meta user
network profile
| bio | website | |
|---|---|---|
| location | ||
| age | ||
| visits | member for | 2 years, 3 months |
| seen | Sep 4 '12 at 16:28 | |
| stats | profile views | 56 |
|
Sep 4 |
comment |
ROC: difference between discrete and continuous? PerformanceAnalytics can use either discrete or log returns. It can also perform simple or geometric chaining. These two things are easily confused. If you have log returns, you almost certainly want to use simple chaining. If you have discrete (often called simple) returns, you may want either geometric chaining or simple chaining, depending on your input data and the analysis that you want to do. |
|
Jun 22 |
comment |
How does Cornish-Fisher VaR (aka modified VaR) scale with time? Something like the alpha-weighting of VaR described for VaR derived from extreme value theory described in Tsay could be derived for the Cornish Fisher Distribution. As another alternative, square root of time sigma scaling will get most of the structure, unless the series is highly skewed or kurtotic. I don't think there is a precise or complete answer in the literature for this, and I haven't done the work to develop a precise answer. |
|
Jun 21 |
awarded | Editor |
|
Jun 21 |
revised |
How does Cornish-Fisher VaR (aka modified VaR) scale with time? add another link, fix grammar error |
|
Jun 21 |
answered | How does Cornish-Fisher VaR (aka modified VaR) scale with time? |
|
Feb 20 |
awarded | Yearling |
|
Oct 23 |
awarded | Critic |
|
Sep 23 |
comment |
How to compute modified-CVaR in the PerformanceAnalytics package? I want to second the advice to pre-calculate the moment matrices before doing optimization. The PortfolioAnalytics package always does this to minimize recalculating things that only need to be done once. You can also do things like cleaning the raw data, Ledoit-Wolf shrinkage on the estimates, etc before applying your optimization criteria. |
|
Aug 5 |
comment |
robust portfolio optimization re-balancing with transaction costs All the components of the objective are arbitrary R functions. The package takes care of the 'wrapper' around all of that, basic box constraints and full investment constraint, dealing with the optimization engines, etc. The objective is layered (and separately multiplied/penalized) by each arbitrary function you define. There was a discussion on R-SIG-Finance this week here showing a custom objective that isn't in the 'standard' model of using returns the way a modified Markowitz approach does. |
|
Aug 2 |
answered | How do I backtest a convertible bond arbitrage strategy in R/Matlab? |
|
Jul 27 |
awarded | Supporter |
|
Jul 27 |
answered | robust portfolio optimization re-balancing with transaction costs |
|
Jul 27 |
awarded | Teacher |
|
Jul 27 |
answered | Use Trades as Input for PerformanceAnalytics |
