SOME LINEAR MODELS FOR 2-WAVE, 2-VARIABLE PANEL ANALYSIS

In the absence of a sufficient number of a priori substantive assumptions ruling out certain conceivable causal linkages among variables, neither cross-lagged correlation nor any other technique for analyzing 2-wave, 2-variable panel data will yield a unique causal inference. A wide variety of distinct linear causal models will always be compatible with a given set of panel data. (PsycINFO Database Record (c) 2006 APA, all rights reserved). © 1969 American Psychological Association.