1 Sigma
This formula tells you how much of your data falls close to the average when your results follow a normal distribution β the familiar bell-shaped curve where most values cluster in the middle and fewer values spread out to the edges. First, let's define two terms. The "mean" is simply the average of all your data points. The "standard deviation" (the symbol Ο, called sigma) is a measure of how spread out your data is β a small standard deviation means values are packed tightly around the average, while a large one means they're widely scattered.
The 1 Sigma rule says that about 68.26% of all your data will fall within one standard deviation on either side of the mean β that is, between (mean minus one Ο) and (mean plus one Ο). You don't calculate this percentage yourself; it is a fixed, known property of any normal distribution. You simply use it to understand roughly two-thirds of your outcomes.
As a project manager, you'll meet sigma when working with quality control and estimating. A high concentration of data within 1Ο tells you results are consistent and predictable. If you find lots of results falling far outside 1Ο, your process has a lot of variation and may need attention. Reading it is straightforward: 1Ο covers the most typical, middle-of-the-road outcomes.
Think of it like the crowd at the center of a music festival. The vast majority of people β about two-thirds β are packed near the main stage (the mean). A smaller number wander out toward the edges. 1Ο captures that dense central crowd where most of the action is.
Imagine your team takes an average of 10 days to complete a task, with a standard deviation of 2 days. One standard deviation below the mean is 10 β 2 = 8 days, and one above is 10 + 2 = 12 days. The 1 Sigma rule tells you that about 68.26% of the time, the task will finish somewhere between 8 and 12 days. So roughly two out of every three tasks will land in that range β a useful, realistic expectation to share with stakeholders.
Every PMP formula explained free β plus worked examples and practice in PMP Math, and full timed mocks in the simulator.