Causality: Causal Diagrams, Associations & Causal Inferences

Proposed Audience:

1)Researchers and Clinician Scientists, who are familiar with Randomized Controlled Trials (RCTs), who now want to use:
a) Observational Data (e.g. Registries, Claims database)
b) Real-world Evidence – RWE (e.g. EMR, Population/Public Health, data from devices, social data sources)

2) Healthcare Life Sciences – Data Scientists, Architects, Business/Data Analysts, who extract EMR data/provide real-time data from Medical data sources for use in Health Research, BioPharma & MedTech – Medical needs.

3) Data Scientists, who frequently encounters causal questions, once they identify association/correlation between variables

4) Industry/Functional Consultants, Business Analysts, who frequently encounters causal inference queries from Data Scientists

5) Anyone who is interested in usage of Causal Diagrams, when to use them and their benefits


Why we need Causal Diagrams/Graphs?

Causal Graphs can be used to understand a problem and explore possible solutions.

Even without mastering the underlying mathematical theory DAGs, we can translate our qualitative subject knowledge, expert knowledge, causal knowledge, into a picture, into a causal graph.

And this picture can be used to identify problems in the study design and to guide the data analysis.

And also to make the scientific discussion much more precise and efficient.
Rather than writing many pages describing our assumptions, we can just draw a picture that represents them.