MOOCs

Currently doing this free online edX course: HarvardX: Causal Diagrams: Draw Your Assumptions Before Your Conclusions | edX and it’s really good. I finished the Pearl book on causal inference thinking it all made sense but wasn’t sure how I would apply it in practice. This course fills that gap by going through many examples of epidemiological findings which only make sense in the light of graphical models. It has made me change how I think about confounding and selection bias.

It is mostly video lectures followed by tests. The lecturer is very clear, it’s well-paced and the questions are good at testing your understanding of the material. It’s also rather bite-sized so you can move on a couple of steps even if you only have ten minutes free one day.

I’ll put my notes on here when I am finished. The author has made his book available online here - at first glance it looks very long and mathematical (the course is much more beginner-friendly).

I like doing MOOCs. I did a Python one this year (Programming in Healthcare – Let’s Do Digital) - it was a bit basic for me but the next one promises to be more challenging. I’ll probably do one of these courses next:

As it happens we have also been discussing creating our own MOOC for refresher DHIS 2 training in our global health project. They had identified two options:

Moodle is well established and widely used so we are going with that option, possibly in combination with Xerte Online Toolkits for authoring learning materials. But Open edX did look good and has a convenient Dockerised version called Tutor: Tutor: the Docker-based Open edX distribution designed for peace of mind — Tutor documentation.