[R-SIG-Finance] MonteCarloOption Questions

eqsf skobayashi at dci.com
Sat Dec 1 00:07:07 CET 2012


First of all, let me preface by saying that I have very little experience
with R but am trying to get up to speed as quickly as possible.

I have been trying to do a Monte Carlo simulation of barrier down and out
options with a rebate when the option is knocked out.  Essentially, trying
to do a very crude Merton-type structural model.  To get my feet wet, I was
experimenting with the MonteCarloOption function in the foptions package. 
As a source of comparison, I also ran the Black-Scholes option valuation
function, GBSOption.  I am using rnorm.Sobol for the innovation and a Wiener
process for the path.  The thing is, the B-S value is always very different
(2-10%) from the MC value for the exact same input assumptions even for
mcSteps=500k.

Also, I'd like to use a non-normal innovation but couldn't find a RNG for
that.  Looked at the students T RNG rt but the output of that function is
just a large data set, not an mcSteps x pathLength matrix.  Also took a look
at fExoticOptions but it doesn't look like you can do anything with the
non-normal distributions with those functions.

Does anyone else out there have experience working with the MonteCarloOption
or fExoticOptions functions?  Is there a more flexible set of functions I'm
missing?

Thanks in advance for any help.



--
View this message in context: http://r.789695.n4.nabble.com/MonteCarloOption-Questions-tp4651509.html
Sent from the Rmetrics mailing list archive at Nabble.com.



More information about the R-SIG-Finance mailing list