how to rank a correlation matrix?

Question

I have found a correlation matrix for my data using the following code:

file_20 <- read.csv("C:/Desktop/ex.csv")
file_20
cor (file_20[,1:19], file_20[1:19], method ="spearman")

But now how can i rank my correlation matrix? Is there any suggestion

NOTE: I have 19 columns and 20 rows (including the header) and my aim is to rank the columns according to spearman rank correlation.

I tried doing

cor (rank(file_20[,1:19]), rank(file_20[1:19]), method ="spearman")

It showed output as

[1] 1

Is there any option to get all my columns of the table ranked?

Please help!

Prasanna Nandakumar Prasanna Nandakumar · Accepted Answer · 2014-01-28T05:01:15

-- use the kendall method argument for cor() instead:

df <- data.frame(x=c(1,2,3,4,5), y=c(5,4,3,2,1))  
cor(df, method="kendall") 
   x  y 
x  1 -1    
y -1  1   
R> 
From help(cor):

For cor(), if method is "kendall" or "spearman", Kendall's tau or Spearman's rho statistic is used to estimate a rank-based measure of association. These are more robust and have been recommended if the data do not necessarily come from a bivariate normal distribution. For cov(), a non-Pearson method is unusual but available for the sake of completeness. Note that "spearman" basically computes cor(R(x), R(y)) (or cov(.,.)) where R(u) := rank(u, na.last="keep"). In the case of missing values, the ranks are calculated depending on the value of use, either based on complete observations, or based on pairwise completeness with reranking for each pair.

how to rank a correlation matrix?

1 Answers