.13
## 41  1  2  0  1 3.16
## 42  1 10  0  1 3.52
## 43  1  8  1  0 3.07
## 44  1  9  0  0 2.76
## 45  1  5  0  0 3.10
## 46  1  3  0  0 2.98
## 47  1  8  0  0 3.54
## 48  1 11  1  0 3.04
## 49  1  1  1  0 2.50
## 50  1  2  0  1 3.24
## 51  1  2  0  0 2.92
## 52  1  1  0  1 2.34
## 53  1  1  1  1 3.47
## 54  1  2  1  0 3.14
## 55  1  4  0  1 3.43
## 56  1  1  1  0 2.77
## 57  1  1  1  1 2.77
## 58  1  1  1  0 3.15
## 59  1  5  1  1 3.87
## 60  1  1  1  1 2.93
## 61  1  3  1  1 4.00
## 62  1  5  1  0 3.51
## 63  1 16  1  0 3.27
## 64  1  6  1  1 2.31
## 65  1  3  1  0 2.76
## 66  1  2  1  1 3.23
## 67  1  3  0  0 3.06
## 68  1  3  0  0 2.98
## 69  1  1  1  1 2.53
## 70  1  6  1  1 2.70
## 71  1  3  0  1 2.39
## 72  1  2  1  1 2.78
## 73  1  4  1  1 2.47
## 74  1 17  1  0 3.45
## 75  1  5  1  0 2.97
## 76  1  5  0  0 2.49
## 77  1 10  0  1 3.44
## 78  1  7  0  0 3.46
## 79  1  9  1  1 2.52
## 80  1  0  1  0 3.02
## 81  1  3  1  1 3.88
## 82  1  5  1  0 3.76
## 83  1 13  1  1 3.41
## 84  1 20  1  1 3.86
## 85  0  0  0  0 2.31
## 86  1  4  1  0 3.32
## 87  1  7  0  0 2.75
## 88  1  1  0  1 2.31
## 89  1  2  0  1 3.08
## 90  1  7  0  0 3.02
## 91  1 12  1  0 3.33
## 92  1  1  1  0 2.64
## 93  1  2  1  1 3.67
## 94  1  3  0  1 2.34
## 95  1 12  0  0 2.75
## 96  1  2  1  0 2.52
## 97  1  4  0  1 2.34
## 98  1  1  0  0 3.86
## 99  0  0  0  0 2.24
## 100 1  7  0  0 2.61

Analisis Regresi Logistik

modelreglog <- glm(Y~X1+X2+X3+X4,family = binomial(link = "logit"),data=datagab)
## Warning: glm.fit: algorithm did not converge
## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred
summary(modelreglog)
## 
## Call:
## glm(formula = Y ~ X1 + X2 + X3 + X4, family = binomial(link = "logit"), 
##     data = datagab)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)
## (Intercept)   -874.4    96281.5  -0.009    0.993
## X1             132.6    14238.0   0.009    0.993
## X2             173.2    31130.0   0.006    0.996
## X3             210.6    35681.2   0.006    0.995
## X4             239.2    26561.0   0.009    0.993
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 2.6948e+01  on 99  degrees of freedom
## Residual deviance: 2.2924e-07  on 95  degrees of freedom
## AIC: 10
## 
## Number of Fisher Scoring iterations: 25