CSS Analytics tiene un post introductorio sobre Value at Risk,
A technique used to estimate the probability of portfolio losses based on the statistical analysis of historical price trends and volatilities.
El foco del articulo es de que tamaño tiene que ser una posición en el mercado. Lo más interesante es, que luego de la critica clásica de que las colas de la distribución de los retornos son más gruesas, propone el siguiente enfoque
Why not simply look at the empirical distribution of daily returns? After all, our own empirical observation tells us that normal distributions are flawed, so why not manage risk based on experience?
In this method we will use an incredibly simple approach:
1) take the daily returns for a given stock, index or strategy
2) compute the 5th percentile of returns (max tail loss)
3) select a budgeted risk level as a maximum daily loss such as 1% (conservative) or 1.5% (aggressive)
4) your position size is the budgeted risk level divided by the absolute value of the max tail loss
5) this position may not exceed 200%
Por ultimo, les dejo la bibliografia que use en un curso de VaR:
Jorion, Philippe. Value at Risk: A New Benchmark for Measuring Financial Risk
Holton, Glyn, Value at Risk, Theory and Practice
RiskMetrics Technical Document. (http://www.riskmetrics.com/publications/techdocs/rmcovv.html)
