rTisane: Externalizing conceptual models for data analysis increases engagement with domain knowledge and improves statistical model quality

The article discusses the rTisane, a domain-specific language (DSL) tool developed to express conceptual models for data analysis. It helps analysts to externalize their assumptions about variables and their relationships, which improves the quality of the statistical models. The tool also increases the engagement of analysts with their domain knowledge. The study found that rTisane leads to statistical models that better fit the data and match the analysts’ assumptions and analysis intent.

Publication date: 25 Oct 2023
Project Page: https://doi.org/10.1145/nnnnnnn.nnnnnnn
Paper: https://arxiv.org/pdf/2310.16262