Morgan, Lucy and Nelson, Barry Lee and Titman, Andrew Charles and Worthington, David John (2017) Detecting bias due to input modelling in computer simulation. In: 2017 Winter Simulation Conference (WSC) :. IEEE Press, USA, pp. 1974-1985. ISBN 9781538634301
DetectingBiasDueToInputModellingWSC17.pdf - Accepted Version
Download (247kB)
Abstract
Bias due to input modelling is almost always assumed negligible and ignored. It is known that increasing the amount of real-world data available for modelling input processes causes this form of bias to decrease faster than the variance due to input uncertainty. However, this does not mean bias is irrelevant when considering the error in a simulation performance measure caused by input modelling. In this paper we present a response surface approach to bias estimation in simulation models along with a diagnostic test for identifying, with controlled power, bias due to input modelling of a size that would be concerning to a practitioner.