Challenges in Time-Varying Causal Effect Moderation Analysis in Mobile Health

Presented by Walter Dempsey, University of Michigan

Friday, 24/01/25, 11am, ET Online
Webex Meeting Link
Meeting # 2633 697 8890
Password: RMMESTAT

Abstract: Twin revolutions in wearable technologies and smartphone-delivered digital health interventions have significantly
expanded the accessibility and uptake of mobile health (mHealth) interventions in multiple domains of health
sciences. Sequentially randomized experiments called micro-randomized trials (MRTs) have grown in popularity as a
means to empirically evaluate the effectiveness of mHealth intervention components. MRTs have motivated a new
class of causal estimands, termed “causal excursion effects”, that allow health scientists to answer important
scientific questions about how intervention effectiveness may change over time or be moderated by individual
characteristics, time-varying context, or past responses. In this talk, we present two new tools for causal effect
moderation analysis. First, we consider a meta-learner perspective, where any supervised learning algorithm can be
used to assist in the estimation of the causal excursion effect. We will present theoretical results and accompanying
simulation experiments to demonstrate relative efficiency gains. Practical utility of the proposed methods is
demonstrated by analyzing data from a multi-institution cohort of first year medical residents in the United States.
Second, we will consider effect moderation with tens or hundreds of potential moderators. In this setting, it becomes
necessary to use the observed data to select a simpler model for effect moderation and then make valid statistical
inference. We propose a two-stage procedure to solve this problem that leverages recent advances in post-selective
inference using randomization. We will discuss asymptotic validity of the conditional selective inference procedure
and the importance of randomization. Simulation studies verify the asymptotic results. We end with an analysis of an
MRT for promoting physical activity in cardiac rehabilitation to demonstrate the utility of the method.
.

Speaker Bio:

Walter Dempsey is an Assistant Professor in the
Department of Biostatistics, Assistant Professor of Data
Science at the Michigan Institute of Data Science
(MIDAS), and an Assistant Research Professor in the
d3lab located in the Institute of Social Research at the
University of Michigan. His research focuses on Statistical
Methods for Digital and Mobile Health. Specifically, his
current work involves three complementary research
themes: (1) experimental design and data analytic
methods to inform multi-stage decision making in
health; (2) statistical modeling of complex longitudinal
and survival data; and (3) statistical modeling of complex
relational structures such as interaction networks.