ABSTRACT
As a sociologist who is only superficially acquainted with trends and developments in quantitative behavioral political science with the exception of simulation studies, the overwhelming emphasis has been on stating generalizations appropriate to specific populations rather than stating general laws of political behavior. The question of whether or not one is generalizing only to specific populations or attempting to state scientific laws has created considerable confusion in the sociological literature. Analogously, a completely closed population is one that is subject to no outside influences, including immigration or emigration. The migration processes should not affect relationships among the variables, though they may very well affect measures of central tendency or dispersion for single variables. As Miller and Stokes have noted, the method of path coefficients provides a simple and useful way of representing a total correlation between any two variables as a function of the causal paths that connect them.
