 # Negative skewness = VAR biased downward?

Maybe im just fried, but wouldn’t having a larger proportion of negative returns increase VAR and overstate, rather than understate it? I get that there would be less variability on the upside, but you still have more frequent negative returns.

This is Q 34 in the schweser live mock.

I thought the same thing, so it isnt just you

i thought most of the PM questions were garbage

I had to look at a graph but check out:

http://en.wikipedia.org/wiki/Skewness

Quoted:

1. negative skew: The left tail is longer; the mass of the distribution is concentrated on the right of the figure. It has relatively few low values. The distribution is said to be left-skewed, left-tailed, or skewed to the left. Example (observations): 1,1001,1002,1003

My memory of negative skew was the exact opposite of what it really is. When you look at the graph you were likely think (like I was) that negative skew has more negative values, it actually has less.

No. VAR assumes a normal distribution–same amount of returns above and below the mean. If your returns are negatively skewed, then you have more negative than positive returns. But VAR is assuming a normal distributions. So your VAR–i.e. your \$ loss #–is understated. In other words, VAR is giving you too small of a loss # because it assumes normal distribution, which is a “more conservative” assumption.

the show ny is correct