As noted earlier, RMark implements both the Seber and Brownie parameterizations of recovery models. However, RMark requires input for unique encounter histories in LDLD format, so to use RMark we must first convert the triangular array into LDLD format. The attached script reads from the MARK formatted data file for adult male and female American Black Ducks, and creates a data object that is compatible with RMark. It also creates and runs the "global" (time*sex) model in the Seber parameterization. Finally, the script exports the RMark results object for importing into the MARK GUI, which we will use in class on Thursday to discuss goodness of fit (please review the material here from my software class on goodness of fit in MARK). Using the black duck data, I compared the observed deviance from the global model S(time*sex) r(time*sex) of 80.87 to the simulation mean of 76.87 (95% CI 74.455 - 79.293). This suggests the need for a c-hat adjustment of 80.87/76.87 = 1.05, somewhat lower than the c-hat based on deviance /df computed by MARK (1.24).
In your review assignment you will use the converted RMark data object as a starting point to create a number of models in RMARK, summarize and produce model averaged survival estimates, and plot the estimate over time for males and females.