[R-sig-Finance] Fwd: Testing technical indicators

[BBands]

On 5/31/06, Jonathan Patton <pattonjava at yahoo.com> wrote:
> I am a programmer and have downloaded and installed R
> and the fExtremes package. I am trying to test various
> ideas that I have about the stock market. I've looked
> through the function reference inside rMetrics and
> there looks to be a lot of useful functions there. I'm
> having trouble though finding examples similar to what
> I would like to do.
>
> Initially, I would like to test a 5 and 10 day moving
> average crossover system to see if there is any
> correlation between the 5 day moving average crossing
> the 10 day moving average. I'm just looking for some
> general direction to get started. I would like to know
> if this type of analysis is possible to begin with and
> then go from there. R looks great and very powerful.
> I've written a small program in vb to do some of this
> but was getting stuck when it came to backtesting.

The solution we use is to create the indicators and systems in Python,
pass the results of the test(s) to R for evaluation via Rpy. This has
proved to be a very robust approach that combines the strengths of
each package into a superior solution. We use gnuplot for 3D system
parameter graphics via gnuplot-py, but these days I gather that can be
done nicely in R as well.

     jab
--
John Bollinger, CFA, CMT
www.BollingerBands.com

If you advance far enough, you arrive at the beginning.