I think you may be barking up the wrong tree. PCA is a method for obtaining orthogonalized vectors for replicating the original data to various degrees depending on the number of eigenvectors chosen. Not sure where the residuals come into the picture.

Looks like the USD 2-10 spread is finally going to invert, I wonder how are those people holding callable spread range accrual conditional upon a positive curve is feeling now!?

<t>QuoteOriginally posted by: bmYes, we do a few of these products. One variant is a callable spread accrual note. In note form the investor gets say a fixed rate that only accrues on days (months) where the defined spread is within a limit; for example the €15y swap rate minus the €2y swap rate is ...

In that case, would you also discourage the use of short-rate model for bermudan swaption?

<t>Kim, for the bermudan on a CMS-Libor swap, using a short-rate tree should also be possible and it should not be unuseably slow. Since there is no closed-form solution for the CMS rate on any node of the tree, it must be computed by pricing the swap on the sub-tree conditonal upon that node being ...

<r>Hi ajeetkc,Do not be dispair. The reason why no one can send you a calculator for Callable Range Accrual is partly because there are so many decisions one have to make to get the final value. LIBOR Market Model is a good framework but to get the most efficient implementation for a structure, ofte...

You may find the paper "Convexity Adjustments and Forward Libor Model Case of Constant Maturity Swaps" by Yinqiu Lu and Salih Neftci useful.

<t>Kr,I most definitely agree with you. The CDS market is still in it's infancy, anyone who wish to delta hedge a CDS option has gotta factor in an enormous hedging cost. For some ref entities, just crossing the spread will cost you an arm and a leg. I am constantly surprised when dealers found out ...

I have seen contracts on Asset Swap with termination feature, do you think an option on an asset swap is similar in nature to an option on a CDS?

SanFranCA2002,There ain't no closed-form solution for American swaptions.

<t>Right, agreed with Stochastix's comment, but does everyone agree with Monk's idea about convexity adjustment for OIS? To me, OIS is a fractal representation of a normal IRS. E.g. Normal 1M Libor Vs 1Year Fixed One year IRS, it does not require any convexity adjustment (for e.g. that suggested by ...

<t>Sorry, I do not understand. If the HW "tree" is constructed as a function of in-the-moneyness of the individually exercisable swaptions, wouldn't we have to build a tree for every deal we have? How would it be possible to perform a bankwide VaR for instance which includes all financial derivative...

Has anyone implemented BGM taking into account smile effect of the swaption market?

OIS is also traded in SGD and HKD. Liquid out to 1 year maturity.