This paper investigates the effect of incorporating normali-zation of the eigenvectors between iterations in the PAST and RP algorithms for principal component analysis (PCA). In addition, an algorithm denoted as exact eigendecomposi-tion (EE) is proposed for PCA. The algorithms are compared for different configurations using Monte Carlo simulations. Simulation results show that EE has the best performance and that normalization may be used for improving PAST and RP.