摘要
在研究变量数列修匀技术的光滑性和拟合度准则的基础上，将中位数引入到加权移动平均法公式中，构建新的数列修匀方法：加权算术平均数──中位数混合移动平均法．论文的后半部分通过实例对加权移动平均法、加权算术平均数──中位数混合移动平均法、指数平滑法和Ｂａｙｅｓｉａｎ方法等四种修匀方法的光滑性和拟合度作了对比研究，最后得出结论：加权算术平均数中位数混合移动平均法具备了计算方法简便、光滑性能好、拟合度较高等特点，对变量数列具有广泛的适应性和良好的修匀效果．
Through the analysis of two properties of smoothing and fitting, this paper puts forward a new graduated method: the mixed moving average method of weighted-arithmetic-mean and median. Compare four methods of Weighted-Moving-Average, Exponential-Smoothing, Bayesian Graduation and the New Graduated Method, the new graduated method would generate a new series of varieties with a good smoothing and excel- lent fitting.
出处
《昆明理工大学学报（理工版）》
2001年第5期50-55,共6页
Journal of Kunming University of Science and Technology(Natural Science Edition)
