I’m in Rome at the International Workshop on Computational Economics and Econometrics. I gave a seminar on Monday on the ever-popular subject of data visualization. Slides are here. In a few minutes, I’ll be speaking on Inference in Complex Systems, a topic of some interest from practical research experience my colleague Rick Hood and I have had in health and social care research.
Here’s a link to my handout for that: iwcee-handout
In essence, we draw on realist evaluation and mixed-methods research to emphasise understanding the complex system and how the intervention works inside it. Unsurprisingly for regular readers, I try to promote transparency around subjectivities, awareness of philosophy of science, and Bayesian methods.
This is a very quick thought for teaching, in passing. People often talk about chi-squared tests being overpowered when n is large. It occurs to me that a good way to broach this concept in an intuitive way is to point out that they are no different to t-tests and the like, but do not provide a meaningful point estimate. When you see the mean difference in blood pressure from drug X is 0.3mmHg, with p<0.001, you know it is clinically meaningless. When you see X2=3.89, nobody knows what to think. So perhaps the best thing to do is to mention this alongside non-parametric rank-based procedures, when you explain that they don’t give you an estimate or confidence interval.
Easy links: dear-data.com deardata-deliveries.tumblr.com
Procedural notes that can be skipped:
I had previously intended to write something about the shapes employed by Giorgia Lupi and the Accurat studio – and indeed I still will. But that takes some time and it got leapfrogged by Dear Data. This post came at a good time because I didn’t get around to it straight away (we’re now at week 35 of the project) and by the time I did, some other ideas had bubbled up in conversations, focussing my attention on the process of design, critique and refinement (which is getting added to my reading pile for the summer). These ideas are so alien to statisticians that I am not sure any of them will have read this far into this post, but they (we) are the ones that need to up their (our) game in communication. Nobody else will do it for us! The other building block that came along in time was finally finding really nice writing paper and resolving to draft everything by hand from now on, preferably in time when I’m physically away from a computer. It has already proven very productive. People seem to have different approaches that work (like starting with bullet points, or cutting out phrases, or mind maps), but mine is to start writing at sentence one, like Evelyn Waugh, and just carry straight on. There is no draft; why should there be? Finding that technique and place to write is really valuable; don’t devalue it and try to squeeze it into a train journey or between phone calls. It’s the principal way in which you communicate your work, and probably the most overlooked.