- Thesis:
- Bachelor in Mathematics
- Author:
- Kai Becker
- Title:
- Der adaptive Lasso-Schätzer
- Supervisors:
- Stefan Richter (Universität Heidelberg)
- Jan JOHANNES
- Abstract:
- Since variabel selection by the lasso estimator is inconsistent under certain conditions, we introduce a weighted lasso estimator, called adaptive lasso estimator. In this approach adaptive wheights are introduced, to penalize the various coefficients in the l1 penalty term. Subsequently, we proof that the adaptive Lasso estimator satisfies the oracle properties. This implies that, firstly, it provides asymptotically optimal estimation, and, secondly, it maintains consistency in variable selection. Furthermore, we compare the estimation achieved using the adaptive lasso estimator with that of the Lasso estimator in several simulations.
References:- Hui Zou. The adaptive Lasso and its oracle properties, Journal of the American Statistical Association, 101(476):1418-1429, 2006.