bcor.test: Bayesian Test for Association/Correlation Between Paired...

In AlexanderLyNL/bstats: Bayesian statistics

Bayesian Test for Association/Correlation Between Paired Samples This mimics cor.test

Description

Bayesian Test for Association/Correlation Between Paired Samples This mimics cor.test

Usage

bcor.test(
  x,
  y,
  z = NULL,
  alternative = c("two.sided", "less", "greater"),
  method = c("pearson", "kendall", "spearman"),
  ciValue = 0.95,
  use = "pairwise.complete.obs",
  h0 = 0,
  kappa = 1,
  hyperGeoOverFlowThreshold = 25,
  oneThreshold = 0.001,
  var = 1
)

Arguments

x, y	numeric vectors of data values. x and y must have the same length
z	data frame of data values of the controlling variables.
alternative	indicates the alternative hypothesis and must be one of "two.sided", "greater" or "less". "greater" corresponds to positive association, "less" to negative association.
method	a character string indicating which correlation coefficient is to b used for the test. One of "pearson", "kendall" or "spearman".
ciValue	numeric in (0, 1) credible level for the returned credible interval.
h0	numeric between -1 and 1 that specifies the point null hypothesis
kappa	numeric > 0 that specifies the
hyperGeoOverFlowThreshold	numeric > 0 such that if log(bf10) > hyperGeoOverFlowThreshold then the Savage-Dickey adaptation is used for to compute the one-sided Bayes factors, instead of the analytical ones.
oneThreshold	numeric > 0 such that if abs(1 - stat) < oneThreshold, then abs(stat) is viewed as one.
var	numeric > 0 that specifies the asymptotic variance of the approximate likelihood for Kendall's tau

Value

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

Examples

x <- rnorm(100)
y <- rnorm(100)

bcor.test(x, y)
bcor.test(x, y, method="kendall")

z <- data.frame(rnorm(100))
bcor.test(x, y, z)

AlexanderLyNL/bstats documentation built on Sept. 11, 2023, 4:10 p.m.