We show that tests for a break in the persistence of a time series in the classicalI(0) - I(1) framework have serious size distortions when the actual data generatingprocess exhibits long-range dependencies. We prove that the limiting distributionof a CUSUM of squares based test depends on the...

This paper analyzes and quantifies the idea of model risk in the environment of internal modelbuilding. We define various types of model risk including estimation risk, model risk in distributionand model risk in functional form. By the quantification of these concepts we analyzethe impact of...