fix: `mean.index()` being padded with trailing NA over length(variables)

It was intended to set the index of the variable with itself to be NA.
As written, this would set the index of the variable among all variables in the data set to be NA, thus creating longer vectors when the index of that variable exceeded the length of `variables`.
Fixes bug introduced in https://github.com/StephanSeifert/SurrogateMinimalDepth/commit/4039d104f14f5f0a09f1c97135550564163febd6

R/meanAdjAgree.R

@@ -67,7 +67,7 @@ mean.index <- function(i, list.res, index.variables) {
   list <- list.res[which(names(list.res) == index.variables[i])]
   mean.list <- round(Reduce("+", list) / length(list), 2)
   if (length(mean.list) > 0) {
-    mean.list[index.variables[i]] <- NA
+    mean.list[i] <- NA
     return(mean.list)
   } else {
     return(rep(NA, length(index.variables)))