Back to search
University of Washington
Tuning parameter selection for a penalized maximum likelihood estimator of species richness
Abstract
dc:description.abstractOur goal is estimating the true number of classes in a population. We focus on the scenario where multiple frequency count tables have been collected from the same population. In this setting we demonstrate the efficacy of a previously published penalized maximum likelihood method. Four novel methods to tune the requisite penalization parameter are proposed. The performance of all proposed tuning methods is compared in simulations.
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Paynter, Alexander Caldwell
- Advisor dc:contributor.advisor
-
- Willis, Amy D
Subjects
dc:subject × 5Rights
dc:rights- Statement dc:rights
-
- CC BY-NC-SA
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/1773/44064