bootstraped spearman correlation in R

Question

[zhangdengwei]

Hi all,

I wanna do bootstraped spearman correlation in R. I found there was a function, spearmanRho, which is capable of doing it in R. But after testing, it seems that there is no difference between with bootstrap and without bootstrap, here is my code:

> LSAT <- c(576,635,558,578,666,580,555,661,651,605,653,575,545,572,594)
> GPA <- c(3.39,3.30,2.81,3.03,3.44,3.07,3.00,3.43,3.36,3.13,3.12,2.74,
+          2.76,2.88,2.96)
> n = length(LSAT)
> xy <- data.frame(cbind(LSAT,GPA))
> xy
   LSAT  GPA
1   576 3.39
2   635 3.30
3   558 2.81
4   578 3.03
5   666 3.44
6   580 3.07
7   555 3.00
8   661 3.43
9   651 3.36
10  605 3.13
11  653 3.12
12  575 2.74
13  545 2.76
14  572 2.88
15  594 2.96 
> cor.test(xy$LSAT, xy$GPA, method = "spearman")

    Spearman's rank correlation rho

data:  xy$LSAT and xy$GPA
S = 114, p-value = 0.0006079
alternative hypothesis: true rho is not equal to 0
sample estimates:
      rho 
0.7964286 
> spearmanRho(x=xy$LSAT,y=xy$GPA,method="spearman",R=1000)
  rho 
0.796

So is there anything I did wrong? or is there any alternative to perform it in R? Any suggestions would be greatly appreciated. Thanks!

Answer 1

[h.mon]

The confidence intervals are calculated by bootstrapping, not the rho statistic itself. Try:

spearmanRho(x=xy$LSAT,y=xy$GPA,method="spearman",R=1000,ci=T)

1 0.796     0.45    0.964
  

[zhangdengwei]

h.mon, thanks for your reply. do you mean that the bootstrap would impact the confidence intervals other than rho?

[Alex Reynolds]

The spearmanRho function uses the stats::cor function to calculate rho. Bootstrapping a certain number of times (the parameter R or 1000 times in your example) then gives you a confidence interval around that measurement of rho.