一种以有序变量为因变量的四归分析方法及其地质应用  

A METHOD OF REGRESSIVE AT ANALYSIS USING ORDER VARIABLES AS VARIABLES AND ITS APPLICATION IN GEOLOGY

作　　者：杨毅恒[1] 范继璋[1] 王学孔[2] 夏立显[1] 

机构地区：[1]长春地质学院教学地质教研室 [2]大庆石油学院

出　　处：《长春地质学院学报》1992年第2期236-240,共5页

摘　　要：在这里所研究的回归分析中,因变量是n个样品的序号——有序变量。我们用迭代法求出m个自变量的线性组合,使其各分量的大小顺序与原给的样品序号尽可能一致,文中用具体实例说明了这种方法在矿床统计预测中的应用。In this paper, a special problem about rand estimation has been discussed : Supposing that there are individuals or objects which hare been ranked according to certain variables and described by variables. When we rearrange the last individual with the former n ones as a whole , which rand should it have?The problem can be reduced to regression analysis in which the dependent variable is the rank order of n individuals.This method is applied in the mineral resource appraisal of iron deposit to show its practical efficiency.

关 键 词：有序变量 回归分析 秩估计 矿床 

分 类 号：P628.1[天文地球—地质矿产勘探]