mean2.2014Thulin {SHT}

Two-sample Test for Multivariate Means by Thulin (2014)

Description

Given two multivariate data X and Y of same dimension, it tests

H_0 : \mu_x = \mu_y\quad vs\quad H_1 : \mu_x \neq \mu_y

using the procedure by Thulin (2014) using random subspace methods. We did not enable parallel computing schemes for this in that it might incur huge computational burden since it entirely depends on random permutation scheme.

Usage

mean2.2014Thulin(X, Y, B = 100, nreps = 1000)

Arguments

X

an (n_x \times p) data matrix of 1st sample.

Y

an (n_y \times p) data matrix of 2nd sample.

B

the number of selected subsets for averaging. B\geq 100 is recommended.

nreps

the number of permutation iterations to be run.

Value

a (list) object of S3 class htest containing:

statistic

a test statistic.

p.value

p-value under H_0.

alternative

alternative hypothesis.

method

name of the test.

data.name

name(s) of provided sample data.

References

Thulin M (2014). “A high-dimensional two-sample test for the mean using random subspaces.” Computational Statistics & Data Analysis, 74, 26–38. ISSN 01679473.

Examples

## CRAN-purpose small example
smallX = matrix(rnorm(10*3),ncol=10)
smallY = matrix(rnorm(10*3),ncol=10)
mean2.2014Thulin(smallX, smallY, B=10, nreps=10) # run the test


## Compare with 'mean2.2011LJW' 
## which is based on random projection.
n = 33    # number of observations for each sample
p = 100   # dimensionality

X = matrix(rnorm(n*p), ncol=p)
Y = matrix(rnorm(n*p), ncol=p)

## run both methods with 100 permutations
mean2.2011LJW(X,Y,nreps=100,method="m")  # 2011LJW requires 'm' to be set.
mean2.2014Thulin(X,Y,nreps=100)