The Generalized Lambda Distribution for the Expression of Measurement Uncertainty

The generalized lambda distribution family fits the probability distributions of a wide variety of data sets, including the most important distributions in measurement applications (normal, uniform, student's t, U-shaped, exponential). This paper illustrates how the representation of measurement uncertainty by means of the four parameters of the distribution can extend the information about the results of a measurement and their uncertainty. Such representation allows an immediate calculation of coverage intervals and is particularly able to support the techniques commonly applied in estimation of combined uncertainty. Moreover, in order to include the classical measurement information, a novel X-parametrization is proposed