select <- dataset$DGRDG != "1"
dataset.higher <- dataset[select,]
table(dataset.higher$DGRDG)

#create a degree matching variable, 1 if they stuck to the same degree, and 0 else
dataset.higher$NBAMEMG <- dataset.higher$NBAMEMG != "9" & dataset.higher$NBAMEMG != "96"
dataset.higher$match <- dataset.higher$NBAMEMG == dataset.higher$NDGMEMG


for (idx in 1:nrow(dataset.higher)) {
  if(dataset.higher[idx, "NBAMEMG"] == dataset.higher[idx, "NDGMEMG"]) {
    dataset.higher[idx, "match"] <- "1"
  }  else{
    dataset.higher[idx, "match"] <- "0"
  }
}


degree.deviation <- function(dataset.higher){
  for (idx in 1:nrow(dataset.higher)) {
    if(dataset.higher[idx, "NBAMEMG"] == dataset.higher[idx, "NDGMEMG"]) {
      dataset.higher[idx, "match"] <- "1"
    }  else{
      dataset.higher[idx, "match"] <- "0"
    }
  }
}

shuffle <- function(){
  use.shuffle <- sample(dataset.higher$match)
  function(dataset.higher){
  for (idx in 1:nrow(dataset.higher)) {
    if(dataset.higher[idx, "NBAMEMG"] == dataset.higher[idx, "NDGMEMG"]) {
      dataset.higher[idx, "match"] <- "1"
    }  else{
      dataset.higher[idx, "match"] <- "0"
    }
  }
}
}

m <- 10**4
D = replicate(m, shuffle())
d = degree.deviation(dataset.higher)
pvalue <- sum(D >= d)/m
pvalue
```