Mnf. Li et S. Olejnik, THE POWER OF RASCH PERSON-FIT STATISTICS IN DETECTING UNUSUAL RESPONSE PATTERNS, Applied psychological measurement, 21(3), 1997, pp. 215-231
Five Rasch person-fit indexes were compared on their ability to detect
spuriously high and low nonsystematic response patterns. The moderati
ng effects of test dimensionality, type of misfit, and test length wer
e also investigated. Results indicated that (1) all fit indexes were n
ot significantly correlated with Rasch trail estimates; (2) their samp
ling distributions deviated significantly from the standard normal dis
tribution; (3) using adjusted cutoff criteria to identify misfit, ECI2
(Z), ECI4(Z), l,(z) and WSR-C performed equally well in the detection
of misfit regardless of test dimensionality, type of misfit, and test
length (however, only I, is recommended for the spuriously high respon
se patterns for a two-dimensional test); (4) the false positive rate f
or each index was less than the nominal .05 level; (5) Rasch person-fi
t indexes are more sensitive to spuriously high response patterns than
to spuriously low response patterns on a two-dimensional test, but wh
en the test is unidimensional they demonstrate equal sensitivity to bo
th types of misfit; and (6) the detectability of misfit increases with
test length.