# Causal Models: Guide to gbiqq

*Draft!: 2020-01-09*

# Preface

**Map**

This (draft) guide is supplementary material for our book-in-progress *Integrated Inferences*.

- The first part of the guide provides a brief motivation of causal models.
- The second part describes how the package works and how to use it.
- The third part illustrates applications of the package for defining and learning from a set of canonical causal models.
- The short last part has a notation guide.

**Credits**

The approach used in gbiqq is a generalization of the biqq models described in “Mixing Methods: A Bayesian Approach” (Humphreys and Jacobs 2015). The conceptual extension makes use of work on probabilistic causal models described in Pearl’s *Causality* (Pearl 2009). The approach to generating a generic stan function that can take data from arbitrary models was developed in key contributions by Jasper Cooper and Georgiy Syunyaev. Lily Medina did magical work pulling it all together and developing approaches to characterizing confounding and defining estimands. Clara Bicalho helped figure out a nice syntax for causal statements. Julio Solis made key contributions figuring out how to simplify the specification of priors.

### References

Humphreys, Macartan, and Alan M Jacobs. 2015. “Mixing Methods: A Bayesian Approach.” *American Political Science Review* 109 (04): 653–73.

Pearl, Judea. 2009. *Causality*. Cambridge university press.