Abstract In recent years there has been a growing interest in studying bilinear time series models. However, there are difficult problems related to the order identification of these models. In this paper, we consider the bilinear time series models, Xt = BXt-k et-1 + et , k>i, k=i and k<i, and propose some methods of order identification based on the structure of autocovarance of {X2t} and the third-order-automoment of {xt}. Decision rules as well as simulated bilinear time series are compared. An advantage of our methods is its simple of implementation.