知识与财富的链接
对自回归模型的5种定阶方法（FPE、AIC、BIC、L1和L2准则）作了概述,并应用上述方法对青岛月平均温度序列进行了自回归模型定阶试验。结果指出,FPE、AIC和L1准则选择自回归模型的阶数较高,L2准则选择自回归的阶数为中等,BIC准则确定的阶数最低。文章还提出了一个应用自回归模型递推预报月平均温度的方法,预报实践证明,由BIC准则产生的低阶自回归模型的效果优于其它方法。
The methods of determining the optimum order of autoregressive(AR )models,such as FPE,AIC,BIC,L_1 and L_2 were summarized and tested by using the monthlymean temperature data in Qingdao. The selected orders of the AR model by use of theFPE,AIC and L_1 criteria are the highest,medium by L_2 and the lowest by BIC,respectively.Additionally,a recurrence method of AR model was suggested to forecastthe monthly mean temperatures in Qingdao. It has been proved by the forecast practicethat the low order AR model from the BIC criterion is more efficient.
