Comments on adaptive IIR filtering with monic normalization

An equation error algorithm is known to give a significant bias in case the output signal is contaminated by white noise. A simple bias removal scheme was proposed previously. Here, we provide some complementary analysis of that algorithm. It is shown how it can be interpreted as an instrumental variable method. Further, by analytical examples, it is demonstrated that the method does not always lend to convergent estimates, even for arbitrarily small step sizes.