Malcolm Barrett
Malcolm Barrett
Time to adoption: https://www.kaggle.com/competitions/sliced-s01e10-playoffs-2/data. Spay-neuter as an intervention? Probably a null effect so could be interesting example of confounding
idea: disney data on time to ride closing. exposure as weather or something?
Simulating survival data: https://www.jstatsoft.org/article/view/v097i03
Now that you mention it, the clustering is really happening at the column level, not the row level like this package is focused on. Maybe better suited to a recipe...
I'm broadly interested in this topic, both in the sense you're talking about (reducing nodes) and in the sense of supernodes with existing nodes also visualized, e.g. something like this...
I think we need an effective sample size section
Oh it looks like last years materials for this aren't in the 2019 snapshot? I guess I didn't update them on this repo. They are actually here: https://github.com/malcolmbarrett/rbootcamp_data_analysis
👀 👀 👀
Cross fitting: https://arxiv.org/abs/2004.10337
Maybe g-computation here