- Abstract:
-
Bayesian or likelihood-based approaches to data analysis became very popular in the field of Machine Learning. However, there exist theoretical results which question the general applicability of such approaches; among those a result by Robins and Ritov which introduce a specific example for which they prove that a likelihood-based estimator will fail (i.e.~it does for certain cases not converge to a true parameter estimate, even given infinite data). In this paper we consider various approaches to formulate likelihood-based estimators in this example, basically by considering various extensions of the presumed generative model of the data. We can derive estimators which are very similar to the classical Horvitz- Thompson and which also account for a priori knowledge of an observation probability function.
- Links To Paper
- 1st Link
- Bibtex format
- @Misc{EDI-INF-RR-1189,
- author = {
Stefan Harmeling
and Marc Toussaint
},
- title = {Bayesian Estimators for Robins-Ritov's Problem},
- year = 2007,
- url = {http://homepages.inf.ed.ac.uk/sharmeli/pubs/techreport2007.pdf},
- }
|