Causality
I've been reading Causality by Judea Pearl, one of my Christmas presents this year. It's an amazing read. I started with the epilogue, to get the grand view of the book from a researcher's perspective. The epilogue's contents can actually be found here.
The epilogue is the transcript from a lecture that Pearl gave to UCLA researchers around the time of the first edition of the book. In it, Pearl outlines the history and issues of causality.
One of the major ideas that Pearl covers is the sticky issue of:
correlation does not imply causation
This issue stems from using algebra instead of causal graphs to describe the world. Causal graphs add a few critical elements to the algebra:
- Preservation of the dynamics of a situation, the ins and the outs to a system
- Using equations as representations of actual mechanisms observable in our experiments
- Interventions setup to explicitly adjust the mechanisms, to uncover actual causality if it exists
Pearl then goes on and gives support and an example of using these ideas.
I'm taking my time with this book, working through ideas with Ruby code and finding out if I understand the concepts deeply enough to be a practitioner. I have a few un-optimized ideas I might share in an upcoming gem, we'll see.
Site Feed