A lower confidence limit for the number of signals

We propose a multi-step procedure for constructing a lower confidence limit for the number of signals present. We derive the probability of a correct estimation, P(CE), and the least favorable configuration (LFC) for our procedure. Under LFC, the P(CE) attains its minimum over the parameter space of all eigenvalues. Therefore a minimum sample size can be determined in order to implement our procedure with a guaranteed probability requirement.