摘要
t型估计的基本思想是以t分布刻画误差分布,可从形式上得到t型估计解的等价权形式,但t型估计不能抵抗病态性的缺点。针对这一缺点,利用广义压缩型抗差估计的思想,对t型估计位置参数的解进行压缩,得到了广义压缩t型估计,并讨论了广义压缩t型估计的具体形式、偏参数选取、迭代方案等。算例证实了该方法的有效性。
T-type estimation is a new kind of robust estimations, which takes t-distribution as the error distri- bution and has some advantages in some respects. The equivalent weight form of t-type estimation is presented. A disadvantage of t-type estimation that it cannot resist ill-conditioning is analyzed. To overcome this drawback, according to the idea of the generalized shrunken type robust estimation, the generalized shrunken t-type estimation is presented, which shrinks the solution of the location parameters. Some important problems of this estimation are discussed. A numerical example shows the validity of the method presented.
出处
《大地测量与地球动力学》
CSCD
北大核心
2009年第3期114-118,共5页
Journal of Geodesy and Geodynamics
基金
国家自然科学基金(40474007)
国家杰出青年科学基金(40125013)
"基础地理信息与数字化技术"山东省重点开放实验室课题(SD040202)
河南省自然科学基金(0511010100)
关键词
粗差
t型估计
抗差有偏估计
广义压缩型抗差估计
广义压缩t型估计
gross errors
t-type estimation
robust biased estimations
generalized shrunken type robust estimation
generalized shrunken t-type estimation