为了方便用户编制大型多媒体系统的时序描述，组合模型是必须的。
In order to facilitate users to specify the temporal specification at the time of authoring a multimedia program, a composition model is needed.
结果表明三因素模型结构不稳定，但短期比长期结构稳定性要高；大部分组合回归系数时序稳定性较差，同时ARMA和GARCH模型对每个回归系数时间序列进行预测显示有较好的预测能力。
The results show that the model is instability in the long run, most coefficient is non-stationary, and we can preferably forecast the coefficient by using the ARMA, GARCH model.
应用推荐