How Portfolio History Affects Value at Risk
Summary
The document explains that whether past positions affect a value-at-risk estimate depends on the calculation method. A historical portfolio-return approach can use the portfolio composition held at each point in the selected history, so position changes are reflected in those past returns. A calculation that applies past market changes to today’s holdings instead measures risk for the current portfolio alone.
The answer describes the common scenario-based process: establish a portfolio and market starting point, apply market shocks, revalue the portfolio, and summarize the resulting profit-and-loss distribution with VaR or a related measure. Portfolio changes during the risk horizon can also be modeled as management actions, but the response says this is often omitted between routine rebalancing dates. The discussion is conceptual and does not prescribe a specific historical window, shock model, or implementation; those choices determine which portfolio history enters the estimate.
Key ideas
- VaR estimates risk from portfolio value changes under a chosen set of market moves or scenarios.
- Historical portfolio returns can reflect positions held at each point in the selected history.
- Applying historical shocks to current holdings measures the risk of today’s portfolio.
- Portfolio changes during the risk horizon can be modeled, but are often excluded between rebalances.
Tags
Full text
# Does VaR calculations consider my portfolio past # Does VaR calculations consider my portfolio past I am relatively new to trading and decided to become more quantitative about it. I have had a portfolio for about two years, where I changed my positions several times. I now learnt about VaR calculation and was wondering does it take into account my past positions or only my positions of today? Thank you ## Answer by Kermittfrog (score 2, accepted) https://quant.stackexchange.com/a/69418 In (value at) risk calculations, we are commonly interested in the risk of changes of the value of our portfolio that are induced by external factors, i.e. thru changes in market prices. To that end, we usually - fix the invested asset universe and the market environment (e.g. rates / prices / vols) at the onset of our risk calculation and compute a base portfolio value. - We apply a number of shocks, or scenarios, to the market environment and reprice our portfolio using a valuation model. The source of these shocks could be randomness or historically observed shifts or whatever we like. - We might want to consider the change in calendar time as well by rolling our portfolio forward by the calendar length of the market shift, e.g. 1D, 5D or 1M. - Given a sufficient number of repetitions of 2/3, we deduct the simulated prices from the initial price to get a profit-and-loss (PnL) distribution. - We compute some statistic from the PnL-distribution such as VaR, Expected Shortfall or the like. We may consider shifts in portfolio composition as well. This is usually called management intervention (at least in banks where I worked) and there you could model hypothetical actions. But most of the time, we do not do that as we are simulating the change in portfolio value between points in time where we rebalance our portfolios, e.g. daily or once a week or so. HTH? ## Answer by D Stanley (score 0) https://quant.stackexchange.com/a/69375 It depends on how you're calculating VaR. If you're looking at your total portfolio's returns over recent history, then it's taking the portfolio at that time into account. If you're looking at the history of just the current positions, then that's only looking at the current positions. Other forward-looking methods like monte-carlo would just look at the current positions as well.
Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.