A new selection criterion for statistical home range estimation

The home range of an animal describes the geographic area where this individual spends most of the time while doing its usual activities. From a statistical viewpoint, the problem of home range estimation can be considered as a set estimation one. In the ecological literature, there are a variety of home range estimators. We address the open question of choosing the ‘best’ home range from a collection of them constructed on the same sample. We introduce the penalized overestimation ratio, a numerical index to rank the estimated home ranges. The key idea is to balance the excess area covered by the estimator (with respect to the sample) and a shape descriptor measuring the over-adjustment of the home range to the data. To our knowledge, apart from computing the home range area, our ranking procedure is the first one both applicable to real data and to any type of home range estimator. Further, optimization of the selection index provides a way to select the tuning parameters of nonparametric home ranges. For illustration purposes, we apply our selection proposal to a dataset of a Mongolian wolf and we carry out a simulation study.