St. James Ballroom
The Data Detective's Toolkit (303863)
*Kim Chantala, RTI InternationalKeywords: Data cleaning, data validation, skip patterns, codebooks, data crosswalks
The Data Detective’s Toolkit is a set of SAS macros to help keep data preparation on schedule and within budget. This toolkit provides an efficient and low-cost way to create codebooks, master lists of SAS data sets for a project, reports of variables needing special investigation or cleaning, validation of skip patterns, and data crosswalks showing the relationship of variables across datasets. Traditionally, these documents are produced at the end of the project with a great deal of programming and manual effort, but these tools allow the programmer to seamlessly create these documents and reports at any time during the data preparation task. Producing these documents early in data collection improves data quality as well as communication between the data collection team and client. The only requirement for producing these documents and reports is having SAS data sets with formats and labels. The Data Detective’s Toolkit is provided as open-source SAS code and can be downloaded from Github at no charge.