Timeline for Help on minimum variance optimization on U.S. Equity/Bond ETFs - Intuition
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Mar 22, 2017 at 7:39 | comment | added | Enrico Schumann | The global minimum-variance portfolio is the 'almost-unconstrained' minimum-variance portfolio, i.e. minimise variance subject only to the budget constraint. In particular, short sales are allowed. So simply leave out the long-only constraints; easiest may be to use MATLAB's quadprog directly and leave out the constraints. (If you need to specify lower bounds, choose extreme ones, such as -1000%.) If you have a frontier as in your example, simply choose the leftmost point (i.e. column). | |
| Mar 21, 2017 at 19:41 | comment | added | whartonone | If anyone knows how to pull the "global minimum variance" portfolio weights from the MATLAB "Portfolio" object, that would be helpful. | |
| Mar 21, 2017 at 19:41 | comment | added | whartonone | You're right - it's 10 points on the efficient frontier. | |
| Mar 21, 2017 at 17:20 | vote | accept | whartonone | ||
| Mar 23, 2017 at 18:18 | |||||
| Mar 21, 2017 at 7:57 | history | answered | Enrico Schumann | CC BY-SA 3.0 |