基于数据列变换的自回归预测方法的改善

Improvement of Autoregressive Prediction Method Based on Data Row Transformation

证明了利用反双曲正弦函数变换能提高数据列的光滑程度,获得结论:设｛x_(k)｝为递增数据列,x_(1)>0,y(k)=ln(x_(k)+(x_(k)~2+1)^(1/2)),则数据列｛y_(k)｝比数据列｛x_(k)｝光滑.给出了改善的自回归预测方法,并且举例加以论证.

This paper proves that the smooth degree of a data row can be increased by transforming the counterhyperbolic sine function. It is concluded that if {x（k）} is an progressive data row, x（1）〉0,y（k）=ln（x（k）＋√x^2（k）＋1 ,then the data row {Y（k）} is smoother than {x（k）}.