Bootstrap error-adjusted single-sample technique
In statistics, the bootstrap error-adjusted single-sample technique (BEST or the BEAST) is a non-parametric method for estimating the distribution of a sample.[1] It is based on a statistical method called bootstrapping. BEST provides advantages over other methods such as the Mahalanobis metric, because it does not assume equal covariance for all spectral groups[clarification needed] or that each group is drawn for a normally distributed population.[2]
Application
BEST is used in detection of sample tampering in pharmaceutical products. Valid (unaltered) samples are defined as those that fall inside the cluster of training-set points when the BEST is trained with unaltered product samples. False (tampered) samples are those that fall outside of the same cluster.[1]
References
- ^ a b Attention: This template ({{cite doi}}) is deprecated. To cite the publication identified by doi:10.1021/ac00142a008, please use {{cite journal}} (if it was published in a bona fide academic journal, otherwise {{cite report}} with
|doi=10.1021/ac00142a008instead. - ^ Attention: This template ({{cite jstor}}) is deprecated. To cite the publication identified by jstor:2685844, please use {{cite journal}} with
|jstor=2685844instead.
Further reading
- Lodder, R.; Hieftje, G. (1988). "Quantile BEAST Attacks the False-Sample Problem in Near-Infrared Reflectance Analysis". Applied Spectroscopy. 42 (8): 1351–1365.
 | This statistics-related article is a stub. You can help Wikipedia by expanding it. |