Dl. Hintzman et T. Curran, MORE THAN ONE-WAY TO VIOLATE INDEPENDENCE - REPLY, Journal of experimental psychology. Learning, memory, and cognition, 23(2), 1997, pp. 511-513
T. Curran and D. L. Hintzman's (1997) analysis of nonindependence in p
rocess dissociation did not confound aggregation bias with process dep
endence, as L. L. Jacoby and P. E. Shrout (1997) claimed. This reply s
hows that the numerical example presented as undermining Curran and Hi
ntzman's arguments is entirely consistent with their equations and rei
nforces their analysis of the effect of subject-item variance in induc
ing aggregation bias. Process dependence and aggregation bias can be u
nderstood as distinct sources of nonindependence in data. However, pro
cess-dissociation estimates are affected by both.