Using the Bootstrap as an Aid in Choosing the Approximate Representation for Vector Time Series
提出一种基于自助法的方法，通过比较各近似模型的预测表现，为向量自回归模型的状态空间表示选择最佳近似，优于仅依赖汉克尔奇异值的方法。
In this article, a procedure is presented to use the bootstrap in choosing the best approximation in terms of forecasting performance for the equivalent state-space representation of a vector autoregressive model. It is found that the proposed procedure, which uses each approximant's forecasting performance, can enhance considerably an approach based simply on the estimated Hankel singular values.