# Membangkitkan Data
## skenario
Y :Keputusan mendapatkan/tidak mendapatkan penghargaan film
X1 :Views (Jt)
X2 :Kategori Film (0:Series, 1:Movie)
X3 :Pendapat Kritikus (0:Bagus, 1:kurang bagus)
X4 :Rating (Skala 5)
# Membangkitkan Data X1
X1 :views (Jt)
Membangkitkan variabel X1 dengan jumlah views 0-200 dengan nilai tengah 2 dan banyak film adalah 100
X1
```r
set.seed(100)
n <- 100
u <- runif(n)X1 <- round (200*(-(log(1-u)/2)))
X1## [1] 37 30 80 6 63 66 167 46 79 19 98 214 33 51 144 111 23 44
## [19] 45 117 77 124 77 138 54 19 147 214 80 33 67 264 43 308 119 220
## [37] 20 99 456 14 40 200 150 176 92 68 152 216 23 37 40 22 27 32
## [55] 89 29 13 26 91 24 62 104 323 113 59 44 61 59 28 119 53 40
## [73] 85 341 108 98 194 149 180 10 62 91 252 406 4 86 132 29 36 132
## [91] 237 24 44 59 237 49 73 13 3 148X2 :Kategori film Keterangan yang digunakan (0:Series, 1:Movie)
X2 <- round(runif(n))
X2## [1] 0 0 0 0 1 1 1 1 0 1 1 1 0 0 1 0 1 1 0 1 0 0 0 1 0 0 1 1 1 0 0 1 1 0 1 0 0
## [38] 0 0 1 1 0 0 1 0 1 1 0 0 0 1 1 0 0 1 1 1 1 0 1 1 1 0 0 0 0 0 1 1 1 0 0 1 1
## [75] 1 0 1 1 0 1 0 1 1 1 0 0 0 0 0 1 1 0 0 1 1 0 0 1 0 1X3 :Pendapat Kritikus Keterangan yang digunakan (0:Bagus , 1:Kurang bagus)
X3 <- round(runif(n))
X3## [1] 0 1 1 1 0 1 1 1 0 0 0 1 0 0 0 1 1 1 0 0 1 0 1 1 0 1 0 0 0 0 1 0 1 1 0 0 0
## [38] 1 1 1 0 1 1 1 0 1 1 0 0 0 0 1 0 0 1 1 0 0 1 1 0 1 0 1 1 1 0 0 1 1 1 1 0 0
## [75] 1 1 0 0 1 0 0 0 0 0 1 1 1 1 0 0 0 1 0 1 0 0 1 1 1 1X3 : Data Rating dengan skala 5
X4 <- round(rnorm(n,4.5,0.6),2)
X4## [1] 5.12 5.49 4.49 4.49 4.65 4.30 4.43 4.44 4.66 4.58 4.35 4.54 4.39 4.98 4.50
## [16] 4.12 4.35 4.09 4.62 5.01 4.88 4.62 4.45 4.67 4.47 3.27 4.72 4.28 5.26 5.80
## [31] 3.76 4.85 4.57 4.19 4.87 4.92 4.44 4.32 3.85 4.13 4.36 4.35 5.07 4.34 5.64
## [46] 4.24 5.45 4.60 3.85 4.85 4.52 4.29 5.01 4.81 5.11 3.89 4.16 3.89 2.69 4.70
## [61] 5.24 4.90 3.70 3.99 3.43 5.24 4.30 3.92 5.03 4.35 3.59 4.49 4.52 4.60 4.75
## [76] 4.12 4.88 3.78 5.31 4.14 4.77 4.87 4.32 3.54 4.30 4.15 4.27 5.01 4.91 4.64
## [91] 4.07 6.07 3.52 3.54 4.70 6.14 4.30 3.75 4.24 6.03menentukan koefisien
b0 <- -10
b1 <- 0.1
b2 <- 0.5
b3 <- 0.3
b4 <- 0.2DataPendukung <- b0 + (b1*X1)+(b2*X2)+(b3*X3)+(b4*X4)
DataPendukung## [1] -5.276 -5.602 -0.802 -8.202 -2.270 -1.740 8.386 -3.712 -1.168 -6.684
## [11] 1.170 13.108 -5.822 -3.904 5.800 2.224 -6.030 -3.982 -4.576 3.202
## [21] -1.024 3.324 -1.110 5.534 -3.706 -7.146 6.144 12.756 -0.448 -5.540
## [31] -2.248 17.870 -3.986 21.938 3.374 12.984 -7.112 1.064 36.670 -6.974
## [41] -4.628 11.170 6.314 9.268 0.328 -1.552 7.090 12.520 -6.930 -5.330
## [51] -4.596 -6.142 -6.298 -5.838 0.722 -5.522 -7.368 -6.122 -0.062 -5.860
## [61] -2.252 2.180 23.040 2.398 -3.114 -4.252 -3.040 -2.816 -5.394 3.570
## [71] -3.682 -4.802 -0.096 25.520 2.550 0.924 10.876 6.156 9.362 -7.672
## [81] -2.846 0.574 16.564 31.808 -8.440 -0.270 4.354 -5.798 -5.418 4.628
## [91] 15.014 -6.086 -4.896 -2.592 15.140 -3.872 -1.540 -7.150 -8.552 6.806p <- exp(DataPendukung)/ (1 + exp(DataPendukung))
p## [1] 0.0050868331 0.0036769058 0.3095978621 0.0002740297 0.0936382122
## [6] 0.1493129345 0.9997720144 0.0238460901 0.2372166839 0.0012492024
## [11] 0.7631450157 0.9999979711 0.0029529302 0.0197626683 0.9969815837
## [16] 0.9023841114 0.0023997215 0.0183069125 0.0101910708 0.9609094714
## [21] 0.2642489817 0.9652430372 0.2478708886 0.9960653855 0.0239861546
## [26] 0.0007873894 0.9978582757 0.9999971150 0.3898363891 0.0039111695
## [31] 0.0955221205 0.9999999827 0.0182351638 0.9999999997 0.9668820154
## [36] 0.9999977032 0.0008145987 0.7434542081 1.0000000000 0.0009350267
## [41] 0.0096796762 0.9999859096 0.9981924974 0.9999056118 0.5812726666
## [46] 0.1747975937 0.9991672966 0.9999963472 0.0009770453 0.0048207181
## [51] 0.0099912903 0.0021460028 0.0018366017 0.0029061955 0.6730472786
## [56] 0.0039819251 0.0006307311 0.0021892601 0.4845049633 0.0028431372
## [61] 0.0951770886 0.8984390721 0.9999999999 0.9166746663 0.0425334484
## [66] 0.0140359223 0.0456511708 0.0564656650 0.0045232095 0.9726151890
## [71] 0.0245544797 0.0081463952 0.4760184150 1.0000000000 0.9275735146
## [76] 0.7158564317 0.9999810938 0.9978837687 0.9999140793 0.0004654688
## [81] 0.0548884510 0.6396856410 0.9999999360 1.0000000000 0.0002160035
## [86] 0.4329070950 0.9873078725 0.0030244409 0.0044164185 0.9903203238
## [91] 0.9999996984 0.0022693271 0.0074209469 0.0696550648 0.9999997341
## [96] 0.0203921963 0.1765352748 0.0007842486 0.0001931211 0.9988941118y <- rbinom(n,1,p)
y## [1] 0 0 0 0 0 0 1 0 0 0 1 1 0 0 1 1 0 0 0 0 0 1 0 1 0 0 1 1 1 0 0 1 0 1 1 1 0
## [38] 1 1 0 0 1 1 1 0 1 1 1 0 0 0 0 0 0 1 0 0 0 0 0 0 1 1 1 0 0 0 0 0 1 0 0 1 1
## [75] 1 1 1 1 1 0 0 1 1 1 0 1 1 0 0 1 1 0 0 0 1 0 0 0 0 1datagab <- data.frame(y,X1,X2,X3,X4)
datagab## y X1 X2 X3 X4
## 1 0 37 0 0 5.12
## 2 0 30 0 1 5.49
## 3 0 80 0 1 4.49
## 4 0 6 0 1 4.49
## 5 0 63 1 0 4.65
## 6 0 66 1 1 4.30
## 7 1 167 1 1 4.43
## 8 0 46 1 1 4.44
## 9 0 79 0 0 4.66
## 10 0 19 1 0 4.58
## 11 1 98 1 0 4.35
## 12 1 214 1 1 4.54
## 13 0 33 0 0 4.39
## 14 0 51 0 0 4.98
## 15 1 144 1 0 4.50
## 16 1 111 0 1 4.12
## 17 0 23 1 1 4.35
## 18 0 44 1 1 4.09
## 19 0 45 0 0 4.62
## 20 0 117 1 0 5.01
## 21 0 77 0 1 4.88
## 22 1 124 0 0 4.62
## 23 0 77 0 1 4.45
## 24 1 138 1 1 4.67
## 25 0 54 0 0 4.47
## 26 0 19 0 1 3.27
## 27 1 147 1 0 4.72
## 28 1 214 1 0 4.28
## 29 1 80 1 0 5.26
## 30 0 33 0 0 5.80
## 31 0 67 0 1 3.76
## 32 1 264 1 0 4.85
## 33 0 43 1 1 4.57
## 34 1 308 0 1 4.19
## 35 1 119 1 0 4.87
## 36 1 220 0 0 4.92
## 37 0 20 0 0 4.44
## 38 1 99 0 1 4.32
## 39 1 456 0 1 3.85
## 40 0 14 1 1 4.13
## 41 0 40 1 0 4.36
## 42 1 200 0 1 4.35
## 43 1 150 0 1 5.07
## 44 1 176 1 1 4.34
## 45 0 92 0 0 5.64
## 46 1 68 1 1 4.24
## 47 1 152 1 1 5.45
## 48 1 216 0 0 4.60
## 49 0 23 0 0 3.85
## 50 0 37 0 0 4.85
## 51 0 40 1 0 4.52
## 52 0 22 1 1 4.29
## 53 0 27 0 0 5.01
## 54 0 32 0 0 4.81
## 55 1 89 1 1 5.11
## 56 0 29 1 1 3.89
## 57 0 13 1 0 4.16
## 58 0 26 1 0 3.89
## 59 0 91 0 1 2.69
## 60 0 24 1 1 4.70
## 61 0 62 1 0 5.24
## 62 1 104 1 1 4.90
## 63 1 323 0 0 3.70
## 64 1 113 0 1 3.99
## 65 0 59 0 1 3.43
## 66 0 44 0 1 5.24
## 67 0 61 0 0 4.30
## 68 0 59 1 0 3.92
## 69 0 28 1 1 5.03
## 70 1 119 1 1 4.35
## 71 0 53 0 1 3.59
## 72 0 40 0 1 4.49
## 73 1 85 1 0 4.52
## 74 1 341 1 0 4.60
## 75 1 108 1 1 4.75
## 76 1 98 0 1 4.12
## 77 1 194 1 0 4.88
## 78 1 149 1 0 3.78
## 79 1 180 0 1 5.31
## 80 0 10 1 0 4.14
## 81 0 62 0 0 4.77
## 82 1 91 1 0 4.87
## 83 1 252 1 0 4.32
## 84 1 406 1 0 3.54
## 85 0 4 0 1 4.30
## 86 1 86 0 1 4.15
## 87 1 132 0 1 4.27
## 88 0 29 0 1 5.01
## 89 0 36 0 0 4.91
## 90 1 132 1 0 4.64
## 91 1 237 1 0 4.07
## 92 0 24 0 1 6.07
## 93 0 44 0 0 3.52
## 94 0 59 1 1 3.54
## 95 1 237 1 0 4.70
## 96 0 49 0 0 6.14
## 97 0 73 0 1 4.30
## 98 0 13 1 1 3.75
## 99 0 3 0 1 4.24
## 100 1 148 1 1 6.03modelreglog <- 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) -16.62916 7.51565 -2.213 0.02692 *
## X1 0.13522 0.04246 3.184 0.00145 **
## X2 2.96334 1.48414 1.997 0.04586 *
## X3 2.22500 1.70179 1.307 0.19106
## X4 0.52382 1.03700 0.505 0.61347
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 136.663 on 99 degrees of freedom
## Residual deviance: 23.317 on 95 degrees of freedom
## AIC: 33.317
##
## Number of Fisher Scoring iterations: 9