Full Idea
There is a fundamental choice between the realist approach to causation which says that the relation is immediately given in experience, and the view that causation is a theoretical relation, and so not directly observable.
Gist of Idea
Either causal relations are given in experience, or they are unobserved and theoretical
Source
E Sosa / M Tooley (Introduction to 'Causation' [1993], §1)
Book Reference
'Causation', ed/tr. Sosa,E. /Tooley,M. [OUP 1993], p.4
A Reaction
Even if immediate experience is involved, there is a step of abstraction in calling it a cause, and picking out events. A 'theoretical relation' is not of much interest there if no observations are involved. I don't think a choice is required here.