Monte Carlo Simulation in Uncertainty Evaluation: Strategy, Implications and Future Prospects

Abstract

Monte Carlo simulation (MCS) is an approach based on the propagation of the full probability distributions. It was introduced by the Joint Committee for Guides in Metrology (JCGM) in the supplement I-JCGM 101:2008. It is used to resolve the problem of calculating measurement uncertainties of complex measurands through simulation of random variables. Further, supplement II on “Extension to any number of output quantities” was published in 2011 and supplement III on “Modelling” is under publication. These supplements cover broader range of measurement issues which are not handled using law of propagation of uncertainty (LPU) alone and provide an alternative method to the conventional LPU approach. The MCS method plays a vital role in cases, where the linearization of the model does not provide enough depiction, or the probability density function of the output quantity deviates considerably from the Gaussian distribution. The SWOT analysis describes the strengths, weaknesses, opportunities and threats associated with the use of MCS in the measurement uncertainty evaluation and is addressed in this paper. The paper also summarizes the implications and prospects associated with the use of MCS in uncertainty evaluation for wide usage in solving problems in physical, biological and engineering sciences.