MixWILD: A Program for Analyzing Intensive Longitudinal Data

2020
Research Category: Health Sciences
Presenter: Jixin Li

The prevalence of wearable devices and sensors are offering enormous opportunities in the collection of Intensive Longitudinal Data (ILD) in medical research. Instantaneous subjective and objective data can be possibly collected at high density by novel methods, such as Ecological Momentary Assessment (EMA) using smartphones and accelerometry in naturalistic settings. However, traditional methods of statistical analysis that are often limited to the subject-specific mean of the outcome and between-subject variance (i.e., random intercept). Moreover, existing methods require researchers to have programming experience in R or Python to be able to write statistical models of interest. We developed MixWILD (Mixed model analysis With Intensive Longitudinal Data), a statistical software designed to perform multi-level modeling (with mixed effects) on longitudinal experience sampling data without having to write complex statistical code. It tests the effects of subject-level parameters (variance and slope) of time-varying variables. MixWILD is generalizable to a variety of data collection strategies (i.e., EMA, sensors) as a robust and reproducible method to test predictors of variability in level 1 outcomes and the associations between subject-level parameters (variances and slopes) and level 2 outcomes. This statistics software provides novel methods of analysis of ILD and enhances understanding of complex effects of intensively time-varying factors on health outcomes. The tool is open-sourced and can be used by researchers to model their intensive longitudinal data as well as train researchers in multi-level modeling using an easy-to-use graphical user interface.

Menu