# krp: Function to compute Khatri-Rao product In rrcov3way: Robust Methods for Multiway Data Analysis, Applicable also for Compositional Data

## Description

The function `krp(A,B)` returns the Khatri-Rao product of two matrices `A` and `B`, of dimensions I x K and J x K respectively. The result is an IJ x K matrix formed by the matching column-wise Kronecker products, i.e. the k-th column of the Khatri-Rao product is defined as `kronecker(A[, k], B[, k])`.

## Usage

 `1` ```krp(A, B) ```

## Arguments

 `A` Matrix of order I x K. `B` Matrix of order J x K.

## Value

The IJ x K matrix of columnwise Kronecker products.

## Note

`A` and `B` must have the same number of columns.

## Author(s)

Valentin Todorov [email protected]

## References

Khatri, C.G. and Radhakrishna Rao, C. (1968). Solutions to Some Functional Equations and Their Applications to Characterization of Probability Distributions. Sankhya: Indian J. Statistics (Series A), 30:167-180. Smilde, A., Bro R. and Gelardi, P. (2004). Multi-way Analysis: Applications in Chemical Sciences, Chichester:Wiley

## Examples

 ```1 2 3 4 5 6 7``` ```A <- matrix(1, nrow=5, ncol=2) B <- matrix(1:4, ncol=2) krp(A,B) A <- matrix(1:10, ncol=2, byrow=TRUE) B <- diag(1,2) krp(A,B) ```

rrcov3way documentation built on June 23, 2017, 4:45 a.m.