Missed Beeps and Missing Data

Abstract

Experience sampling research measures people’s thoughts, feelings, and actions in their everyday lives by repeatedly administering brief questionnaires throughout the day. Nonresponse—failing to respond to these daily life questionnaires—has been a vexing source of missing data. The present research examined person-level, day-level, and signal-level predictors of nonresponse. We analyzed data from a sample of 450 young adults who were signaled 8 times a day for 7 days. At the person level, nonresponse was higher for men and for people high in positive schizotypy, depressive symptoms, and hypomania. At the day level, nonresponse increased over the first few days of the study and then declined toward the end. At the signal level, time of day strongly predicted nonresponse. Lagged signal-level analyses examined how emotions and experiences at a prior signal prospectively predicted the likelihood of ignoring the next signal. Only one variable—feelings of enthusiasm—had a significant lagged effect, which suggests that within-day experiences are not major sources of nonresponse. For the most part, the day of the study and the time of day had the most salient effects. Understanding the predictors of missing data allows researchers to implement methods to increase compliance and to handle missing data more effectively by including predictors of nonresponse.

Real-time subjective assessment of psychological stress: Associations with objectively-measured physical activity levels

“…This compliance rate is similar to that found in similarly structured EMA studies of mood and affect (e.g., Silvia, Kwapil, Eddington, & Brown, 2013). Nonresponse to individual prompts was significantly more likely for women, non-Hispanic Blacks, and for people with higher physical activity levels.…”

“…Sokolovsky et al (2014) discuss the possibility that a causal relationship between EMA prompt response and the subject under study can lead to error and possibly even spurious results. Reassuringly, Silvia et al (2013) find that within-day variation in mood and experiences do not have a strong effect on prompt-level compliance in a similarly structured EMA study. Person-level and situational variables (such as time of day) are much stronger predictors of EMA non-response.…”

Negative affective stress reactivity: The dampening effect of snacking

“…Of the eligible sample (n = 382), 113 participants (30%) dropped out and 269 participants (70%) completed the study (Figure 1). Missings in this study occurred at beep level, which is a known phenomenon in ESM research (Silvia, Kwapil, Eddington, & Brown, 2013). Participants were instructed to complete their reports immediately after the beep, to minimize memory distortion.…”

Everyday creativity in daily life: An experience-sampling study of “little c” creativity.

“…For example, people could choose to get survey calls between 8 a.m. to 8 p.m., 10 a.m. to 10 p.m., 1 p.m. to 1 a.m., or any other convenient 12-hr window. Because some college students keep eccentric hours, allowing personalized survey windows ensured that the surveys arrived during the waking hours, thus reducing missing data (Silvia, Kwapil, Eddington, & Brown, 2013). An interactive voice response (IVR) system, running Telesage's SmartQ (Telesage, 2009), administered the automated surveys.…”