A Monte Carlo Study of Some Tests of Model Adequacy in Time Series Analysis
通过蒙特卡洛实验，考察了时间序列中自回归和移动平均模型拟合检验的小样本性质，比较渐近等价方法的表现，并评估过度拟合及非正态性对检验功效和稳健性的影响。
In this article, we conduct a Monte Carlo experiment of several computationally attractive tests of model adequacy in time series analysis. The experiment is designed to examine the small-sample properties of tests of fitted autoregressive and moving average models, to compare the performances of asymptotically equivalent procedures, to consider the effects on estimated significance levels and powers of testing against both appropriate and inappropriate alternatives, to evaluate the effects on power of progressively (and unnecessarily) overfitting a model, and to examine the robustness of the tests to departures from normality.