Navigating the garden of forking paths: theoretical foundations for interactive data analysis in data-driven science

Theory and Methods Challenge Fortnight, Alan Turing Institute

Our TMCF

Theory & Methods Challenge Fortnights are intensive, two-week events where teams of 12 experts from across the Turing university partner network and external institutions worldwide collaborate to initiate work on tackling a foundational challenge in data science and artificial intelligence. Each event focuses on a specific theoretical or methodological challenge that has the potential to impact data science and artificial intelligence at a fundamental level.

via turing.ac.uk.

Welcome to our upcoming Turing Theory & Methods Challenge Fortnight (TMCF). Our challenge will take place in the British Library in summer 2024.

The ambition behind TMCFs is nicely laid out on the Alan Turing Institute’s website (above). Ours seeks to a address a problem familiar to data-driven research: the garden of forking paths fallacy (Gelman and Loken 2013). We have assembled a stellar team to work on the challenge – world-leaders in data science engineering and practice. Alongside the challenge we intend to host public lectures and seminars – more news on this to follow.

We will update these pages through 2024 as planning and other preparatory work develops.


Cagatay Turkay and Roger Beecham, Challenge Leads

Key Dates

  • Week 1 (full team) : Monday 17th June – Friday 21st June 2024
  • Week 2 (UK-based team) : Monday 8th July – Friday 12th July 2024

References

Gelman, Andrew, and Eric Loken. 2013. The garden of forking paths: Why multiple comparisons can be a problem , even when there is no "fishing expedition"; or "p-hacking"; and the research hypothesis was posited ahead of time.” In Department of Statistics, Columbia University. http://www.stat.columbia.edu/~gelman/research/unpublished/p_hacking.pdf.