The function heatmapin R should help the person interpret the relative values of the elements of the matrix. However, apparently, it does not color the cells sequentially within the given graph, which is a serious obstacle to the correct interpretation of relative values.
For example, let's generate some data by combining columns of normal random variations:
foo <- cbind(replicate(10,rnorm(10)))
Now, if we match the columns of foo, we can verify that we get 1 in the diagonal elements, since the correlation of any column with itself is 1:
cor.matrix <- cor(foo)
But when building:
heatmap(cor.matrix,Rowv=NA,Colv=NA)
(we suppress the dendrogram entry here, although this does not seem to matter)
the diagonal cells are not colored evenly, as you can see: 
Can anyone explain what is going on here?
source
share