Correlation significance testing using Fisher's z-transformation
Correlation significance testing using Fisher's z-transformation.
cor_test(y, x, type = "pearson", rho = 0, a = 0.05 )
y |
A numerical vector. |
x |
A numerical vector. |
type |
The type of correlation you want. "pearson" and "spearman" are the two supported types because their standard error is easily calculated. |
rho |
The value of the hypothesised correlation to be used in the hypothesis testing. |
a |
The significance level used for the confidence intervals. |
The function uses the built-in function "cor" which is very fast, then computes a confidence interval and produces a p-value for the hypothesis test.
A vector with 5 numbers; the correlation, the p-value for the hypothesis test that each of them is equal to "rho", the test statistic and the $a/2%$ lower and upper confidence limits.
Michail Tsagris
R implementation and documentation: Michail Tsagris mtsagris@uoc.gr.
x <- rcauchy(60) y <- rnorm(60) cor_test(y, x)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.