Bfj. Manly et Ja. Schmutz, Estimation of brood and nest survival: Comparative methods in the presenceof heterogeneity, J WILDL MAN, 65(2), 2001, pp. 258-270
The Mayfield method has been widely used for estimating survival of nests a
nd young animals, especially when data are collected at irregular observati
on intervals. However, this method assumes survival is constant throughout
the study period, which often ignores biologically relevant variation and m
ay lead to biased survival estimates. We examined the bias and accuracy of
I modification to the Mayfield method;hat allows for temporal variation in
survival, and we developed and similarly tested 2 additional methods. One o
f these 2 new methods is simply an iterative extension of Klett and Johnson
's method, which we refer to as the Iterative Mayfield method and bears sim
ilarity to Kaplan-Meier methods. The other method uses maximum likelihood t
echniques for estimation and is best applied to survival of animals in grou
ps or families, rather than as independent individuals. We also examined ho
w robust these estimators are to heterogeneity in the data, which can arise
from such sources as dependent survival probabilities among siblings, inhe
rent differences among families, and adoption. Testing of estimator perform
ance with respect to bias, accuracy, and heterogeneity was done using simul
ations that mimicked a study of survival of emperor goose (Chen canagica) g
oslings. Assuming constant survival for inappropriately long periods of tim
e or use of Klett and Johnson's methods resulted in large bias or poor accu
racy (often >5% bias or root mean square error) compared to our Iterative M
ayfield or maximum likelihood methods. Overall, estimator performance was s
lightly better with our Iterative Mayfield than our maximum likelihood meth
od, but the maximum likelihood method provides a more rigorous framework fo
r testing covariates and explicitly models a heterogeneity factor. We demon
strated use of all estimators with data from emperor goose goslings. We adv
ocate that future studies use the new methods outlined here rather than the
traditional Mayfield method or its previous modifications.