Partially-Adaptive Robust Estimators of Locations via Exponential Embedding,
WISCONSIN UNIV-MADISON DEPT OF MATHEMATICS
Pagination or Media Count:
A general method is presented for constructing a location estimator which is asymptotically efficient at any two different location-scale families of symmetric distributions as well as at an appropriately defined class of distributions lying in between. The method works by embedding the two families in a comprehensive parametric model and identifying the estimator with the MLE. The case when the families are Normal and Double exponential is examined in detail. Additional keywords maximum likelihood estimation, equations, asymptotic normality, embedding, sensitivity curve, reprints.
- Numerical Mathematics