David Bessler pointed out that Bertrand Russell changed his views on causality relative the those he expressed in 1913 (see Epilogue, page 337). In his book Human Knowledge: Its Scope and Limits (Simon and Schuster, 1948) Russell states: "The power of science is its discovery of causal laws" (page 308).
I have found the change in Russell's writing to be merely stylistic. True, he now (1948) allows himself free use of causal vocabulary, but he still interprets causal claims to be no more than predictions and retrodictions supported by physical laws (the same view that he held in his The Principle of Mathematics, 1903, pp. 474-479). Such passive predictions, void of intervention and directionality, are not classified as "causal" in our book (see Chapter 1). No wonder Russell turned so tolerant to causal speech -- stripped of its two distinctive features, causation ceases to be a challenge.
Subject: Gentle introduction to d-separation
At the request of several readers who have had (temporary) difficulties switching from algebraic to graphical thinking, I have written a more gentle introduction to d-separation, supplementing the one given in Chapter 1, pp. 16-18.
Next Discussion (N. Megiddo: Simpson's paradox and decision trees)