PLACKETT-BURMAN DESIGN

Abstract

This article focuses on Placket t-Burman designs (P-B plans) for experiments, which represent an efficient tool for experimental designs, especially in investigating the influence of a large number of factors. Unlike traditional designs such as full factorial experiments (FFE) and fractional factorial experiments (FrFE), P-B plans allow for the effective processing of experiments with a higher number of factors without the need for an exponential increase in the number of trials. Although P-B plans do not directly enable the analysis of interactions between factors, they are ideal for exploring and analyzing the main effects of factors. The article examines in detail the advantages and disadvantages of P-B plans, including their ability to provide experimental error estimates and their efficiency in screening studies. The orthogonality and balance of P-B plans are emphasized, and their application in practice is illustrated with an example of a manufacturing process influenced by multiple factors. The approach based on P-B plans is shown to be a significant contribution to the field of experimental design, especially in situations where it is necessary to efficiently evaluate the impact of a large number of factors with a limited number of trials.