ABSTRACT
The Auto Regressive Integrated Moving Average (ARIMA) is primarily a within-subject analytic technique and does not lend itself directly to an analysis of a cross-subject design. For a Markov Chain analysis, the time continuum may be divided into discrete time units or may remain a continuum. Specifically, instead of being expressed in the form of a linear equation as in ARIMA, the model in Markov Chain is expressed in the form of a conditional probability matrix known as a transition matrix. The frequency matrix can be transformed into a transition matrix by dividing each cell by the row total. In matrix algebra, which is essentially a form of mathematical shorthand, mathematical computations are performed on entire matrices rather than individual numbers. Once the transition matrix model is constructed for the stochastic process, the model can be tested to assess if the identified model is a good description of the underlying process.
