Use of generalized linear models for estimating nest survival
Estimating nest success and evaluating factors potentially related to the survival rates of nests are key aspects of many studies of avian populations. A strong interest in nest success has led to a rich literature detailing a variety of estimation methods for this vital rate. In recent years, modeling approaches have undergone especially rapid development. Despite these advances, most researchers still employ Mayfield’s ad-hoc method (Mayfield 1961) or, in some cases, the maximum-likelihood estimator of Johnson (1979) and Bart and Robson (1982). Such methods permit analyses of stratified data but do not allow for more complex and realistic models of nest survival rate that include covariates that vary by individual, nest age, time, etc. and that may be continuous or categorical. Methods that allow researchers to rigorously assess the importance of a variety of biological factors that might affect nest survival rates can now be readily implemented in Program MARK and in SAS’s Proc GENMOD and Proc NLMIXED. To facilitate use of these methods, the following resources are provided.
- Studies in Avian Biology 34 - A special issue on Nest Survival Data Analyses
- Rotella, J.J. 2007. Modeling nest-survival data: recent improvements and future directions. Studies in Avian Biology 34:145-148.
- Rotella, J.J., M.L. Taper, S.E. Stephens, M.S. Lindberg. 2007. Extending methods for modeling heterogeneity in nest-survival data using generalized mixed models. Studies in Avian Biology 34:34-44.
- Appendix 1 - SAS code for fixed- and mixed-effects models
- Appendix 2 - SAS code for Monte Carlo simulations
- Sturdivant, R.X., J.J. Rotella, R.E. Russell. 2007. A smoothed residual based goodness-of-fit statistic for nest-survival models. Studies in Avian Biology 34.
- Appendix 1 - SAS code for Goodness-of-fit tests of mixed models of nest-survival data
- SAS code for Goodness-of-fit tests of fixed-effects-only models of nest-survival data (not presented in the paper but shown here for mallard example)
- Studies in Avian Biology 34 - Literature Cited.
- Rotella, J.J., S. J. Dinsmore, T.L. Shaffer. 2004. Modeling nest-survival data: a comparison of recently developed methods that can be implemented in MARK and SAS. Animal Biodiversity and Conservation 27:187-204.
SAS code – tools for analyzing nest-survival data in SAS & MARK as used in the manuscript’s tables
- Mallard dataset in SAS format
- SAS code for converting a dataset from SAS input format to Program MARK’s input format
- SAS code for converting a dataset from Program MARK’s input format to SAS input format
- Proc NLMIXED code for single fixed-effect model - simple example for running 1 model
- Proc NLMIXED code for fixed-effects models – example for Mallard nests with AICc Table
- Proc NLMIXED code for mixed models (includes Observer-Effects term) – example for Mallard nests with AICc Table
- Proc GENMOD code for analyzing fixed-effects models – example for Mallard nests.
- SAS code for simulating and analyzing nest-survival data with Proc NLMIXED