PathPricer and Likelihood ratio

[Lapin]

Hi,

I would like to add some likelihood ratio method to my MC pricer.
This should be done by calculating a weight for each path.
I have the following questions and I am looking for guidance:

1- for each path I need the first random number used to calculate the path. How can I retrieve it in the path pricer? As far as I know, we can retrieve the value of the underlying at each point but not the random variable.

2- the pathpricer class returns a real which is the value of the path. I need in this case to use this value for each path and to weigths it with my likelihood ratio. Then I need to sum them up and then take the mean to get my greek. Where should I put the code for it? Any recommendation? Would it be better to put it directly in the McSimulation class, extending this class to support likelihood ratio?


Cheers

[Luigi Ballabio]

Hi,
        apologies for the delay---I was working to make sure Santa could bring
you QuantLib 0.9.0...

On Fri, 2007-11-30 at 10:13 -0800, Yomi wrote:
> I would like to add some likelihood ratio method to my MC pricer.
> This should be done by calculating a weight for each path.
> I have the following questions and I am looking for guidance:

I'm not much familiar with likelihood ratio, so I don't know if this is
possible in your case, but you might try and calculate the weight in a
custom-written path generator instead. It would have access to the
underlying random numbers, and could return the likelihood ratio as the
weight of the returned Sample<Path>. Do you think this could be
arranged?

Later,
        Luigi


--

feature, n:
A surprising property of a program. Occasionally documented.
To call a property a feature sometimes means the author did not
consider that case, and the program makes an unexpected, though
not necessarily wrong response. See BUG. "That's not a bug,
it's a feature!" A bug can be changed to a feature by
documenting it.



-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2005.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/
_______________________________________________
QuantLib-users mailing list
[hidden email]
https://lists.sourceforge.net/lists/listinfo/quantlib-users