# can measurements go out of the uncertainty bounds?

In the below picture, the measurements are inside the $\pm 3 \sigma$ bounds. In my experiment, the measurements sometimes go out of the uncertainty bounds.

This is a snapshot of my plot where the red is $\pm 3 \sigma$ bounds (i.e. $true \pm 3\sigma$ ), the black is the measurements, the blue is the true value and the green is the EKF. Is there something wrong with my results?

The meaning of $±3σ$ is that for a given distribution of the measurements, most of the measurements (which have values of up to three time the standard deviation around the average) will be in that boundary. By definition there will be values out side the boundary.