This month I gave a 45-minute presentation “Transparency in Science and Statistics” for the Italian Reproducibility Network. This presentation reflects my recent thinking on the topic. Important themes include “how to use a Ulysses contract to avoid fooling yourself (and others)”, “how to reveal uncertainty that often remains hidden”, “what is model-myopia (and how to avoid it)”, and “can Mertonian norms provide actionable common ground for statistics?”. The presentation can be found on YouTube at this link. This work is the result of a long-standing collaboration with Balazs Aczel and Alexandra Sarafoglou.
As I mentioned in the presentation, none of what I’m saying is earth-shattering or particularly surprising: most people will probably agree that “transparency is good, secrecy is bad”. I would not object to the ideas being called trivially self-evident. However, the practical ramifications of these trivial ideas are nonetheless profound; in science, what we believe and how we act are apparently not perfectly in sync.
I enjoyed giving the presentation, and I would like to thank the organizers for handling the logistics so smoothly. As it turns out, the Italian Reproducibility Network has an entire series of presentations on YouTube; one by my close colleague Felix Schönbrodt is available through this link.
Wagenmakers, E.-J. (2023). Transparency in science and statistics: https://www.youtube.com/watch?v=JCnKc9RHerc. Invited online presentation for the Italian Reproducibility Network, February 2023.
Hardwicke, T. E., & Wagenmakers, E.-J. (2023). Reducing bias, increasing transparency and calibrating confidence with preregistration: https://osf.io/preprints/metaarxiv/d7bcu/. Nature Human Behaviour, 7, 15-26.
Wagenmakers, E.-J., Sarafoglou, A., Aarts, S., Albers, C., Algermissen, J., Bahnik, S., van Dongen, N., Hoekstra, R., Moreau, D., van Ravenzwaaij, D., Sluga, A., Stanke, F., Tendeiro, J., & Aczel, B. (2021). Seven steps toward more transparency in statistical practice: https://www.nature.com/articles/s41562-021-01211-8. Nature Human Behaviour, 5, 1473-1480.
Wagenmakers, E.-J., Sarafoglou, A., & Aczel, B. (2022). One statistical analysis must not rule them all: https://media.nature.com/original/magazine-assets/d41586-022-01332-8/d41586-022-01332-8.pdf. Nature, 605, 423-425.