data<-read.csv('C:/Users/rusoc/OneDrive/Escritorio/TEC/Mineria de datos/segmentation data.csv')
#Modelo logit
modelo_logit = glm(Marital.status~Age,data=data,family=binomial(link="logit"))
summary(modelo_logit)
## 
## Call:
## glm(formula = Marital.status ~ Age, family = binomial(link = "logit"), 
##     data = data)
## 
## Coefficients:
##              Estimate Std. Error z value Pr(>|z|)    
## (Intercept)  1.360554   0.153562   8.860   <2e-16 ***
## Age         -0.038493   0.004145  -9.286   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 2772.5  on 1999  degrees of freedom
## Residual deviance: 2679.0  on 1998  degrees of freedom
## AIC: 2683
## 
## Number of Fisher Scoring iterations: 4
#Modelo probit
modelo_probit = glm(Marital.status~Age,data=data,family=binomial(link="probit"))
summary(modelo_probit)
## 
## Call:
## glm(formula = Marital.status ~ Age, family = binomial(link = "probit"), 
##     data = data)
## 
## Coefficients:
##              Estimate Std. Error z value Pr(>|z|)    
## (Intercept)  0.830517   0.093675   8.866   <2e-16 ***
## Age         -0.023391   0.002509  -9.324   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 2772.5  on 1999  degrees of freedom
## Residual deviance: 2680.2  on 1998  degrees of freedom
## AIC: 2684.2
## 
## Number of Fisher Scoring iterations: 4
#Estimamos los criterios de información para cada modelo
CIA_Logit = AIC(modelo_logit)
CIA_Probit = AIC(modelo_probit)
CIA_Logit
## [1] 2683.008
CIA_Probit
## [1] 2684.179

Modelo con mejor ajuste con base al CIA es el logit al tener un valor menor.

#Predicciones
predict(modelo_logit, data.frame(Age = mean(data$Age)), type="response")
##         1 
## 0.4945746