compute_CV {QuadratiK}R Documentation

Compute the critical value for two-sample KBQD tests

Description

This function computes the critical value for two-sample kernel tests with centered Gaussian kernel using one of three methods: bootstrap, permutation, or subsampling.

Usage

compute_CV(B, Quantile, data_pool, size_x, size_y, h, method, b = 1)

Arguments

B

the number of bootstrap/permutation/subsampling samples to generate.

Quantile

the quantile of the bootstrap/permutation/subsampling distribution to use as the critical value.

data_pool

a matrix containing the data to be used in the test.

size_x

the number of rows in the data_pool matrix corresponding to group X.

size_y

the number of rows in the data_pool matrix corresponding to group Y.

h

the tuning parameter for the kernel test.

method

the method to use for computing the critical value (one of "bootstrap", "permutation", or "subsampling").

b

the subsampling block size (only used if method is "subsampling").

Value

the critical value for the specified method and significance level.

References

Markatou Marianthi, Saraceno Giovanni, Chen Yang (2023). “Two- and k-Sample Tests Based on Quadratic Distances.” Manuscript, (Department of Biostatistics, University at Buffalo)


[Package QuadratiK version 1.1.1 Index]