Semi-parametric modification of cumulative sum algorithms for the change-point detection of non-Gaussian sequences

The expansion of logarithm likelihood ratio in the stochastic series to find the sequential change-point detection of non-Gaussian sequences is used. The moment criteria of the minimum of upper limit error probabilities sum to find the expansion coefficients is applied. The proposed method is a semi-parametric type of cumulative sum (CUSUM) algorithm which needs of higher-order statistics. Results show that polynomial algorithms are more effective in comparison with similar non-parametric procedures.