Problem
Research questions and friction points this paper is trying to address.
Gaussian Process
Functional Data Analysis
Distributional Assumptions
Covariate Dependence
Functional Moments
Functional Moments Regression
🤖 AI Summary
This study addresses the validity of Gaussian process assumptions in functional data by proposing a testing framework based on functional moment regression to systematically evaluate distributional shape and its potential dependence on covariates. The method provides the first quantitative assessment of deviations from Gaussianity, revealing that commonly used transformations often fail to eliminate such departures and elucidating their impact on inference and prediction. Applied to minute-level physical activity data from NHANES 2011–2014, the analysis demonstrates a significant violation of the Gaussian process assumption. While fixed-effect estimates remain robust under moderate effect sizes, individual-level inference and prediction are notably compromised when effect sizes are small.
📝 Abstract
The Gaussian Process (GP) assumption is often used in functional data analysis. We propose a method to assess departures from the GP assumption, both in terms of the shape of the distribution and its potential dependence on covariates, using a sequence of functional moment regressions. Our methods are inspired by and applied to objectively measured minute-level physical activity data from the National Health and Nutrition Examination Survey (NHANES) 2011-2014 study. In this setting, we find that the GP assumption is not satisfied, quantify the associations between functional moments and covariates, and show that standard data transformations, such as the log transformation, do not resolve the discrepancy between assumptions and reality. We further show that when the effect sizes are moderate, inference on the functional fixed effects is largely unaffected by departures from the GP assumption. However, when effect sizes are small, both inference and prediction of subject-level data can be strongly affected. Extensive simulations support these findings. This pragmatic paper presents new methods for real data analysis, with implications for statistical methodology and for understanding human activity and health.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Functional Moments Regression
Gaussian Process Assumption
Functional Data Analysis
Moment-based Inference
NHANES
🔎 Similar Papers
No similar papers found.
