Abstract
Asymptotic properties of the harmonic moment tail index Estimator are derived for distributions with regularly varying tails. The estimator shows good robustness properties and stands out for its simplicity. A tuning parameter allows for regulating the trade-off between robustness and efficiency. Small sample properties are illustrated by a simulation study.
| Original language | English |
|---|---|
| Pages (from-to) | 193-220 |
| Number of pages | 28 |
| Journal | Annals of the Institute of Statistical Mathematics |
| Volume | 66 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - Feb 2014 |
Fields of science
- 101018 Statistics
- 101029 Mathematical statistics
JKU Focus areas
- Computation in Informatics and Mathematics
Projects
- 1 Finished
-
Model selection
Duller, C. (Researcher) & Wagner, H. (PI)
01.01.2012 → 31.12.2025
Project: Other › Project from scientific scope of research unit
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver