Higher-order statistics method is an overhead subject in the fields of signal processing in the world in recent years. The pulse signals are analyzed by applying parametric bispectrum estimation. Non-Gaussian AR model is for calculating the bispectrum of pulse signals for 15 heroin addicts and 15 healthy persons. Characteristic parameters of magnitude bispectrum of the pulse signals are obtained by using horizontal slices of magnitude bispectrum. Characteristic parameters of bispectrum phase of the pulse signals are obtained by using horizontal slices of bispeetrum phase. Moreover,two primary criterions are also obtained by using the characteristic parameters. Exactness ratios of two pnmary criterions reach 93.3% and 90%, respectively. The research result shows that parametric bispectmm estimation for analyzing pulse signals of heroin addicts is really an effective method.