In fMRI there are two classes of inference: one aims to make a comment abou
t the "typical" characteristics of a population, and the other about "avera
ge" characteristics. The first pertains to studies of normal subjects that
try to identify some qualitative aspect of normal functional anatomy. The s
econd class necessarily applies to clinical neuroscience studies that want
to make an inference about quantitative differences of a regionally specifi
c nature. The first class of inferences is adequately serviced by conjuncti
on analyses and fixed-effects models with relatively small numbers of subje
cts. The second requires random-effect analyses and larger cohorts. (C) 199
9 Academic Press.