Probability distribution in nonlinear estimation-a measurement dedicated approach

Uncertainty characterization of the measurement quantity by a probability density function is considered. The performance evaluation of the probability density function estimation of the measurement is investigated. It is given by either the geometrical approach or the proposed approach, called "corrected normality probability". An efficient method, the so-called Monte Carlo Latin hypercube sampling, is used to compare the predicted results of both approaches. The choice between these methods critically depends on the error variance and the model nonlinearity.