Unreplicated Designs for Homogeneous Random Noise Exploration

Abstract

Grasping the variation of system plays a crucial role in industrial systems. Different treatment combinations provide the information about the fluctuation of response surfaces. However, they are unable to extract the exact information of pure errors especially when the model is complex. It is known that conducting replicates is one solution. On the other hand, replication does not provide information about response surfaces and therefore is usually treated as a waste. In this talk, we introduce a loss function and aim at constructing unreplicated designs, which are expected to have sufficient information of pure error and are capable of exploring the response surface. (Joint work with Mr. Wei-Hsiang Yu) ??? Keywords: Pure error; Gaussian process; Quality improvement; Dispersion effects