Premium
Abstract factor analysis of data with multiple sources of error and a modified Faber–Kowalski f ‐test †
Author(s) -
Malinowski Edmund R.
Publication year - 1999
Publication title -
journal of chemometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.47
H-Index - 92
eISSN - 1099-128X
pISSN - 0886-9383
DOI - 10.1002/(sici)1099-128x(199903/04)13:2<69::aid-cem526>3.0.co;2-w
Subject(s) - truncation (statistics) , statistics , factor (programming language) , chemometrics , mathematics , algorithm , computer science , chemistry , chromatography , programming language
Chemical data gleaned from instrumental measurements, such as spectroscopy and chromatography, are often contaminated by multiple sources of error that vary during data collection. Abstract factor analysis (AFA) of such data invariably leads to an excessive number of factors. Various sources of experimental and instrumental artifacts that cause such errors are discussed. Model data, containing multiple sources of error, are created and factor analyzed. By appropriate truncation of the factor space, the number of chemical factors can be determined in these situations using the factor indicator function (IND), the Malinowski F ‐test and a modified Faber–Kowalski F ‐test. Infrared, ultraviolet and visible spectroscopic absorbance data are used to demonstrate the success of the method. Copyright © 1999 John Wiley & Sons, Ltd.