As with random vectors, other than in certain special cases, it can be difficult to describe and manipulate random processes through the use of joint-probability density functions (pdfs), although the definitions for the joint-pdf is provided. Instead, the video discusses that second-order statistics including the mean sequence, the autocorrelation sequence (ACF) (second-moment), and the autocovariance sequence (central moment) are often adequate for capturing key salient features of the random processes. After extending the definitions for the mean and correlations previously seen for random vectors to random processes, two examples are given. The first example derives the ACS for a process which is based on an a priori defined physics-based model (namely, an harmonic process). The second example considers finding the ACS of a linear function of random processes (in this case, a non-causal delay).