Variance-Bias Tradeoff in Finite Impulse Response Estimates Obtained by Correlation Analysis

Correlation analysis can in some cases produce better identification results than an ordinary least squares approach. This is for example the case when a Finite Impulse Response system is estimated from illconditioned input-output measurements. In this report, the correlation analysis method is rewritten as a regularized least squares algorithm and the performance of the method is discussed in this context. It turns out that the fact that correlation analysis can be viewed as a kind of regularization explains why and in what sense this method sometimes produces more accurate estimates than the ordinary least squares approach.