Approximate theory-aided robust efficient factorial fractions under baseline parametrization

TL;DR

This paper develops efficient fractional factorial designs using approximate theory and discretization, focusing on robustness to model misspecification and demonstrating effectiveness with small run sizes.

Contribution

It introduces a novel approach combining approximate theory and discretization for designing robust fractional factorial experiments under baseline parametrization.

Findings

Designs are robust to model misspecification.

Method performs well with small run sizes.

Provides practical examples demonstrating effectiveness.

Abstract

With reference to a baseline parametrization, we explore highly efficient fractional factorial designs for inference on the main effects and, perhaps, some interactions. Our tools include approximate theory together with certain carefully devised discretization procedures. The robustness of these designs to possible model misspecification is investigated using a minimaxity approach. Examples are given to demonstrate that our technique works well even when the run size is quite small.