Abstract
Estimation of the population size n from k i.i.d. binomial observations with unknown success probability p is relevant to a multitude of applications and has a long history. Without additional prior information this is a notoriously difficult task when p becomes small, and the Bayesian approach becomes particularly useful. For a large class of priors, we establish posterior contraction and a Bernstein-von Mises type theorem in a setting where and as . Furthermore, we suggest a new class of Bayesian estimators for n and provide a comprehensive simulation study in which we investigate their performance. To showcase the advantages of a Bayesian approach on real data, we also benchmark our estimators in a novel application from super-resolution microscopy.
Funding Statement
A.M. and T.S. acknowledge support and funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy EXC 2067/1-390729940, DFG CRC 755 (A6), and DFG RTN 2088. L.F.S. was funded by DFG RTG 2088 (B4) and J.S.H. was supported by a TOP II grant from the NWO.
Acknowledgements
We would like to thank the reviewers and are particularly grateful to one referee for a detailed report with additional insights and hints to the literature. These comments have lead to a substantial improvement of the article.
We also thank Alexander Egner and Oskar Laitenberger for providing us with data recorded at the Institute for Nanophotonics Göttingen e.V.
J. Schmidt-Hieber, L. F. Schneider and T. Staudt have contributed equally to this work
Funding Statement
A.M. and T.S. acknowledge support and funding by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy EXC 2067/1-390729940, DFG CRC 755 (A6), and DFG RTN 2088. L.F.S. was funded by DFG RTG 2088 (B4) and J.S.H. was supported by a TOP II grant from the NWO.
Acknowledgements
We would like to thank the reviewers and are particularly grateful to one referee for a detailed report with additional insights and hints to the literature. These comments have lead to a substantial improvement of the article.
We also thank Alexander Egner and Oskar Laitenberger for providing us with data recorded at the Institute for Nanophotonics Göttingen e.V.
J. Schmidt-Hieber, L. F. Schneider and T. Staudt have contributed equally to this work
Citation
Johannes Schmidt-Hieber. Laura Fee Schneider. Thomas Staudt. Andrea Krajina. Timo Aspelmeier. Axel Munk. "Posterior analysis of n in the binomial problem with both parameters unknown—with applications to quantitative nanoscopy." Ann. Statist. 49 (6) 3534 - 3558, December 2021. https://doi.org/10.1214/21-AOS2096
Information