stats (version 3.4.1)

cor.test: Test for Association/Correlation Between Paired Samples

Description

Test for association between paired samples, using one of Pearson's product moment correlation coefficient, Kendall's \(\tau\) or Spearman's \(\rho\).

Usage

cor.test(x, …)
# S3 method for default
cor.test(x, y,
         alternative = c("two.sided", "less", "greater"),
         method = c("pearson", "kendall", "spearman"),
         exact = NULL, conf.level = 0.95, continuity = FALSE, …)
# S3 method for formula
cor.test(formula, data, subset, na.action, …)

Arguments

x, y

numeric vectors of data values. x and y must have the same length.

alternative

indicates the alternative hypothesis and must be one of "two.sided", "greater" or "less". You can specify just the initial letter. "greater" corresponds to positive association, "less" to negative association.

method

a character string indicating which correlation coefficient is to be used for the test. One of "pearson", "kendall", or "spearman", can be abbreviated.

exact

a logical indicating whether an exact p-value should be computed. Used for Kendall's \(\tau\) and Spearman's \(\rho\). See ‘Details’ for the meaning of NULL (the default).

conf.level

confidence level for the returned confidence interval. Currently only used for the Pearson product moment correlation coefficient if there are at least 4 complete pairs of observations.

continuity

logical: if true, a continuity correction is used for Kendall's \(\tau\) and Spearman's \(\rho\) when not computed exactly.

formula

a formula of the form ~ u + v, where each of u and v are numeric variables giving the data values for one sample. The samples must be of the same length.

data

an optional matrix or data frame (or similar: see model.frame) containing the variables in the formula formula. By default the variables are taken from environment(formula).

subset

an optional vector specifying a subset of observations to be used.

na.action

a function which indicates what should happen when the data contain NAs. Defaults to getOption("na.action").

…

further arguments to be passed to or from methods.

Value

A list with class "htest" containing the following components:

statistic

the value of the test statistic.

parameter

the degrees of freedom of the test statistic in the case that it follows a t distribution.

p.value

the p-value of the test.

estimate

the estimated measure of association, with name "cor", "tau", or "rho" corresponding to the method employed.

null.value

the value of the association measure under the null hypothesis, always 0.

alternative

a character string describing the alternative hypothesis.

method

a character string indicating how the association was measured.

data.name

a character string giving the names of the data.

conf.int

a confidence interval for the measure of association. Currently only given for Pearson's product moment correlation coefficient in case of at least 4 complete pairs of observations.

Details

The three methods each estimate the association between paired samples and compute a test of the value being zero. They use different measures of association, all in the range \([-1, 1]\) with \(0\) indicating no association. These are sometimes referred to as tests of no correlation, but that term is often confined to the default method.

If method is "pearson", the test statistic is based on Pearson's product moment correlation coefficient cor(x, y) and follows a t distribution with length(x)-2 degrees of freedom if the samples follow independent normal distributions. If there are at least 4 complete pairs of observation, an asymptotic confidence interval is given based on Fisher's Z transform.

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 tests may be used if the data do not necessarily come from a bivariate normal distribution.

For Kendall's test, by default (if exact is NULL), an exact p-value is computed if there are less than 50 paired samples containing finite values and there are no ties. Otherwise, the test statistic is the estimate scaled to zero mean and unit variance, and is approximately normally distributed.

For Spearman's test, p-values are computed using algorithm AS 89 for \(n < 1290\) and exact = TRUE, otherwise via the asymptotic \(t\) approximation. Note that these are ‘exact’ for \(n < 10\), and use an Edgeworth series approximation for larger sample sizes (the cutoff has been changed from the original paper).

References

D. J. Best & D. E. Roberts (1975), Algorithm AS 89: The Upper Tail Probabilities of Spearman's \(\rho\). Applied Statistics, 24, 377--379.

Myles Hollander & Douglas A. Wolfe (1973), Nonparametric Statistical Methods. New York: John Wiley & Sons. Pages 185--194 (Kendall and Spearman tests).

See Also

Kendall in package Kendall.

pKendall and pSpearman in package SuppDists, spearman.test in package pspearman, which supply different (and often more accurate) approximations.

Examples

## Hollander & Wolfe (1973), p. 187f.
## Assessment of tuna quality.  We compare the Hunter L measure of
##  lightness to the averages of consumer panel scores (recoded as
##  integer values from 1 to 6 and averaged over 80 such values) in
##  9 lots of canned tuna.

x <- c(44.4, 45.9, 41.9, 53.3, 44.7, 44.1, 50.7, 45.2, 60.1)
y <- c( 2.6,  3.1,  2.5,  5.0,  3.6,  4.0,  5.2,  2.8,  3.8)

##  The alternative hypothesis of interest is that the
##  Hunter L value is positively associated with the panel score.

cor.test(x, y, method = "kendall", alternative = "greater")
## => p=0.05972

cor.test(x, y, method = "kendall", alternative = "greater",
         exact = FALSE) # using large sample approximation
## => p=0.04765

## Compare this to
cor.test(x, y, method = "spearm", alternative = "g")
cor.test(x, y,                    alternative = "g")

## Formula interface.
require(graphics)
pairs(USJudgeRatings)
cor.test(~ CONT + INTG, data = USJudgeRatings)