Inferential Validity of Digital Health Measures
Carmen D. Tekwe, Mercy Oladuti, Yuanyuan Luan, Andi Mai, Orfeu M. Buxton, See Ling Loy, Jeffrey S. Gonzalez, Roger S. Zoh
Abstract
Digital health measures increasingly inform treatment evaluation, risk classification, clinical monitoring, and regulatory decisions. Existing validity concepts concern a measure's technical soundness, clinical meaningfulness, usability, and scalability. Inferential validity concerns how well a measure supports a scientific, clinical, or regulatory conclusion. We propose assessing inferential validity as a downstream evaluation layer that links measurement system evidence to trustworthy conclusions.
Create a lesson
Related papers
Statistical Theory in the Age of Machine-Assisted Mathematics: Rethinking How Theory Is Made and Taught
Pietro Coretto
Statistical Leadership of What? Statistics After AI
Anders Gorst-Rasmussen
When to take one box, when to take two: A concrete analysis of Newcomb's problem
Radford M. Neal
Algorithms for optimizing model-based incomplete block designs
Jonas Bjermo, Frank Miller
Data Assimilation: Addressing Spurious Correlations and Scalability Issues
Eric Crislip, Moe Khalil, Kyle Neal
Becoming Good Stewards of Information: A framework for integrating ethical, civic, and professional formation throughout the statistics and data science curriculum
Kaitlyn G Fitzgerald