TY - JOUR
T1 - The detection of errors in multivariate data using principal components
AU - Hawkins, Douglas M.
PY - 1974
Y1 - 1974
N2 - Serious problems arise in the maintenance of reliability in large data bases, since it becomes difficult to verify incoming data manually. This article considers the case in which the base consists of data vectors following a multivariate normal distribution. Five screening procedures are proposed—a “one-at-a-time” test, the standard χ2test, and three statistics derived from principal component analysis. From analysis of a practical example, it emerges that the statistics derived from principal component analysis have superior performance. © 1974, Taylor & Francis Group, LLC.
AB - Serious problems arise in the maintenance of reliability in large data bases, since it becomes difficult to verify incoming data manually. This article considers the case in which the base consists of data vectors following a multivariate normal distribution. Five screening procedures are proposed—a “one-at-a-time” test, the standard χ2test, and three statistics derived from principal component analysis. From analysis of a practical example, it emerges that the statistics derived from principal component analysis have superior performance. © 1974, Taylor & Francis Group, LLC.
UR - http://www.scopus.com/inward/record.url?scp=0009928479&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0009928479&partnerID=8YFLogxK
U2 - 10.1080/01621459.1974.10482950
DO - 10.1080/01621459.1974.10482950
M3 - Article
VL - 69
SP - 340
EP - 344
JO - Journal of the American Statistical Association
JF - Journal of the American Statistical Association
SN - 0162-1459
IS - 346
ER -