High dimensional estimator of the maximum Sharpe ratio with and without short sales
A cross-validated weighted estimator is proposed for the population maximum Sharpe ratio with and without short sales. The estimator is an optimal linear combination of a factor analysis-based estimator and a linear shrinkage estimator, which is expected to remain competitive in various covariance s...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/140169 |
| Summary: | A cross-validated weighted estimator is proposed for the population maximum Sharpe ratio with and without short sales. The estimator is an optimal linear combination of a factor analysis-based estimator and a linear shrinkage estimator, which is expected to remain competitive in various covariance structures. Simulation results imply that the weighted estimator outperforms at least one of its constituting estimators under certain covariance structure and the difference is significant, especially when the dimension is large or close to the sample size. |
|---|