HI,
Not sure if this is what you wanted.
mat1<- matrix(c(1, 1, -1, -1, 1, -1, -1, -2, 1, 1, 1, 1), byrow=TRUE, nc=4)
fun1<- function(mat){
???? ??? matP<- mat
??? matN<- mat
??? matP[matP<0]<- NA
??? matN[matN>0]<- NA
??? resP<-rowSums(matP,na.rm=TRUE)/ncol(matP)
??? resN<- rowSums(matN,na.rm=TRUE)/ncol(matN)
??? res<- rbind(resP,resN)
??? row.names(res)<- c("Mean_Pos","Mean_Neg")
??? res
??? }
fun1(mat1)
#???????? [,1]? [,2] [,3]
#Mean_Pos? 0.5? 0.25??? 1
#Mean_Neg -0.5 -1.00??? 0
A.K.
hello,
when i use the function rowMeans, which is sum/n, can i divide
it in 2 parts, -> Sum(just positive values)/n and Sum(just negative
values)/n. i need both for my regression but dont know how to do it.
for example we have the matrix
1 ?1 ?-1 ?-1 ? -> rowMeans([1:3 , 2]) ?just positive -> 1
1 -1 -1 ?-2 ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?
? ? ? ? ? ? ? ? ? ?1/2 ?here not 0 because we dont use the -1
1 1 ? 1 ? 1 ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ?1
thanks for helping