Lower bounds to the accuracy of inference on heavy tails
- Submitting institution
-
Middlesex University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 927
- Type
- D - Journal article
- DOI
-
10.3150/13-BEJ512
- Title of journal
- Bernoulli
- Article number
- -
- First page
- 979
- Volume
- 20
- Issue
- 2
- ISSN
- 1350-7265
- Open access status
- Out of scope for open access requirements
- Month of publication
- February
- Year of publication
- 2014
- URL
-
http://eprints.mdx.ac.uk/18125/
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
0
- Research group(s)
-
-
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper suggests a novel method of deriving minimax lower bounds to the accuracy of statistical inference on non-parametric classes of distributions (in particular, heavy-tailed distributions). This research is significant because of the complexity of the considered problem, and its applications to extreme value theory. A lower bound can be used as a benchmark when choosing a particular estimator from a list of available estimators. This research provides important insights into the topics of non-parametric estimation and information retrieval.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -