Modeling Human Dynamics by Means of Cointegration Methodology

The cointegration approach, developed by Engle and Granger (1987 ), allows treating nonstationary (i.e., integrated) time series as a multivariate system if their linear combination is stationary. Various psychological processes are often integrated but interconnected. Thus, cointegration methodology offers flexible techniques for modeling human dynamics. This paper introduces cointegration methodology to psychological researchers. After a brief introduction to time-series analysis, we summarize cointegration techniques and describe the so-called cointegration vector (β) and adjustment coefficient (α), the main parameters of cointegrated systems. We show that β and α are flexible tools for modeling long-term equilibrium as well as short-term dynamic adjustment within the multivariate system. An empirical example demonstrates advantages of cointegration methods in a typical research situation. Possible domains of application within the scope of psychology are discussed.