Recurrent event analysis in the presence of real-time high frequency data via random subsampling

TL;DR

This paper introduces a random subsampling method for efficient likelihood-based analysis of high-frequency recurrent event data from digital sensors, enabling practical modeling of physiological impacts on behaviors like suicidal ideation.

Contribution

It proposes a novel subsampling framework that approximates likelihood calculations, making recurrent event analysis computationally feasible with high-frequency data.

Findings

Method reduces computational costs significantly.

Estimator remains unbiased despite subsampling.

Application to real data demonstrates practical utility.

Abstract

Digital monitoring studies collect real-time high frequency data via mobile sensors in the subjects' natural environment. This data can be used to model the impact of changes in physiology on recurrent event outcomes such as smoking, drug use, alcohol use, or self-identified moments of suicide ideation. Likelihood calculations for the recurrent event analysis, however, become computationally prohibitive in this setting. Motivated by this, a random subsampling framework is proposed for computationally efficient, approximate likelihood-based estimation. A subsampling-unbiased estimator for the derivative of the cumulative hazard enters into an approximation of log-likelihood. The estimator has two sources of variation: the first due to the recurrent event model and the second due to subsampling. The latter can be reduced by increasing the sampling rate; however, this leads to increased computational costs. The approximate score equations are equivalent to logistic regression score equations, allowing for standard, "off-the-shelf" software to be used in fitting these models. Simulations demonstrate the method and efficiency-computation trade-off. We end by illustrating our approach using data from a digital monitoring study of suicidal ideation.