OUTLIER DETECTION IN CALIBRATION

被引:20
作者
HU, YZ
SMEYERSVERBEKE, J
MASSART, DL
机构
[1] Pharmaceutical Institute, Vrije Universiteit Brussel, B-1090 Brussels
关键词
D O I
10.1016/0169-7439(90)80051-7
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Hu, Y., Smeyers-Verbeke, J. and Massart, D.L., 1990. Outlier detection in calibration. Chemometrics and Intelligent Laboratory Systems, 9: 31-44. Four calibration methods recently introduced in analytical chemistry, namely the single median method, repeated median method, fuzzy calibration, and least median of squares, are compared with least squares calibration. For fuzzy calibration, the program includes two variants, one with a circle, and one with a line as support. Monte-Carlo simulation was performed to compare the performance of the five methods in detecting outliers. © 1990.
引用
收藏
页码:31 / 44
页数:14
相关论文
共 34 条
  • [1] Draper, Smith, Applied Regression Analysis, (1981)
  • [2] Draper, Smith, Applied Regression Analysis, (1981)
  • [3] Cook, Detection of influential observations in linear regression, Technometrics, 19, pp. 15-18, (1977)
  • [4] Cook, Weisber, Residuals and Influence in Regression, (1982)
  • [5] Montgomery, Peck, Introduction to Linear Regression Analysis, (1982)
  • [6] Rousseeuw, Leroy, Robust Regression and Outlier Detection, pp. 1-18, (1987)
  • [7] Rousseeuw, Leroy, Robust Regression and Outlier Detection, (1987)
  • [8] Hodge, Efficiency in normal samples and tolerance of extreme values for some estimates of location, Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1, pp. 163-168, (1967)
  • [9] Hampel, A general qualitative definition of robustness, The Annals of Mathematical Statistics, 42, pp. 1887-1896, (1971)
  • [10] Donoho, Huber, The notation of breakdown point, A Festschrift for Erich Lehmann, (1983)