For the past 8 years I have been working, with Judy Zeh, as a member of the International Whaling Commission Scientific Committee on bowhead whale, Balaena mysticetus, population size and population dynamics.
Population size estimation is difficult because the annual ice-based visual and acoustic census at Point Barrow, Alaska misses many whales, and because it is impossible to know for sure whether several observations correspond to several whales or to a single one. We developed a stochastic model that incorporates the main uncertainties, and has a hierarchical structure. The resulting method is called the Bayes empirical Bayes estimation method.
Population dynamics are also hard to study because most of the whales' life history (births, deaths, sexual maturity) is not observed directly and there are great uncertainties. The IWC uses a deterministic population dynamics model to set quotas and determine protection levels, and we have been working with Geof Givens on ways to take account of uncertainties about the inputs and outputs to this model. The result is called the Bayesian synthesis method.
Adrian E. Raftery, Geof H. Givens and Judith E. Zeh (1995). Inference from a deterministic population dynamics model for bowhead whales (with Discussion). Journal of the American Statistical Association, 90:402-430.
Click here to return to Adrian Raftery's home page.
Click here to return to the Statistics Dept. home page.
Click here to return to the University of Washington home page.