'Methods Failing the Data, Data Failing the Methods'
A thesis is nominally a unified contribution to knowledge. Something new, several pieces of knowledge all pointing in the same direction. I am not focussed enough to do this. It’s also “a big claim”. I obviously had to retrodict a single big claim, and surely most people do the same. I’m not amazed with it as a contribution to science but it is a pretty good representation of my mind: unfocussed, sweeping; long on synthesis, short on analysis; more amusing than deep but not not deep. It’s called Methods Failing the Data, Data Failing the Methods. Here’s an attempt to explain plainly what I actually did. (You can also click “The Point” on the individual papers here.) What did I actually discover? Mask wearing in community settings reduces SARS-CoV-2 transmission Noted the global pre-mandate voluntary spike in mask wearing Identified a ubiquitous methodological mistake (the mandate timing proxy) First international analysis of masks with a random sample of self-reported mask wearing data
A thesis is nominally a unified contribution to knowledge. Something new, several pieces of knowledge all pointing in the same direction. I am not focussed enough to do this. It’s also “a big claim”. I obviously had to retrodict a single big claim, and surely most people do the same. I’m not amazed with it as a contribution to science but it is a pretty good representation of my mind: unfocussed, sweeping; long on synthesis, short on analysis; more amusing than deep but not not deep. It’s called Methods Failing the Data, Data Failing the Methods . Here’s an attempt to explain plainly what I ac
Explore this link on the map →related reading
- Gap Mapgap-map.org
- Researchgleech.org
- The End of Theory: The Data Deluge Makes the Scientific Method Obsolete | WIREDwired.com
- How Life Sciences Actually Work: Findings of a Year-Long Investigation - Alexey Guzeyguzey.com
- The Limits of Dataissues.org
- RajLabrajlaboratory.blogspot.com
- The speed of science - Works in Progress Magazineworksinprogress.co
- Make It Work, Then Prove It Works: A Framework for Research - Vincent Sitzmannvincentsitzmann.com
- 1 Introduction – <span style='font-weight: 700'>Causal Inference</span><br/> <i style='color: #00b7ff'>The Mixtape</i>mixtape.scunning.com
- Gwern's Most Important Writing (in essays, tweets, book reviews, and other forms) - Alexey Guzeyguzey.com
- Zen and the Art of Machine Learning Researchblog.jxmo.io
- An Insider’s Guide to Asking the Right Questions During Your PhD - New Sciencenewscience.org