What is the function that will provide you the lower and upper bounds of correlation coefficient separately?

问题

m=c(1,2,5,4,6,8)
h=c(1,2,9,8,7,3)
cor(m,h)
#[1] 0.4093729

If you estimate the correlation coefficient (R), then you can also estimate a 95% confidence interval for correlation coefficient (R), resulting in, for example something like

 R = 0.40  [0.33 0.56]

where the "best" estimate for R is 0.40 and there's a 95% chance that the true R is between 0.3 and 0.56. (Note that these numbers are completely made up.)

I am looking for a function, which will provide the lower and upper bounds of R separately . To have something like:

 R = 0.40
upper  [0.33]
 lower [0.56] 

something simiilar to this in MATLAB:

         [R,P,RLO,RUP]=corrcoef(...) also returns matrices RLO and RUP, of the same size as R,            
         containing lower and upper bounds for a 95% confidence interval for each coefficient.

回答1:

In the "see also" section of cor's help page, it says

cor.test for confidence intervals (and tests)

> cor.test(m, h)

    Pearson's product-moment correlation

data:  m and h
t = 0.8974, df = 4, p-value = 0.4202
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.6022868  0.9164582
sample estimates:
      cor 
0.4093729 

Or to get at the interval more directly:

> x = cor.test(m, h)
> x$conf.int
[1] -0.6022868  0.9164582
attr(,"conf.level")
[1] 0.95

来源：https://stackoverflow.com/questions/17808560/what-is-the-function-that-will-provide-you-the-lower-and-upper-bounds-of-correla