4-22
l   Classical variance:
diverges for some commonly observed noise processes, such as random walk, i.e., the variance increases with increasing number of data points.
l  Allan variance:
        •  Converges for all noise processes observed in precision
            oscillators.
        •  Has straightforward relationship to power law spectral density types.
        •  Is easy to compute.
        •  Is faster and more accurate in estimating noise processes than the Fast Fourier Transform.
Why sy(t)?
-