The Christmas Bird Count (CBC) is a valuable source of information about mi
dwinter populations of birds in the continental U.S. and Canada. Analysis o
f CBC data is complicated by substantial variation among sites and years in
effort expended in counting; this feature of the CBC is common to many oth
er wildlife surveys. Specification of a method for adjusting counts for eff
ort is a matter of some controversy. Here, we present models for longitudin
al count surveys with varying effort; these describe the effect of effort a
s proportional to exp(B effort(P)), where B and p are parameters. For any f
ixed p, our models are loglinear in the transformed explanatory variable (e
ffort)(P) and other covariables. Hence, we fit a collection of loglinear mo
dels corresponding to a range of values of p and select the best effort adj
ustment from among these on the basis of fit statistics. We apply this proc
edure to data for six bird species in five regions, for the period 1959-198
8.