Bayesian approaches have gotten increasingly popular but may be overwhelming at first. This extensive guide will walk you thru applications, libraries, and dependencies of causal discovery approaches.
The countless possibilities of Bayesian techniques are also their weakness; the applications are enormous, and it could be troublesome to grasp how techniques are related to different solutions and thus applications. In my previous blogs, I actually have written about various topics similar to structure learning, parameter learning, inferences, and a comparative overview of various Bayesian libraries. On this blog post, I’ll walk you thru the landscape of Bayesian applications, and describe how applications follow different causal discovery approaches. In other words, how do you create a causal network (Directed Acyclic Graph) using discrete or continuous datasets? Can you identify causal networks with(out) response/treatment variables? How do you choose which search methods to make use of similar to PC, Hillclimbsearch, etc? After reading this blog you’ll know where to begin and how you can select essentially the most appropriate Bayesian techniques for causal discovery to your use case. Take your time, grab a…
