Modeling for Causal Inference

Causal Models are mathematical models representing a causal relationship within an individual system or population. They allow for inferences to be drawn about the causal relationships from statistical data. These models allow us to get a good understanding of the relationship between causation and probability.

With all these methods we are trying to remove the bias and trying to build the parallel universe where we have answers to when treatment is given and when not given.

We can never observe the true potential outcomes in a case(The fundamental problem of causal Inference). With these models, we try to build this parallel universe and try to observe and infer what would have been the answer to the counterfactual question. We try to come closer to the real counterfactual outcome by using these models.

NOTE: With these Methods, we can try to reduce the bias within our Model. It does not completely remove the bias.