We present a survival analysis of Soay sheep mark recapture and recovery da
ta. Unlike previous conditional analyses, it is not necessary to assume equ
ality of recovery and recapture probabilities; instead these are estimated
by maximum likelihood. Male and female sheep are treated separately, with t
he higher numbers and survival probabilities of the females resulting in a
more complex model than that used for the males. In both cases, however, ag
e and time aspects need to be included and there is a strong indication of
a reduction in survival for sheep aged 7 years or more. Time variation in s
urvival is related to the size of the population and selected weather varia
bles, by using logistic regression. The size of the population significantl
y affects the survival probabilities of male and female lambs, and of femal
e sheep aged 7 or more years. March rainfall and a measure of the North Atl
antic oscillation are found to influence survival significantly for all age
groups considered, for both males and females. Either of these weather var
iables can be used in a model. Several phenotypic and genotypic individual
covariates are also fitted. The only covariate which is found to influence
survival significantly is the type of horn of first-year female sheep. Ther
e is a substantial variation in the recovery probabilities over time, refle
cting in part the increased effort when a population crash was expected. Th
e goodness of fit of the model is checked by using graphical procedures.