University of Twente Student Theses

Login

The accuracy and robustness of the correlation bootstrap method and the implicit correlation method for loss-reserving triangles : exploring the impact of data quality and outliers on the correlation estimate and challenging the assumptions of these methods.

Remmelink, M. (2021) The accuracy and robustness of the correlation bootstrap method and the implicit correlation method for loss-reserving triangles : exploring the impact of data quality and outliers on the correlation estimate and challenging the assumptions of these methods.

[img] PDF
2MB
Abstract:Within the regulatory framework of Solvency II, the correlation parameter has an important role in the aggregation of the risk capitals. This thesis researches the accuracy and robustness of the correlation bootstrap method and the implicit correlation method when estimating the correlation parameter between loss-reserving triangles. Both methods use a bootstrapping technique to create a distribution of the profit & loss for a homogeneous risk group (HRG). By determining the SCR for two individual HRGs and a third SCR for the combined portfolio, it is possible to derive an implied correlation parameter based on the standard formula. The difference between the two methods is in the methodology used to obtain the SCR for the combined portfolio. In this study, the methods are explained step by step and a simulation study is performed to get insights into the performance of both methods. Furthermore, the assumptions belonging to the correlation bootstrap method and the implicit correlation method are challenged.
Item Type:Essay (Master)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:83 economics
Programme:Industrial Engineering and Management MSc (60029)
Link to this item:https://purl.utwente.nl/essays/86043
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page