Irina Gaynanova | Replicability, Reproducibility, Reviewing, and Optimism for the Future of Science

#datascience #science #statistics #replication

Irina Gaynanova | Replicability, Reproducibility, Responsibility, and Optimism for the Future of Science

Irina Gaynanova (Texas A&M) describes why she thinks that replicability is a prerequisite for reproducibility in science and how scientists can (personally) start improving the replicability of research. We also discuss how the concepts of replicability/reproducibility can differ according to the domain-specific context and the methods used.

Please forward to any students or colleagues who would find this of interest!

0:00 Replicable research precedes reproducible science
8:30 Reproducing training vs test performance
15:45 The value of manual annotation
23:25 Review process vs messy elements of replication
35:20 Gaming performance metrics & battle of the algorithms
50:40 Proprietary data sets
1:00:00 Silver linings & optimism for the future