Inside Out: Externalizing Assumptions in Data Analysis as Validation Checks
Journal of Data Science · 01.01.2025 · 1-18
DOI: 10.6339/25-jds1206 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Data Science, online erschienen am 09.03.2026. Verfasst von H. Sherry Zhang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In data analysis, unexpected results often prompt researchers to revisit their procedures to identify potential issues. While some researchers may struggle to identify the root causes, experienced researchers can often quickly diagnose problems by checking a few key assumptions. These checked assumptions, or expectations, are typically informal, difficult to trace, and rarely discussed in publications. In this paper, we introduce the term analysis validation checks to formalize and externalize these informal assumptions. We then introduce a procedure to identify a subset of checks that best predict the occurrence of unexpected outcomes, based on simulations of the original data. The checks are evaluated in terms of accuracy, determined by binary classification metrics, and independence, which measures the shared information among checks. We demonstrate this approach with a toy example using step count data and a generalized linear model example examining the effect of particulate matter air pollution on daily mortality.
Zitieren
APA
Zhang, H. S., & Peng, R. D. (2025). Inside Out: Externalizing Assumptions in Data Analysis as Validation Checks. Journal of Data Science, 1-18. https://doi.org/10.6339/25-jds1206
Vancouver
Zhang HS, Peng RD. Inside Out: Externalizing Assumptions in Data Analysis as Validation Checks. Journal of Data Science. 2025:1-18. doi:10.6339/25-jds1206
BibTeX
@article{Zhang2025,
author = {Zhang, H. Sherry and Peng, Roger D.},
title = {Inside Out: Externalizing Assumptions in Data Analysis as Validation Checks},
journal = {Journal of Data Science},
year = {2025},
pages = {1--18},
doi = {10.6339/25-jds1206}
}
EUVIMED