 
Summary: Note: This is the final version with some errata corrections to Table 2. Figures and Tables are
at the end, not inserted at nearest point of reference.
A. Neil Arnason
arnason@cs.umanitoba.ca
ESTIMATING CLOSED POPULATION SIZE AND NUMBER OF
MARKED ANIMALS FROM SIGHTING DATA
A. NEIL ARNASON, Department of Computer Science, University of Manitoba, Winnipeg, MB
R3T 2N2, Canada
CARL J. SCHWARZ, Department of Statistics, University of Manitoba, Winnipeg, MB
R3T 2N2, Canada
JON M. GERRARD, Manitoba Institute of Cell Biology, 100 Olivia Street, Winnipeg, MB
R3E 0V9, Canada
Abstract: We describe a new estimator of population size that can be formed when independent
sightings are made of marked and unmarked animals in a closed population where a subset of the
population is individually marked. Each marked animal must bear a unique mark but the number
of marked animals alive in the population is unknown. The estimate can be used when no
recaptures or removals of animals are possible during the experiment. An example is estimating
the number of immature bald eagles (Haliaeetus leucocephalus) on a lake some years after
banding of nestlings. We derive the maximum likelihood estimates for population size and
number of marks, and we show how to develop confidence intervals and perform goodnessoffit
