Skip to content
Prev 7375 / 15274 Next

Defining an objective function in fPortfolio

Hello Felipe,

I am not an expert in fPortfolio, so I can't tell you with 100%
certainty if its working or not. I tried for a while and didn't get it
running with the portfolio package. Maximizing the return is more
complex than the min Variance program...

I have two suggestions:

1. Create efficient frontier (with lets say 1000 or 2000 points) and
then determine a portfolio on that frontier which is closest to your
target sigma. The function could be

portspec <- portfolioSpec()
setNFrontierPoints (portspec) <- 2000
portfolio <- portfolioFrontier(DATA,portspec,"LongOnly")

Remember that you don't want to end up in the lower branch... :-)

2. Solve it with a heuristic (e.g. DEoptim - see my last thread). But
I just started using it.

Lui


On Mon, Jan 24, 2011 at 10:52 PM, Luis Felipe Parra
<felipe.parra at quantil.com.co> wrote:
Message-ID: <AANLkTikfksJDpmh0qvhcj08F5JX9Q4fkV12JjXz2v+fn@mail.gmail.com>
In-Reply-To: <AANLkTikeua-fWUyq8CqKTf2Kiw3Mf13hTm3L2zgHns9S@mail.gmail.com>