Hi,
It was really amazing to see Measurents.jl handling uncertainty propagation … However I would like to know what is the level of confidence used in the uncertainty calculation
in measurements.jl.
Does that takes into account only expanded uncertainty with 95% confidence?
Can I find expanded uncertainty with 99% confidence in measurements.jl? And how?
Thanks in advance!
According to one of the Measurements.jl references (JCGM, “Evaluation of measurement data - Guide to the expression of uncertainty in measurement”, BIPM, September 2008), the linear error propagation theory used, seems to be formulated in terms of standard deviations, but it also applies to the propagation of multiples of these with the following caveats:
“If each standard deviation σi is replaced by a multiple k*σi, with the same k for each σi, the standard deviation of the output quantity z is replaced by k*σz. However, it does not apply to the propagation of confidence intervals. If each σi is replaced with a quantity δi that defines an interval corresponding to a given level of confidence p, the resulting quantity for z, δz, will not define an interval corresponding to the same value of p unless all of the wi (input uncertainties) are described by normal distributions.”
That was indeed really informative! Thanks for your time…