Computational aspects in uncertainty estimation by Monte Carlo Method

Authors

  • Luis Pablo Constantino Departamento de Metrología Física, Laboratorio Tecnológico del Uruguay, LATU

DOI:

https://doi.org/10.26461/08.02

Keywords:

Metrology, Uncertainty, Monte Carlo, Software, GUM, source code, Delphi

Abstract

The purpose of this paper is to analyze the various aspects related to the development of a software application aimed to uncertainty estimation by Monte Carlo Method, independent from worksheet or third party applications, such as MSExcel, MathLab or R. Difficulties and their available solutions around the needed stages to achieve this goal are discussed, as well as the algorithms needed for creating a math equations parser, the pseudo-random numbers generators with main probability distributions found in uncertainty calculations, and the management of Type A uncertainties.The application developed is tested on three samples: Air density determination according to CIPM equation, the pressuregenerated by a Pressure Balance and the standardizing of a solution of sodium hydroxide as in example A2 of EURACHEM/CITEC CG 4 guide. Finally, these results are compared with the results obtained applying the classical method (GUM) and those obtained using R software.

Downloads

Download data is not yet available.

References

BOX, G. E. P.; MULLER, M. E. A note on the generation of random normal deviates. En: The Annals of Mathematical Statistics. 1958, 29(2)610:611.

BURKS, A. W.; WARREN, D. W.; WRIGHT, J. B. An analysis of a logical machine using parenthesis-free notation. En: Mathematical Tables and Other Aids to Computation. 1954, 46(8):53-57.

DAGPUNAR, J. Principles of random variate generation. Oxford: Clarendon Press, 1988• EURACHEM; CITAC. EURACHEM / CITAC Guide CG 4:quantifying uncertainty in analytical measurement. 3rd ed. London: EURACHEM, [s.d.].

JCGM 100. Evaluation of measurement data: guide to the expression of uncertainty in measurement [En línea]. [s.l.]: JCGM, 2008. [Consulta 2 de mayo de 2013]. Disponible en: http://www.bipm.org/utils/common/documents/jcgm/JCGM_100_2008_E.pdf

JCGM 101. Evaluation of measurement data. Supplement 1 to the “guide to the expression of uncertainty in measurement”. Propagation of distributions using a Monte Carlo method [En línea]. [s.l.]: JCGM, 2008. [Consulta 2 de mayo de 2013]. Disponible en: http://www.bipm.org/utils/common/documents/jcgm/JCGM_101_2008_E.pdf.

KREJCI, Roman. Another random numbers generator(32-bit) [En línea]. [s.l.]: [s.n.], 1999. [Consulta 2 de mayo de 2013]. Disponible en: http://www.rksolution.cz/delphi/tips.htm.

MARSAGLIA, G.; BRAY, T. A convenient method for generating normal variables. En: SIAM Rev.1964, 6(3):260–264.

MATSUMOTO, M.; NISHIMURA, T. Mersenne twister: a 623-dimensionally equidistributed uniform pseudorandom number generator. En: ACM Trans. on Modeling and Computer Simulation. 1998, 8(1):3-30.

PICARD, A.; DAVIS, R. S.; GLÄSER, M.; FUJII, K. Revised formula for the density of moist air. En: Metrologia, 2008, 45(2):149-155.

SAUCIER, R. Computer generation of statistical distributions [En línea]. [s.l.]: Army Research Laboratory, 2000. [Consulta 2 de mayo de 2013]. Disponible en: http://ftp.arl.mil/random/random.pdf.

THOMAS, D.B.; LUK, W.; LEONG, P.H. Gaussian random number generators. En: ACM Comput. Surv. 2007, 39(4):Article 11

Published

2013-12-08

How to Cite

Constantino, L. P. (2013). Computational aspects in uncertainty estimation by Monte Carlo Method. INNOTEC, (8 ene-dic), 13–22. https://doi.org/10.26461/08.02

Issue

Section

Articles