• C++ Programming for Financial Engineering
    Highly recommended by thousands of MFE students. Covers essential C++ topics with applications to financial engineering. Learn more Join!
    Python for Finance with Intro to Data Science
    Gain practical understanding of Python to read, understand, and write professional Python code for your first day on the job. Learn more Join!
    An Intuition-Based Options Primer for FE
    Ideal for entry level positions interviews and graduate studies, specializing in options trading arbitrage and options valuation models. Learn more Join!

Value At Risk When price data is not complete

Joined
11/16/11
Messages
8
Points
11
Dear all,

I now encounter a problem for calculating VaR for a portfolio consisting of FX, ETFs, Futures and Bonds.

Since the assets in the the portfolio are constantly changing, I only have the price data for each asset during the time when they are in the portfolio.

For example, for a futures contract A, we opened a long position in A on 7 Sept 2013 and closed the position in 7 Oct 2013. And now, on 5 Dec 2014, we long A again (that means we need to consider A now when calculating VaR). The price data for A only consists the prices between 7 Sept 2013 and 7 Oct 2013.

It is seemingly impossible for me to construct the covariance matrix for the porfolio. What should I do to estimate the Value at risk then???
 
Where are you getting your FX, ETF, Futures, and Bonds data from? What is the time frame?
 
Where are you getting your FX, ETF, Futures, and Bonds data from? What is the time frame?
All the securtieis' price data are retrieved from Bloomberg.

I am using python to do this calculation. We need to calculate the VaR based on past 2 year's price history.

However, the data was initially for calculating PnL for the portfolio. Therefore, only when the security is in our portfolio, the price data will be recorded.

Thanks!
 
All the securtieis' price data are retrieved from Bloomberg.

I am using python to do this calculation. We need to calculate the VaR based on past 2 year's price history.

However, the data was initially for calculating PnL for the portfolio. Therefore, only when the security is in our portfolio, the price data will be recorded.

Thanks!

Well, then you will simply have to download the needed data manually and save in the appropriate directory.
 
For futures though you might need sort of a rolling time series. For instance, for FX futures there is not going to be 2 years of (liquid) trading data. I think in Bloomberg you could download BP1 Curncy which is a rolling closest to expiration (hence the one) expiration BP future. There are defaults in Bloomberg for how to handle price adjustments.
 
Back
Top