@article{Alter_Donakowski_Gager_Heus_Hunter_Ionescu_Iverson_Jagadish_Lagoze_Lyle_et al._2020, title={Provenance metadata for statistical data: An introduction to Structured Data Transformation Language (SDTL)}, volume={44}, url={https://iassistquarterly.com/index.php/iassist/article/view/983}, DOI={10.29173/iq983}, abstractNote={<p>Structured Data Transformation Language (SDTL) provides structured, machine actionable representations of data transformation commands found in statistical analysis software.   The Continuous Capture of Metadata for Statistical Data Project (C<sup>2</sup>Metadata) created SDTL as part of an automated system that captures provenance metadata from data transformation scripts and adds variable derivations to standard metadata files.  SDTL also has potential for auditing scripts and for translating scripts between languages.  SDTL is expressed in a set of JSON schemas, which are machine actionable and easily serialized to other formats.  Statistical software languages have a number of special features that have been carried into SDTL.  We explain how SDTL handles differences among statistical languages and complex operations, such as merging files and reshaping data tables from “wide” to “long”. </p>}, number={4}, journal={IASSIST Quarterly}, author={Alter, George and Donakowski, Darrell and Gager, Jack and Heus, Pascal and Hunter, Carson and Ionescu, Sanda and Iverson, Jeremy and Jagadish, H.V. and Lagoze, Carl and Lyle, Jared and et al.}, year={2020}, month={Dec.} }