THE LOGIC OF NOMOTHETIC EXPLANATION
    Criteria for Nomothetic Causality
    False Criteria for Nomothetic Causality

Before social researchers say that one variable causes another, that a causal relationship exists, three criteria must be satisfied:

    1. There must be an empirical relationship or correlation between the two variables.

    2. The "cause" must precede the "effect" in time.

    3. The observed correlation cannot be spurious, it can't be caused by some third variable

There are other possible criteria that social researchers do not require.  For example, the correlation between two variables does not have to be perfect; exceptions do not disprove the relationship.