Several steps are taken to develop methods for analyzing systems that involve probabilistic causation. The basic ideas and distinctions are illustrated for systems with dichotomous variables. It is shown that these basic ideas have analogous counterparts in causal systems with continuous variables. By using a generalized conditional probability density function, it is shown that the causal models developed by proponents of path analysis and structural equation methods are special cases of a general probabilistic causal model. It is also argued that the general probabilistic causal model may be appropriate in situations where the traditional path analysis model does not fit. Implications for hypothesis testing are drawn. (Author)