Anyone can spend five minutes with the iQ Portfolio Optimizer and walk away with something that looks great on paper. But the real work lies in understanding how that portfolio is likely to behave over time - based (of course) on history.
You need to clearly communicate an portfolio’s “personality” so clients know what to expect—through bull markets and bear. A key part of that story is volatility risk, typically measured by standard deviation. But standard deviation doesn’t tell the whole story. To really understand volatility, you also need skew and kurtosis. They show how returns behave in extreme markets—not just how much they move, but in which direction (and how often).
Why Skew and Kurtosis Add Meaning to Standard Deviation
As an investment advisor, you should be extremely familiar with standard deviation—the go-to measure of volatility. But sometimes, standard deviation alone doesn’t tell the whole story. That’s where skew and kurtosis come in. These two statistics, included in iQUANT factcards and the iQ Optimizer PDF printout, help advisors better understand how returns behave, especially in extreme market conditions.
Understanding Skew: The Balance of a Bell Curve
Skew is like a seesaw. When it’s level, returns are balanced on both sides—this is called zero skew. But if one side dips, it means the returns lean more to one side than the other.
Positive skew means more frequent small losses and fewer large gains.
Negative skew flips that—more small gains, but a higher chance of big losses.
In investing, skew helps advisors see which side the “tail risk” is on. Two investments might have the same standard deviation, but if one has a negative skew, it carries more downside risk—something not visible in standard deviation alone.
Kurtosis: The Weight of the Tails
Now imagine you’re watching two different weather forecasts. Both say the average temperature is 70°F with a 10° swing. But one includes freak 100°F days once a month. That’s kurtosis.
High kurtosis means more data in the tails—more surprises.
Low kurtosis suggests most returns stay close to the average.
In portfolio terms, high kurtosis signals a higher chance of rare but extreme returns. Standard deviation treats all variability equally, but kurtosis focuses on how often those big shocks actually happen.
Bringing It All Together
Standard deviation is like knowing how much temperatures usually swing. Skew tells you whether the wild days tend to be extra hot or cold. Kurtosis tells you how often they get truly extreme.
Let’s say you're comparing two ETFs with identical standard deviations. ETF A has negative skew and high kurtosis. ETF B has near-zero skew and low kurtosis. On paper, they look equally volatile. But ETF A hides a greater chance of rare, steep losses—exactly the kind of tail risk you'd want to flag in a conservative portfolio. In that case, ETF B may be the better choice for clients focused on controlling volatility.
Using skew and kurtosis alongside standard deviation gives advisors a clearer, fuller picture of risk. These stats are built right into the iQUANT factcards and the Optimizer PDF printout, so they’re easy to reference during planning and portfolio building.
Of course, when assessing the overall risk of a model, a 40 Act product, or a total portfolio, advisors should also consider capture ratios, up and down market betas, and up/down market correlations. While not a replacement for full risk analysis, skew, kurtosis, and standard deviation work beautifully together for evaluating volatility risk.
What’s the difference between beta and correlation? You need to know this! We’ll address it in next week’s blog.