Abstract
A common procedure in testing analytical methods is to send a portion of each of a number of samples to each of several laboratories. The results of such a study are submitted to statistical analysis to determine the two important variance components in the problem: replication error and laboratory bias. Outliers are relatively common in these data both among laboratory effects and among the residuals. This paper presents a method of analysis for interlaboratory studies that is robust to the existence of outliers and long-tailed distributions of random effects. Theoretical considerations as well as a Monte Carlo study are adduced as support for this new technique.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 421-431 |
| Number of pages | 11 |
| Journal | Biometrika |
| Volume | 70 |
| Issue number | 2 |
| DOIs | |
| State | Published - Aug 1983 |
Fingerprint
Keywords
- Biweight estimate
- Huber estimate
- Least squares
- Monte Carlo method
- Outlier
- Random effects
- Robust estimation
- Variance component
ASJC Scopus subject areas
- Statistics, Probability and Uncertainty
- Applied Mathematics
- Mathematics(all)
- Statistics and Probability
- Agricultural and Biological Sciences (miscellaneous)
- Agricultural and Biological Sciences(all)
Cite this
Robust statistical analysis of interlaboratory studies. / Rocke, David M.
In: Biometrika, Vol. 70, No. 2, 08.1983, p. 421-431.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Robust statistical analysis of interlaboratory studies
AU - Rocke, David M
PY - 1983/8
Y1 - 1983/8
N2 - A common procedure in testing analytical methods is to send a portion of each of a number of samples to each of several laboratories. The results of such a study are submitted to statistical analysis to determine the two important variance components in the problem: replication error and laboratory bias. Outliers are relatively common in these data both among laboratory effects and among the residuals. This paper presents a method of analysis for interlaboratory studies that is robust to the existence of outliers and long-tailed distributions of random effects. Theoretical considerations as well as a Monte Carlo study are adduced as support for this new technique.
AB - A common procedure in testing analytical methods is to send a portion of each of a number of samples to each of several laboratories. The results of such a study are submitted to statistical analysis to determine the two important variance components in the problem: replication error and laboratory bias. Outliers are relatively common in these data both among laboratory effects and among the residuals. This paper presents a method of analysis for interlaboratory studies that is robust to the existence of outliers and long-tailed distributions of random effects. Theoretical considerations as well as a Monte Carlo study are adduced as support for this new technique.
KW - Biweight estimate
KW - Huber estimate
KW - Least squares
KW - Monte Carlo method
KW - Outlier
KW - Random effects
KW - Robust estimation
KW - Variance component
UR - http://www.scopus.com/inward/record.url?scp=0000750772&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0000750772&partnerID=8YFLogxK
U2 - 10.1093/biomet/70.2.421
DO - 10.1093/biomet/70.2.421
M3 - Article
VL - 70
SP - 421
EP - 431
JO - Biometrika
JF - Biometrika
SN - 0006-3444
IS - 2
ER -