Daniel is incorrect. Although VAR measures left-tail risk, the analytical method (also known as the variance-covariance or delta normal method) for estimating VAR requires the assumption of a normal distribution. This is because the analytical method utilizes the standard deviation of returns. For example, in calculating a daily VAR we calculate the standard deviation of daily returns in the past and assume it will be applicable to the future. Then using the asset’s expected one-day return and standard deviation, we estimate the one-day VAR at the desired level of significance. The assumption of normality is problematic because it is well documented that returns are not normally distributed in emerging markets.

Shrum is correct. Emerging market data often contain structural breaks (e.g., when liberalizations occur, the pattern of stock returns dramatically changes). If a country is expected to undergo a structural change in the future, then historical data are not very useful for prediction