Robust monitoring of CAPM portfolio betas II

In this work, we extend our study in Chochola et al. [7] and propose some robust sequential procedure for the detection of structural breaks in a Functional   Capital Asset Pricing Model (FCAPM). The procedure is again based on MM-estimates and partial weighted sums of MM-residuals and “robustifies” the approach of Aue et al. [3], in which ordinary least squares (OLS) estimates have been used. Similar to Aue et al. [3], and in contrast to Chochola et al. [7], high-frequency data can now also be taken into account. The main results prove some null asymptotics for the suggested test as well as its consistency under local alternatives. In addition to the theoretical results, some conclusions from a small simulation study together with an application to a real data set are presented in order to illustrate the finite sample performance of our monitoring procedure.