Tea - A High-level Language and Runtime System for Automating Statistical Analysis

Explore a groundbreaking 20-minute conference talk from the ACM Symposium on User Interface Software and Technology that introduces Tea, a high-level declarative language and runtime system designed to revolutionize statistical analysis. Discover how Tea allows users to express study designs, parametric assumptions, and hypotheses in a user-friendly manner, eliminating the need for extensive statistical expertise. Learn how this innovative system compiles high-level specifications into a constraint satisfaction problem, automatically determining and executing valid statistical tests. Gain insights into Tea's ability to match expert choices while intelligently switching to non-parametric tests when necessary. Examine the system's effectiveness in preventing false negatives and false positives commonly associated with incorrect test applications, potentially transforming the landscape of replicable statistical analysis in research.