WiSER: Robust and scalable estimation and inference of within‐subject variances from intensive longitudinal data

• Published in: Biometrics Vol. 78; no. 4; pp. 1313 - 1327
• Main Authors: German, Christopher A., Sinsheimer, Janet S., Zhou, Jin, Zhou, Hua
• Format: Journal Article
• Language: English
• Published: United States Blackwell Publishing Ltd 01.12.2022
• Subjects: Accelerometers; accelerometry; Algorithms; Blood pressure; blood pressure variability; clinical trials; Computer Simulation; diabetes; Diabetes mellitus; electronic health record (EHR); Electronic health records; Electronic medical records; emotions; Female; glycemic variation; Humans; Inference; intraindividual variability; Longitudinal Studies; method of moments; mHealth; Models, Statistical; Probability; regression analysis; Robustness (mathematics); telemedicine; Variability; Variance; Wearable technology; Womens health; blood pressure variability; mHealth; electronic health record (EHR); method of moments; intraindividual variability; glycemic variation
• ISSN: 0006-341X; 1541-0420; 1541-0420
• DOI: 10.1111/biom.13506

The availability of vast amounts of longitudinal data from electronic health records (EHRs) and personal wearable devices opens the door to numerous new research questions. In many studies, individual variability of a longitudinal outcome is as important as the mean. Blood pressure fluctuations, glycemic variations, and mood swings are prime examples where it is critical to identify factors that affect the within‐individual variability. We propose a scalable method, within‐subject variance estimator by robust regression (WiSER), for the estimation and inference of the effects of both time‐varying and time‐invariant predictors on within‐subject variance. It is robust against the misspecification of the conditional distribution of responses or the distribution of random effects. It shows similar performance as the correctly specified likelihood methods but is 103 ∼ 105 times faster. The estimation algorithm scales linearly in the total number of observations, making it applicable to massive longitudinal data sets. The effectiveness of WiSER is evaluated in extensive simulation studies. Its broad applicability is illustrated using the accelerometry data from the Women's Health Study and a clinical trial for longitudinal diabetes care.