Enhanced Dynamic Documents for Reproducible Research

Abstract

Dynamic documents that combine text and code, which is evaluated to dynamically create content when the document is “rendered,” for example, Sweave, are a large step forward in reproducible data analysis and computation. However, to capture the research process, we need richer paradigms and infrastructure. The process includes all the investigations and computations, and not just the final reported ones, and the entirety represents reproducible research. In addition to richer paradigms for reproducability, we want to be able to capture more complex aspects of the computational process, such as the use of multiple languages, and also engage different communities using other programming languages so that reproducible computations and research become more widespread. We also need to integrate existing and future approaches with commonly used tools such as Microsoft Word and make the resulting documents richer for authors and readers. We present two approaches to structured, dynamic documents that use modern, ubiquitous standard technologies (XML) and provide extensible infrastructure for richer documents. The first integrates R and Microsoft Word for use by a broader audience and provides some innovations in this interface, and the second uses eXtensible Stylesheet Language (XSL) and R to provide a flexible and extensible infrastructure for richer, more accessible dynamic documents.