Bayesian networksare the main probabilistic graphical model that causal graphical models (causal Bayesian networks) inherit most of their properties from. 完整的联合分布分解参数会爆炸 那就只依赖局部变量,可以去掉相互独立变量的边,这样就能大大减少参数 当满足如下两个性质的时候 简化后的DAG = P 所有依赖都...
2. Adjacent nodes in the DAG are dependent. 主要说明如果有边存在,则必不独立。 Definition 3.2(What is a cause?)A variable𝑋is said to be a cause of a variable𝑌if𝑌can change in response to changes in𝑋. Assumption 3.3((Strict) Causal Edges Assumption)In a directed graph, every ...
Causal inference goes beyond prediction by modeling the outcome of interventions and formalizing counterfactual reasoning. In this blog post, I provide an introduction to the graphical approach to causal inference in the tradition of Sewell Wright, Judea Pearl, and others. We first rehash the common ...
Directed paths are also chains, because each is causal on the next. Let’s say we also assume that weight causes cholesterol to rise and thus increases risk of cardiac arrest. Now there’s another chain in the DAG: from weight to cardiac arrest. However, this chain is indirect, at least...
The discussion is thorough with an effort to build everything from the first principles. 缺点 内容不够广泛 只介绍potential outcome,没有介绍其他“对手”的理论。比如DAG、比如SEM,都是与potential outcome竞争的理论。 超大的篇幅,600多页。但是只讲了随机试验。没有讲cluster randomized experiments, interferen...