Open AccessPatterns of Missing Data With Ecological Momentary Assessment Among People Who Use Drugs: Feasibility Study Using Pilot Study Data
Author(s) -
Kelly L. Markowski,
Jeffrey A. Smith,
G. Robin Gauthier,
Sela R. Harcey
Publication year - 2021
Publication title -
jmir formative research
Language(s) - English
Resource type - Journals
ISSN - 2561-326X
DOI - 10.2196/31421
Subject(s) - missing data , phone , relative risk , morning , medicine , feeling , data collection , demography , psychology , confidence interval , statistics , social psychology , mathematics , philosophy , linguistics , sociology
Background Ecological momentary assessment (EMA) is a set of research methods that capture events, feelings, and behaviors as they unfold in their real-world setting. Capturing data in the moment reduces important sources of measurement error but also generates challenges for noncompliance (ie, missing data). To date, EMA research has only examined the overall rates of noncompliance. Objective In this study, we identify four types of noncompliance among people who use drugs and aim to examine the factors associated with the most common types. Methods Data were obtained from a recent pilot study of 28 Nebraskan people who use drugs who answered EMA questions for 2 weeks. We examined questions that were not answered because they were skipped , they expired , the phone was switched off , or the phone died after receiving them. Results We found that the phone being switched off and questions expiring comprised 93.34% (1739/1863 missing question-instances) of our missing data. Generalized structural equation model results show that participant-level factors, including age (relative risk ratio [RRR]=0.93; P =.005), gender (RRR=0.08; P =.006), homelessness (RRR=3.80; P =.04), personal device ownership (RRR=0.14; P =.008), and network size (RRR=0.57; P =.001), are important for predicting off missingness, whereas only question-level factors, including time of day (ie, morning compared with afternoon, RRR=0.55; P <.001) and day of week (ie, Tuesday-Saturday compared with Sunday, RRR=0.70, P =.02; RRR=0.64, P =.005; RRR=0.58, P =.001; RRR=0.55, P <.001; and RRR=0.66, P =.008, respectively) are important for predicting expired missingness. The week of study is important for both (ie, week 2 compared with week 1, RRR=1.21, P =.03, for off missingness and RRR=1.98, P <.001, for expired missingness). Conclusions We suggest a three-pronged strategy to preempt missing EMA data with high-risk populations: first, provide additional resources for participants likely to experience phone charging problems (eg, people experiencing homelessness); second, ask questions when participants are not likely to experience competing demands (eg, morning); and third, incentivize continued compliance as the study progresses. Attending to these issues can help researchers ensure maximal data quality.