ABSTRACT
Empirical work in psychology and other social sciences frequently collects many measurements from individuals in an attempt to maximize statistical power. These sequential measurements, assumed to be influenced by one or more independent variables manipulated by the experimenter as well as a number of random and latent variables, are of ten treated as an independent and identically distributed (IID) sample. That is, considering each subject as a random-data-generating device like a coin, the measurements are collected over time just as one would write down the sequence of heads and tails obtained from independent flips of a coin.
