Risk analysis of catastrophes using experts' judgements: An empirical study on risk analysis of major civil aircraft accidents in Europe

We present an empirical study performed on risk analysis of major civil aircraft accidents in Europe by using expert judgements. The main goal is to investigate in practice some theoretical models which have been constructed previously. These models calibrate and aggregate judgements of the experts in order to predict the future risks. The statistical tools which are used in this work are Bayesian. The main results of this pilot study are: (i) The models which we used in order to predict the future risks seem to work satisfactorily. (ii) Calibration of the experts' assessed risks are needed. (iii) We introduced two different methods to estimate the assessment error variances of the experts. The first method is built on probability assessments and the second method on interval assessments. The differences between these two methods are in general not remarkably prominent. (iv) All individual distributions are positively skewed. The aggregated distributions are less skewed.