This paper describes a novel method using fractional calculus to estimate non-integer moments of a random variable from the measured Laplace transform of its probability density function. We demonstrate that the ω-th moment (ω∈ R) of the random variable can be directly obtained by a linear transformation of the data. When ω> 0, computation of moments corresponds to fractional integration of the data. When ω≤0, computation of moments corresponds to fractional differentiation.
展开▼