link="https://docs.google.com/spreadsheets/d/e/2PACX-1vQWAwF5XnCfLYkPoPsWzR8Ut-h1_KSsTYQB1uC6lPxIgRe-EI9x7r5ELluLXgl_5g/pub?output=csv"
midata=read.csv(link,stringsAsFactors = F)

table(midata$BECARIO)

## 
##    NO    SI 
## 26478 40771

names(midata)

## [1] "REGION"   "BECARIO"  "GESTION"  "DISTRITO" "POBREZA"

midata[ ,c(1:5)] = lapply(midata[ , c(1:5)], as.factor)

summary(midata)

##        REGION      BECARIO       GESTION        DISTRITO     POBREZA    
##  LIMA     : 7639   NO:26478   Privada: 5628   Rural :26837   NoP:34339  
##  CUSCO    : 4760   SI:40771   Publica:61621   Urbana:40412   P  :32910  
##  PIURA    : 4744                                                        
##  JUNIN    : 4606                                                        
##  LORETO   : 4403                                                        
##  CAJAMARCA: 3895                                                        
##  (Other)  :37202

set.seed(2019)

 vars1=midata[,c("BECARIO","POBREZA")]

#regresion
rlog1=glm(BECARIO~., data=vars1,family = binomial)

#resultado clásico:
summary(rlog1)

## 
## Call:
## glm(formula = BECARIO ~ ., family = binomial, data = vars1)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -1.3667  -1.3641   0.9992   1.0016   1.0016  
## 
## Coefficients:
##             Estimate Std. Error z value Pr(>|z|)    
## (Intercept) 0.428769   0.011042  38.831   <2e-16 ***
## POBREZAP    0.005903   0.015789   0.374    0.708    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 90166  on 67248  degrees of freedom
## Residual deviance: 90166  on 67247  degrees of freedom
## AIC: 90170
## 
## Number of Fisher Scoring iterations: 4

### semilla

set.seed(2019)

### primer modelo:
#data como subset
#BECARIO DEPENDIENTE
#TAMBIEN SE PUEDE PONER EL NUMERO DE LAS COLUMNAS DE LAS VARIABLES INDEPEDIENTES 
vars2=midata[,c("BECARIO","POBREZA","GESTION")]

#regresion
rlog2=glm(BECARIO~., data=vars2,family = binomial)

#resultado clásico:
summary(rlog2)

## 
## Call:
## glm(formula = BECARIO ~ ., family = binomial, data = vars2)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -1.3756  -1.3721   0.9914   0.9945   1.0846  
## 
## Coefficients:
##                 Estimate Std. Error z value Pr(>|z|)    
## (Intercept)     0.230123   0.027282   8.435  < 2e-16 ***
## POBREZAP       -0.007801   0.015893  -0.491    0.624    
## GESTIONPublica  0.224493   0.028248   7.947 1.91e-15 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 90166  on 67248  degrees of freedom
## Residual deviance: 90103  on 67246  degrees of freedom
## AIC: 90109
## 
## Number of Fisher Scoring iterations: 4

vars3=midata[,c("BECARIO","POBREZA","GESTION","DISTRITO")]

#regresion
rlog3=glm(BECARIO~., data=vars3,family = binomial)

#resultado clásico:
summary(rlog3)

## 
## Call:
## glm(formula = BECARIO ~ ., family = binomial, data = vars3)
## 
## Deviance Residuals: 
##     Min       1Q   Median       3Q      Max  
## -1.3820  -1.3624   0.9858   1.0030   1.0966  
## 
## Coefficients:
##                  Estimate Std. Error z value Pr(>|z|)    
## (Intercept)     1.933e-01  3.058e-02   6.320 2.62e-10 ***
## POBREZAP       -8.051e-05  1.616e-02  -0.005  0.99602    
## GESTIONPublica  2.318e-01  2.838e-02   8.167 3.16e-16 ***
## DISTRITOUrbana  4.401e-02  1.649e-02   2.669  0.00762 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## (Dispersion parameter for binomial family taken to be 1)
## 
##     Null deviance: 90166  on 67248  degrees of freedom
## Residual deviance: 90096  on 67245  degrees of freedom
## AIC: 90104
## 
## Number of Fisher Scoring iterations: 4

##TABLAS

t1 = table(midata$REGION,midata$BECARIO)

t1

##                
##                   NO   SI
##   AMAZONAS       894 1701
##   ANCASH        1389 2146
##   APURIMAC      1194 1773
##   AREQUIPA       510  799
##   AYACUCHO       709 1586
##   CAJAMARCA     1447 2448
##   CALLAO         499  914
##   CUSCO         2095 2665
##   HUANCAVELICA   899 1614
##   HUANUCO        938 1338
##   ICA            591  906
##   JUNIN         1889 2717
##   LA LIBERTAD   1297 2031
##   LAMBAYEQUE     825 1537
##   LIMA          3121 4518
##   LORETO        1993 2410
##   MADRE DE DIOS  204  227
##   MOQUEGUA        88  224
##   PASCO          824 1048
##   PIURA         1699 3045
##   PUNO          1512 1476
##   SAN MARTIN     989 1843
##   TACNA          210  472
##   TUMBES         220  432
##   UCAYALI        442  901

t2 = table(midata$DISTRITO,midata$BECARIO)

t2

##         
##             NO    SI
##   Rural  10678 16159
##   Urbana 15800 24612

t3 = table(midata$POBREZA,midata$BECARIO)

t3

##      
##          NO    SI
##   NoP 13544 20795
##   P   12934 19976