Data Confessions Matter
Xiao-Li emphasizes the critical need for transparency in data science, advocating for "data confessions" to enhance reproducibility and replicability. He highlights the tendency to focus excessively on model development while neglecting the quality of the data itself. By disclosing limitations and potential defects, the scientific community can foster progress and integrity in research.In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
SDS 581: Bayesian, Frequentist, and Fiducial Statistics in Data Science — with Xiao-Li Meng
Related Questions
How does data science differ from traditional statistics according to the Harvard Data Science Review?
How does data science differ from traditional statistics according to the Harvard Data Science Review in the episode AI Today Podcast: Interview with Harvard Data Science Review (HDSR) Podcast hosts Liberty Vittert & Xiao-Li Meng and the clip Data Science Evolution?