The scent-station survey method has been widely used to estimate trend
s in carnivore abundance. However, statistical properties of scent-sta
tion data are poorly understood, and the relation between scent-statio
n indices and carnivore abundance has not been adequately evaluated. W
e assessed properties of scent-station indices by analyzing data colle
cted in Minnesota during 1986-93. Visits to stations separated by <2 k
m were correlated for all species because individual carnivores someti
mes visited several stations in succession. Thus, visits to stations h
ad an intractable statistical distribution. Dichotomizing results for
lines of 10 stations (0 or greater than or equal to 1 visits) produced
binomially distributed data that were robust to multiple visits by in
dividuals. We abandoned 2-way comparisons among years in favor of test
s for population trend, which are less susceptible to bias, and analyz
ed results separately for biogeographic sections of Minnesota because
trends differed among sections. Before drawing inferences about carniv
ore population trends, we reevaluated published validation experiments
. Results implicated low statistical power and confounding as possible
explanations for equivocal or conflicting results of validation effor
ts. Long-term trends in visitation rates probably reflect real changes
in populations, but poor spatial and temporal resolution, susceptibil
ity to confounding, and low statistical power limit the usefulness of
this survey method.