the reason that China is not "responsible for the imbalance because it saves too much", is that "saving too much" cannot cause an imbalance. If there is such a thing as "saving too much" causing anything. It is a symptom, not a cause.

I suspect that supply-side economics is consistent with the view that savings causes investment. This is inconsistent with Keynes' paradox of thrift. Therefore in a Keynesian view saving doesn't cause investment. It is either that investment causes saving or that there's a third common cause of both.

Causal relationships are extremely difficult to infer from data. You run into correlation is not causation, as well as the problem of what direction causation runs in (post hoc ergo propter hoc being a possible problem here). And since economics is not experimental but historical, one would have to do a thorough historical study and then ensure that no external factors have been overlooked that can introduce a spurious apparent direction of causation.

Is economics ultimately a collection of just-so stories? Do we like the paradox of thrift because it is consistent with solidarity politics?

By laying out pros and cons we risk inducing people to join the debate, and losing control of a process that only we fully understand. - Alan Greenspan