Current and Future Directions of Intensive Longitudinal Data Analysis

• Activity Number: 18 - CURRENT and FUTURE DIRECTIONS of INTENSIVE LONGITUDINAL DATA ANALYSIS
• Type: Topic Contributed
• Date/Time: Sunday, July 28, 2019 : 2:00 PM to 3:50 PM
• Sponsor: Health Policy Statistics Section
• Author(s): Summer Frank-Pearce* and Michael Businelle and Darla Kendzor and Emily Hébert
• Companies: and Oklahoma Tobacco Research Center, The University of Oklahoma Health Sciences Center and Oklahoma Tobacco Research Center, The University of Oklahoma Health Sciences Center and Oklahoma Tobacco Research Center, The University of Oklahoma Health Sciences Center
• Keywords: Intensive Longitudinal Data; Mixed Model; Time-Lagged Models; Joint Modeling; Ecological Momentary Assessment

Abstract

Due to the wide-spread use of remote data collection devices such as smartphones and activity monitors, the collection of intensive longitudinal data (ILD), or data collected at multiple occasions over a relatively short period of time, has become increasingly common. ILD allow researchers to explore in-the-moment associations between quickly-changing subject attributes or behaviors, providing insight into the patterns and volatility/variability of behaviors within a day. Applied researchers are often interested in using ILD to model the in-the-moment associations between exposures (such as psychosocial, social and environmental risk factors or study interventions) on behavioral or health outcomes (such as self-reported stress levels or smoking cessation). This presentation will review commonly used multilevel or mixed modeling techniques for ILD including time-lagged models and the joint consideration of response mean and variation, with applications to tobacco use.