Mathematical aggregation of probabilistic expert judgements

Mathematical aggregation of the probabilistic expert’s judgements in a structured expertjudgement analysis is said to be relevant and critical. Due to absence of data, the judgementsof the experts are used to perform forecasting and risk analysis. However, there is a gapin the literature where there may exist correlation in such judgements. This research isconcerned with the situation where multiple experts are providing their numerical probabilityassessment for multiple quantities of interest. For each quantity of interest, there is a needof linear optimal weight on the basis of the experts’ judgement. This optimality is achievedby minimising the mean squared error (MSE) between the unbiased judgements provided bythe experts for a quantity of interest, whose true value is unknown. Further, it has beenassumed that the judgements of the experts is dependent on the sets of multiple quantitiesof interests, while, their errors presented in the judgements are correlated. This thesispresents two novel mathematical methods towards aggregating expert’s judgement throughlinear pooling. The first method is based on the empirical Bayes parametric formulation,and the second method is non-parametric. Both the chosen methods are compared usinga stimulation study. This is to examine the performance of a given dependency structurewhich is further illustrated using a case study. In this context, a highly positive correlatedexpert gets the least weight when compared to an independent or negatively correlatedexperts. As stated in literature and reaffirmed through the simulation studies in this thesis,asymptotically the non-parametric approach has a slower error rate convergence, wherethe error is defined in terms of the MSE in comparison to the parametric empirical Bayesmethod. Based on the simulation study and the case study results, it is found that theempirical Bayes method outperforms the non-parametric method.

Name dc:type.qualificationname

phd

Level dc:type.qualificationlevel

doctoral-pg

Grantor dc:publisher.institution

University of Strathclyde

Year dc:date.issued

2017

Author dc:creator

• Ganguly, Taposhri

Advisors dc:contributor.advisor

• Quigley, John
• Walls, Lesley

DOI

10.48730/r6sa-pq11

Identifier

T14766

Author Identifier

201064195

OAI identifier oai:identifier

oai:strathclyde:t148fh22s