Learn R Programming

SFDesign (version 0.1.3)

maximin.remove: Sequentially remove design points from a design while maintaining low reciprocal distance criterion as possible

Description

This function sequentially removes design points one-at-a-time from a design while maintaining low reciprocal distance criterion as possible.

Usage

maximin.remove(D, n.remove, r = 2 * p)

Value

the updated design.

Arguments

D

the design matrix.

n.remove

number of design points to remove.

r

the power parameter in the maximin.crit. By default it is set as 2p.

Details

maximin.remove sequentially removes design points from a design in a greedy way while maintaining low reciprocal distance criterion (see maximin.crit) as possible. In each iteration, the design point with the largest sum of reciprocal distances with the other design points is removed, that is, \(k^* = \arg\max_k \sum_{i\neq k}\frac{1}{\|\bm x_k - \bm x_i\|^r}\).

Examples

Run this code
n = 20
p = 3
n.remove =  5
D = maximinLHD(n, p)$design
D = maximin.remove(D, n.remove)

Run the code above in your browser using DataLab