SIPVADE: A new computer programme with seventeen statistical tests for outlier detection in evaluation of international geochemical reference materials and its application to Whin Sill Dolerite WS-E from England and Soil-5 from Peru
Sp. Verma et al., SIPVADE: A new computer programme with seventeen statistical tests for outlier detection in evaluation of international geochemical reference materials and its application to Whin Sill Dolerite WS-E from England and Soil-5 from Peru, GEOSTAND N, 22(2), 1998, pp. 209-234
Citations number
26
Categorie Soggetti
Earth Sciences
Journal title
GEOSTANDARDS NEWSLETTER-THE JOURNAL OF GEOSTANDARDS AND GEOANALYSIS
A new computer programme was written in programming language TURBOC, which
enables us to apply a procedure involving seventeen statistical tests (a to
tal of sixty five single or multiple outlier versions of these tests) for o
utlier detection in univariate sample at a high confidence level of 99% (si
gnificance level alpha = 0.01). The outlying observations should be evaluat
ed first for technical reasons and then rejected manually from the data bas
e until no more outliers are detected and the final statistical parameters
are computed from the remaining data. This programme has been used successf
ully to process two reference material data bases: WS-E from England and So
il-5 from Peru. The final mean values for WS-E are more reliable (character
ized by smaller standard deviations and narrower confidence limits) than th
ose obtained earlier using a different statistical approach. The applicatio
n of a large number of statistical tests to Soil-5 also resulted in smaller
standard deviation values for most elements than the method involving a li
mited number of such tests. For WS-E, some laboratories seem to have produc
ed multiple data that were detected as statistical outliers. A close analys
is of the distribution of outliers as a function of laboratory, country and
analytical method leads to a technical justification for these outlying ob
servations, probably in terms of inadequate QA/QC practices. Use of geochem
ical criteria indicates that the new mean values in WS-E might be closer to
the "true" concentrations. This procedure of outlier detection and elimina
tion is therefore recommended in the study of the existing RM.