This example builds a state-space model for the plant with the subspace method. The subspace method implemented in this toolkit uses principal component analysis to estimate parameters. This method does not require a zero correlation between the input signal and the output noise. Hence, you can estimate the state-space model for the plant using the subspace method even when the plant is in a closed-loop system. The method that directly applies open-loop identification method to closed-loop data is known as the direct identification method.