5.20 We have already seen that the annual survival rates of wild animals may be estimated by means of ring-recovery experiments, resulting in data of the kind displayed in Table 1.5, and using models such as that of Exercise 5.8.

An alternative approach is to make observations of previously marked live animals resulting in capture-recapture experiments. In some cases capturerecapture and ring-recovery data may be combined; see, e.g., Lebreton et al.

(1995), Catchpole et al. (1998a), and Example 6.4. In the classical CormackJolly-Seber model for capture-recapture data, the probabilities of annual survival are allowed to vary from year to year, but do not depend on the age of the animal. The probability that a live marked animal is captured in any year is also allowed to vary from year to year. Write down the probability that an animal captured and marked in year i is next seen alive in year j. Explain why this model is parameter-redundant, and suggest how to proceed.