The reproducible research movement in statistics

Abstract

It is now widely recognized that the traditional published article is insufficient to permit verification of computational results. The emergence of powerful computational hardware combined with vast data collection and storage capabilities presents many novel opportunities for researchers. Unfortunately the standards for communication of published computational findings have evolved in ways that make verification and validation next to impossible and impede the ability of others to build on past research [1-3]. A movement toward reproducible research – dissemination that includes sufficient experimental details such that results can be replicated by others in the field, i.e. the code and the data – has developed in many disciplines and research areas to address this shortcoming in research [9]. In this paper I will present a jointly developed set of standards to guide the dissemination of reproducible research, and discuss changes originating outside academia that affect computational and empirical research dissemination including recent journal publication and federal agency dissemination requirements. Standards and Scientific Communication In December of 2012, more than 70 computational scientists and other stakeholders such as journal editors and funding agency officials gathered at Brown University for the ICERM Workshop on “Reproducibility in Computational and Experimental Mathematics. ” This workshop provided an opportunity for a broad cross

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 13 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.