A note on Rebonato and Jäckel's parametrization method for finding nearest correlation matrices

Alec N. Kercheval

Portfolio risk forecasts are often made by estimating an asset or factor correlation matrix. However, estimation difficulties or exogenous constraints can lead to correlation matrix candidates that are not positive semidefinite (psd). Therefore, practitioners need to reimpose the psd property with the minimum possible correction. Rebonato and J?ackel (2000) raised this question and proposed an approach; in this paper we improve on that approach by introducing a more geometric perspective on the problem.