On the performance of principal component analysis in multiple gross error identification

In this paper, the use of the principal component test for the identification stage of three existing collective compensation strategies is presented. The three modified techniques are UBET (unbiased estimation of gross errors), SEGE (simultaneous estimation of gross errors) in the form of their recent modifications (MUBET and MSEGE), and SICC (serial identification with collective compensation). These techniques are modified to apply a statistical test based on principal component analysis instead of the nodal, global, and measurement tests they use. The performance of the modified techniques is assessed by means of Monte Carlo simulations. Comparative analysis indicates that PCA tests do not significantly enhance the ability in identification features of these strategies, and even in some cases, it may lower the exact identification performance.