Minggu, 18 Agustus 2024

Regresi Logistik dengan data mtcars

 Data mtcars berisi tentang suatu mobil dengan beberap faktor atau avriabel. dalam hal ini saya disclaimer mungkin penentuan variabel bebas dan tidak bebasnya begitu berbeda, tetapi setidaknya saya memberikan cara untuk membuat suatau regresi logistik. mudah-mudahan berguna. 


reglogmtcar.R
#Regresi Logistikmtcars

#Menyiapkan data MTcars

#Regresi mtcars
reglogmtcars<-glm(vs~disp+wt,data=mtcars,family="binomial")
summary(reglogmtcars)
## 
## Call:
## glm(formula = vs ~ disp + wt, family = "binomial", data = mtcars)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)  
## (Intercept)  1.60859    2.43903   0.660    0.510  
## disp        -0.03443    0.01536  -2.241    0.025 *
## wt           1.62635    1.49068   1.091    0.275  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 43.86  on 31  degrees of freedom
## Residual deviance: 21.40  on 29  degrees of freedom
## AIC: 27.4
## 
## Number of Fisher Scoring iterations: 6
#KIta mencoba model lain mengganti wt dengan hp
reglogmtcars2<-glm(vs~disp+hp,data=mtcars,family="binomial")
summary(reglogmtcars2)
## 
## Call:
## glm(formula = vs ~ disp + hp, family = "binomial", data = mtcars)
## 
## Coefficients:
##              Estimate Std. Error z value Pr(>|z|)  
## (Intercept)  8.158348   3.238656   2.519   0.0118 *
## disp        -0.003515   0.011765  -0.299   0.7651  
## hp          -0.061257   0.035496  -1.726   0.0844 .
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 43.86  on 31  degrees of freedom
## Residual deviance: 16.75  on 29  degrees of freedom
## AIC: 22.75
## 
## Number of Fisher Scoring iterations: 7
#KIta mencoba model lain mengganti hp dengan drat
reglogmtcars3<-glm(vs~disp+drat,data=mtcars,family="binomial")
summary(reglogmtcars3)
## 
## Call:
## glm(formula = vs ~ disp + drat, family = "binomial", data = mtcars)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)  
## (Intercept) 20.78542   11.12266   1.869   0.0617 .
## disp        -0.04371    0.01867  -2.341   0.0192 *
## drat        -3.43990    2.16431  -1.589   0.1120  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 43.860  on 31  degrees of freedom
## Residual deviance: 19.468  on 29  degrees of freedom
## AIC: 25.468
## 
## Number of Fisher Scoring iterations: 7
#KIta mencoba model lain mengganti menambah wt
reglogmtcars4<-glm(vs~disp+drat+wt,data=mtcars,family="binomial")
summary(reglogmtcars4)
## 
## Call:
## glm(formula = vs ~ disp + drat + wt, family = "binomial", data = mtcars)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)  
## (Intercept) 16.95724   11.15757   1.520   0.1286  
## disp        -0.05287    0.02243  -2.357   0.0184 *
## drat        -3.06950    2.08161  -1.475   0.1403  
## wt           1.36072    1.61400   0.843   0.3992  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 43.860  on 31  degrees of freedom
## Residual deviance: 18.726  on 28  degrees of freedom
## AIC: 26.726
## 
## Number of Fisher Scoring iterations: 7
#KIta mencoba model semua variabel
reglogmtcars5<-glm(vs~disp+gear,data=mtcars,family="binomial")
#model yang paling mendektai signifikan 

summary(reglogmtcars5)
## 
## Call:
## glm(formula = vs ~ disp + gear, family = "binomial", data = mtcars)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)  
## (Intercept) 41.46032   20.55385   2.017   0.0437 *
## disp        -0.08533    0.04000  -2.133   0.0329 *
## gear        -6.64466    3.46953  -1.915   0.0555 .
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 43.860  on 31  degrees of freedom
## Residual deviance: 12.496  on 29  degrees of freedom
## AIC: 18.496
## 
## Number of Fisher Scoring iterations: 8
reglogmtcars6<-glm(vs~disp+mpg,data=mtcars,family="binomial")

summary(reglogmtcars6)
## 
## Call:
## glm(formula = vs ~ disp + mpg, family = "binomial", data = mtcars)
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)
## (Intercept)  0.38791    6.01361   0.065    0.949
## disp        -0.01611    0.01051  -1.532    0.125
## mpg          0.13232    0.21448   0.617    0.537
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 43.860  on 31  degrees of freedom
## Residual deviance: 22.283  on 29  degrees of freedom
## AIC: 28.283
## 
## Number of Fisher Scoring iterations: 6

Tidak ada komentar:

Posting Komentar

Analisis Faktor Rstudio

  Analisis Faktor ...