K. Faber et Br. Kowalski, MODIFICATION OF MALINOWSKI F-TEST FOR ABSTRACT FACTOR-ANALYSIS APPLIED TO THE QUAIL-ROOST-II DATA SETS, Journal of chemometrics, 11(1), 1997, pp. 53-72
Malinowski's F-test is a popular method for selecting the number of fa
ctors in abstract factor analysis. Very recently we introduced a modif
ication of this F-test that is based on an alternative number of degre
es of freedom. In this paper the modification is applied to the Quail
Roost II data sets. These artificial data sets have recently been incl
uded in a data base of reference data sets for chemometrical method te
sting. Balanced scaling is applied as a preprocessing step, since the
noise in the raw data violates the requirement of a constant variance.
In comparison with the original test, highly improved pseudorank esti
mates are obtained by using the modification. These results demonstrat
e the potential usefulness of the modified F-test for the analysis of
real data, since the noise structure of the Quail Roost II data sets i
s, for example, very similar to the hypothesized noise structure of da
ta collected from hyphenated instruments. (C) 1997 by John Wiley & Son
s, Ltd.