New$10 Sign Up Bonus & $30 Free Trial Reward
Start challenge

Standard deviation

Also called SD, sigma

A statistic showing how widely values, such as daily returns, spread around their average. In trading it is the most common measure of volatility and the risk input of the Sharpe ratio.

Reading
2 min
Sources
4BookProfessional bodyResearch
Updated
On this page· 5 sections
  1. How it works
  2. Example
  3. Watch out
  4. Sources
  5. Related terms

Two price series can share the same average daily return and still look nothing alike: one drifts, the other lurches. Standard deviation is the number that tells them apart. It measures how far values tend to sit from their mean, in the same units as the data[4].

In finance it does double duty. Since Harry Markowitz’s work on portfolios, standard deviation, the square root of variance, has been the predominant measure of risk[2]. It is also the denominator of the Sharpe ratio[3].

How it works

For a set of data, take each value’s distance from the mean, square it, add the squares, divide and take the square root. A sample divides by n − 1, one less than the number of values; a whole population divides by N[4]. For a probability distribution, each squared deviation is first multiplied by its probability[1].

The result is never negative. When it is zero, there is no spread at all[4].

Two rules turn it into a range. For bell-shaped, symmetric data, about 68% of values lie within one standard deviation of the mean, about 95% within two and more than 99% within three[4]. For any data at all, at least 75% lie within two[4].

Time stretches it. When one-period returns are summed over T periods and have zero serial correlation, the standard deviation grows with the square root of T[3].

Example

Say five daily returns are +1.0%, −0.5%, +0.8%, −1.2% and +0.4%.

  1. Mean: 0.5% ÷ 5 = 0.1%.
  2. Deviations from the mean: +0.9, −0.6, +0.7, −1.3 and +0.3 points.
  3. Squares: 0.81, 0.36, 0.49, 1.69 and 0.09, adding up to 3.44.
  4. As a sample: 3.44 ÷ 4 = 0.86, and √0.86 ≈ 0.93%.
  5. As a population: 3.44 ÷ 5 = 0.688, and √0.688 ≈ 0.83%.

With five values, the two methods differ by about 0.1 percentage point. Sharpe notes that when every fund is measured over the same number of periods, the version dividing by T gives the same ranking[3].

Watch out

Upside counts as much as downside. Standard deviation assumes a symmetric distribution and penalizes upside and downside deviations equally[2].

A calm record can understate the risk. Kidd’s CFA Institute article recounts that the Japanese equity market had ten years of only positive annual returns from 1980 to 1989, then fell 39% in 1990, a loss its small sample of negative monthly returns would not have predicted[2].

The 68–95 rule needs the bell shape. Without it, only the weaker bound holds: at least 75% within two standard deviations[4].

Sources

  1. BookOpenStax (Rice University)4.2 Mean or Expected Value and Standard Deviation (Introductory Statistics, Illowsky & Dean)Checked November 9, 2026
  2. Professional bodyCFA InstituteThe Sortino Ratio: Is Downside Risk the Only Risk that Matters? (Deborah Kidd, CFA, Investment Performance Measurement, 2012)Checked November 9, 2026
  3. ResearchStanford University (William F. Sharpe)The Sharpe Ratio (William F. Sharpe, The Journal of Portfolio Management, Fall 1994; author's copy)Checked November 9, 2026
  4. BookOpenStax (Rice University)2.7 Measures of the Spread of the Data (Introductory Statistics, Illowsky & Dean)Checked November 9, 2026
All terms in Tronexopedia

Your challenge starts here

Start your challengeFree TrialNew
Registration bonus

Get $10 free in your Wallet when you sign up

Register and use your $10 Wallet credit to reduce the price of your first challenge.

The $10 bonus is credited to your personal Wallet and can only be used to reduce the price of a challenge purchase. Credits cannot be withdrawn or used for payouts.

Start now & get $10