Dear SIPTAnts,

I’m not sure this is “news”, but I’d still like to raise a point. It’s for those of you who care to connect probability to the real world.

The point is that science needs falsifiability. And purely probabilistic models aren’t really falsifiable, they’re at most improbable. This appears to be a major reason why we have all these theories of probability, and the related communities, and there’s no way to prove anyone wrong. Which is good for our careers, and less so with regard to progress.

Contrast this with structural causal modelling. When we put forward a causal graph (a theory), any of its arcs is either right or wrong. This we can often test experimentally, or by other means. We correct the model, re-test and iterate, eventually consolidating our model of the world. Probability still plays a role there, although one of secondary importance.

So it seems to me that the scientific method is based on causality rather than probability. I guess I’m not saying anything new. I just wanted to make the point; to me it seemed something worth reflecting on.

Bests Marco