Monte Carlo Var on corporate bonds

Discussion on Value-at-Risk Models
Forum rules
DISCLAIMER: We do not warrant or represent that this forum or its content is free of viruses, worms or other code that might be contaminating or destructive. We cannot guarantee that documents or files downloaded from the Site will be free from viruses and we do not accept any responsibility for any damage or loss caused by any virus. Accordingly, for your own protection, you must use virus-checking software when using the forum. You must not post or provide to us via the forum, any document or file which you believe may contain a virus. You must virus check any document or file which you intend to post or provide to us via the forum. You must ensure that any document or file you intend to post to the forum does not contravene any applicable laws or contravene any person's legal rights. We do not accept any responsibility for any damage or loss you may suffer.
Simon Vasco
Posts: 1
Joined: Tue Jun 11, 2013 9:09 am

Monte Carlo Var on corporate bonds

Postby Simon Vasco » Tue Jun 11, 2013 1:26 pm

Hi Carol,

I wanted to run a Monte Carlo Var on a portfolio of corporate bonds but was unclear as to the standard practice for deriving volatility and correlation numbers - i.e. what historical data does one use to calculate the volatility and correlation that are inputs to the Monte Carlo model. I can think of 3 ways to proceed but none of them seem entirely satisfactory. I wondered what your preferred route was?

1) Although one could use historical single name bond data (with some sort of duration adjustment) this would present a problem for recently issued bonds with little data.

2) Using single name CDS data (where available) would mean there was sufficient data but one would not easily be able to capture the cds-bond basis effect in the model (which can be significant).

3) Using generic proxies (e.g. a bond index) and adjusting as necessary for spread and duration. This would be fairly straightforward to implement but would tend to miss idiosyncratic behaviour and would not capture the basis effect for very high spread names.

thanks,
Simon Vasco

Return to “Volume IV”

Who is online

Users browsing this forum: Baidu [Spider] and 2 guests