摘要
对我国近两年490批次、23个进口国的进口铁矿中SiO2含量进行了总体统计分析,在数据统计分布特征研究基础上,使用内核密度估计对进口铁矿SiO2含量进行数据多态性分析,使用自举法对原始数据样本值重复取样以获得稳健的SiO2含量代表值估计及标准偏差,并证明以自举法重新取样样本分布的均值与标准偏差作为有限单次样本代表值是合理、有效的。
Content characteristics of silica dioxide in iron ores imported from 23 countries, totally 490 batches, in recent two years are investigated by statistical methods. Based on the study on data distribution characteristics, a new robust statistics method,kernel density estimation, coupled with bootstrap method is introduced to acquire the representative values of silica dioxide content and the standard deviations for imported iron ores. It is clearly demonstrated that this method shows a prior advantage to give a robust description in explanation for central tendency and variation of data profiles. It has also proved that the conclusion of substitution of bootstrap mean value and its standard deviation for the representative value of silica dioxide content from single specimen analysis is reasonable and effective.
出处
《岩矿测试》
CAS
CSCD
2007年第1期29-32,共4页
Rock and Mineral Analysis
关键词
铁矿
二氧化硅
代表值
统计学描述
内核密度估计
自举法
ion ore
silica dioxide
representative value
statistical description
kernel density estimation
bootstrap
