mvt_test {BFpack}

Multivariate Student t test

Description

First step to performs a Bayesian multivariate one sample Student t test using the (adjusted) fractional Bayes factor using the BF() function.

Usage

mvt_test(X, Y, null = NULL, paired = FALSE, ...)

Arguments

X

a data matrix with the variables in the columns.

Y

an optional data matrix with the variables in the columns.

null

a vector of the null values of the variables.

paired

a logical indicating whether you want a multivariate paired t-test.

...

further arguments to be passed to or from methods.

Details

X must be a data matrix and null must be a vector of the assumed null values of the variables.

Value

An object that can be applied to the BF().

References

Mulder, J. and Gu, X. (2023). Bayesian Testing of Scientific Expectations under Multivariate Normal Linear Models. Multivariate Behavioral Research, 57, 767-783. DOI: 10.1080/00273171.2021.1904809.

Examples

mvt_fmri <- mvt_test(fmri[,1:2],null = c(0,0))
BF(mvt_fmri)

# the same test can be executed via the lm() function
intercept <- rep(1,nrow(fmri))
lm1 <- lm(cbind(Face,Vehicle) ~ -1 + intercept, data=fmri)
BF(lm1,hypothesis="intercept_on_Face=intercept_on_Vehicle=0")