NIST Uncertainty Machine

https://uncertainty.nist.gov/

The NIST Uncertainty Machine is a web-based software application produced by the National Institute of Standards and Technology (NIST) to evaluate the measurement uncertainty associated with a scalar or vectorial output quantity that is a known and explicit function of a set of scalar input quantities for which estimates and evaluations of measurement uncertainty are available.

The NIST Uncertainty Machine implements the approximate method of uncertainty evaluation described in the "Guide to the expression of uncertainty in measurement" (GUM), and the Monte Carlo method of the GUM Supplements 1 and 2. Input and output quantities are modeled as random variables, and their probability distributions are used to characterize measurement uncertainty. For inputs that are correlated, the NIST Uncertainty Machine offers the means to specify the corresponding correlations, and the manner in which they will be taken into account.

The output of the NIST Uncertainty Machine comprises:

• An estimate of the output quantity (measurand)
• Evaluations of the associated standard and expanded uncertainties
• Coverage intervals for the true value of the measurand
• An uncertainty budget that quantifies the influence that the uncertainties of the inputs have upon the uncertainty of the output

For details about the NIST Uncertainty Machine, and examples of its application, please refer to its user's manual, and to T. Lafarge and A. Possolo (2015) "The NIST Uncertainty Machine", NCSLI Measure Journal of Measurement Science, volume 10, number 3 (September), pages 20-27.

NIST is the national metrology institute of the United States of America. Visit us at www.nist.gov. Founded in 1901, NIST is a non-regulatory federal agency within the U.S. Department of Commerce. NIST's mission is to promote U.S. innovation and industrial competitiveness by advancing measurement science, standards, and technology in ways that enhance economic security and improve our quality of life.

Bug reports and suggestions for improvement are most welcome: please send them to antonio.possolo@nist.gov.

Instructions

• Select the number of input quantities.
• Change the quantity names if necessary.
• For each input quantity choose its distribution and its parameters.
• Choose and set the correlations if necessary.
• Choose the number of realizations.
• Write the definition of the output quantity in a valid R expression.
• Run the computation.