Education

data<-haven::read_sav("C:/Users/aklwin/OneDrive/Documents/R/Data/Data.sav")

data2<-data %>% filter(CHD6t18==1)
# Include only households with children 6 to 18 year old

table(data2$CHD6t18ALTEDU)

## 
##  1  2  3 
## 19 13 70

# tabulate the above households with their children for access to alternative education

data3<-data.frame(table(data2$CHD6t18ALTEDU))
Access<-data3[1,2] + data3[2,2]
# We are summing 1 + 2 

TotCh<-sum(data3[,2])+1
#As we later show in next block, we need to add +1 in total
  #because of the presence of 1 missing value

NAlt <-Access/TotCh
NAlt

## [1] 0.3106796

# This is percent of households with 6 to 18 year old children with access to alternative education

Chdrop<-sum(data$CHD6t18DS,na.rm = TRUE)
# As the column is the count, just get the total
Chdrop

## [1] 85

# this is drop-out children count
# But we don't have total age 6 to 18 children count
  #we know only # households with age 6 to 18
  #so we cannot take Chdrop(total drop-out children)
  #we need to count how many households have at least one drop-out child

Droptb<-data.frame(table(data$CHD6t18DS))
Droptb

##   Var1 Freq
## 1    0   48
## 2    1   32
## 3    2   18
## 4    3    3
## 5    4    2

# this shows househods with Age 6-18 child/children with drop-out

Drophh <-sum(Droptb[c(2:5),2])

rc<-data.frame(dim(data2))
rc

##   dim.data2.
## 1        103
## 2        150

# first row is total 6 to 18 year old. We can notice 103 instead of 102 of previous table that means one missing value is not displayed in the table previously.
#also consistent with the drop-out table

pcChDrop <-Drophh/rc[1,1]
pcChDrop

## [1] 0.5339806

# This is percent of households with drop-out children