Thread by @WomenInStat

I’m going to begin today with a bold claim: Being an applied statistician is a lot like being an ethnographer.

I say this both based upon years of experience working in collaborative projects and consulting and based on my experience studying ethnography. (Recall: before my PhD in statistics, I started and quit a PhD in sociology).

Very often a question asked is not the ‘real’ question at hand. Typically, the person asking has a sense of the problem, but may not know exactly how to ask the question.

For this reason, I like to ask people to back up, tell me more about their project, and then I ask them a lot of questions. I assume that it’s not straightforward – figuring out their question is a puzzle in and of itself.

A question is never really in the abstract. There are always constraints – some resource driven, and some socially determined. You have to elicit these as well – and some of them may be unspoken.

One constraint is disciplinary norms. As I showed earlier this week, economists like to use CRVE, while sociologists like to use MLMs. They both ‘get the job done’ in terms of taking into account clustering, but the approach – what is signal, what is noise – is different.

To be clear: I’m not saying your job is to reify norms. But they need to be acknowledged, as they affect how the person will need to write about their work.

Another constraint is what the person – and their team – knows how to do themselves. What software do they use? What methods are they familiar with? You simply can’t provide an answer without also providing a means to getting between here and there.

Finally, very often the job of a statistical consultant is to be an ‘outsider.’ As an outsider, it’s ok for me to ask a lot of questions. Much of the work is more about ‘thinking statistically’ than modeling or calculation.

For example, what are the goals of the project, the questions guiding the research? What is the study design? Why are you using this model and not another?

In summary: Like an ethnographer, be curious, listen carefully, and observe.

Try to really being intellectually engaged with the work – ask a lot of questions, think carefully about what is possible, and help them. Remember that statistics is one part of science, but not the whole of it.