Intensive Longitudinal Data Research Articles

First-interview response patterns of intensive longitudinal psychological and health data.

Self-report data are essential in health psychology research where an individual's perception is critical to understanding one's health and psychological status. Intensive data collection over time, including daily diary assessments, is necessary in understanding within- and between-person variability in health and psychological processes over time. An "initial elevation or latent decline" (IELD) effect, inherent of self-report data, is increasingly acknowledged in the social psychology literature, but awareness of this effect in health psychology research is lacking, particularly in studies that emphasize within- and between-person variability in self-reports. The IELD effect is a pattern in which responses tend to be more extreme at the initial interview relative to subsequent responses. This paper illustrates the impact of IELD in applications of mixed-effects models based on observational self-reports and concludes that researchers take such effects into account in data analysis or in the research designing phase to help mitigate such effects.

Assessing and Addressing Zero Inflation in Intensive Longitudinal Data

Assessing and Addressing Zero Inflation in Intensive Longitudinal Data

Assessment of fit of the time-varying dynamic partial credit model using the posterior predictive model checking method.

Several new models based on item response theory have recently been suggested to analyse intensive longitudinal data. One of these new models is the time-varying dynamic partial credit model (TV-DPCM; Castro-Alvarez etal., Multivariate Behavioral Research, 2023, 1), which is a combination of the partial credit model and the time-varying autoregressive model. The model allows the study of the psychometric properties of the items and the modelling of nonlinear trends at the latent state level. However, there is a severe lack of tools to assess the fit of the TV-DPCM. In this paper, we propose and develop several test statistics and discrepancy measures based on the posterior predictive model checking (PPMC) method (PPMC; Rubin, The Annals of Statistics, 1984, 12, 1151) to assess the fit of the TV-DPCM. Simulated and empirical data are used to study the performance of and illustrate the effectiveness of the PPMC method.

Dynamic Structural Equation Models with Missing Data: Data Requirements on N and T

Dynamic structural equation modeling (DSEM) is a useful technique for analyzing intensive longitudinal data. A challenge of applying DSEM is the missing data problem. The impact of missing data on DSEM, especially on widely applied DSEM such as the two-level vector autoregressive (VAR) cross-lagged models, however, is understudied. To fill the research gap, we evaluated how well the fixed effects and variance parameters in two-level bivariate VAR models are recovered under different missingness percentages, sample sizes, the number of time points, and heterogeneity in missingness distributions through two simulation studies. To facilitate the use of DSEM under customized data and model scenarios (different from those in our simulations), we provided illustrative examples of how to conduct Monte Carlo simulations in Mplus to determine whether a data configuration is sufficient to obtain accurate and precise results from a specific DSEM.

Mediation Analyses of Intensive Longitudinal Data with Dynamic Structural Equation Modeling

Currently, dynamic structural equation modeling (DSEM) and residual DSEM (RDSEM) are commonly used in testing intensive longitudinal data (ILD). Researchers are interested in ILD mediation models, but their analyses are challenging. The present paper mathematically derived, empirically compared, and step-by-step demonstrated three types (i.e., 1-1-1, 2-1-1, and 2-2-1) of intensive longitudinal mediation (ILM) analyses based on DSEM and RDSEM models. Specifically, each ILM model was demonstrated with a simulated example and illustrated with the corresponding annotated Mplus codes. We compared two types of detrending methods in mediation analyses and showed that RDSEM was superior to DSEM because the latter included the time tj variable as a Level 1 predictor. Lastly, we extended ILM analyses based on DSEM and RDSEM to multilevel autoregressive mediation models, cross-classified DSEM, and intensive longitudinal moderated mediation models.

Speech Features as Predictors of Momentary Depression Severity in Patients With Depressive Disorder Undergoing Sleep Deprivation Therapy: Ambulatory Assessment Pilot Study.

The use of mobile devices to continuously monitor objectively extracted parameters of depressive symptomatology is seen as an important step in the understanding and prevention of upcoming depressive episodes. Speech features such as pitch variability, speech pauses, and speech rate are promising indicators, but empirical evidence is limited, given the variability of study designs. Previous research studies have found different speech patterns when comparing single speech recordings between patients and healthy controls, but only a few studies have used repeated assessments to compare depressive and nondepressive episodes within the same patient. To our knowledge, no study has used a series of measurements within patients with depression (eg, intensive longitudinal data) to model the dynamic ebb and flow of subjectively reported depression and concomitant speech samples. However, such data are indispensable for detecting and ultimately preventing upcoming episodes. In this study, we captured voice samples and momentary affect ratings over the course of 3 weeks in a sample of patients (N=30) with an acute depressive episode receiving stationary care. Patients underwent sleep deprivation therapy, a chronotherapeutic intervention that can rapidly improve depression symptomatology. We hypothesized that within-person variability in depressive and affective momentary states would be reflected in the following 3 speech features: pitch variability, speech pauses, and speech rate. We parametrized them using the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) from open-source Speech and Music Interpretation by Large-Space Extraction (openSMILE; audEERING GmbH) and extracted them from a transcript. We analyzed the speech features along with self-reported momentary affect ratings, using multilevel linear regression analysis. We analyzed an average of 32 (SD 19.83) assessments per patient. Analyses revealed that pitch variability, speech pauses, and speech rate were associated with depression severity, positive affect, valence, and energetic arousal; furthermore, speech pauses and speech rate were associated with negative affect, and speech pauses were additionally associated with calmness. Specifically, pitch variability was negatively associated with improved momentary states (ie, lower pitch variability was linked to lower depression severity as well as higher positive affect, valence, and energetic arousal). Speech pauses were negatively associated with improved momentary states, whereas speech rate was positively associated with improved momentary states. Pitch variability, speech pauses, and speech rate are promising features for the development of clinical prediction technologies to improve patient care as well as timely diagnosis and monitoring of treatment response. Our research is a step forward on the path to developing an automated depression monitoring system, facilitating individually tailored treatments and increased patient empowerment.

Avoidance and fear day by day in social anxiety disorder

Objective Theories assert that avoidance maintains maladaptive anxiety over time, yet a clear prospective test of this effect in the day-by-day lives of people with social anxiety disorder (SAD) is lacking. Method We used intensive longitudinal data to test prospective relationships between social fear and social avoidance in 32 participants with SAD who reported on a total of 4256 time points. Results Results suggested that avoidance strongly predicted future anxiety, but only in a minority of people with SAD. Relationships between anxiety and avoidance varied considerably across individuals. Pre-registered tests found that the strength of autocorrelation for social fear is a good target for future testing of prediction of exposure response. Participants with lower autocorrelations were less likely to show between-session habituation. Conclusions Overall, results suggest avoidance maintains fear in SAD for at least some individuals, but also indicates considerable variability. Further intensive longitudinal data is needed to examine individuals with SAD across varying time courses.

Idiographic psychological networks based on intensive longitudinal data are increasingly employed in clinical practice. However, these models mainly focus on the associations among psychological variables and changes in these associations, whereas the underlying factors for those changes are not taken into account. The factors contributing to change can be studied with moderation analyses, but although such analyses are standard in

Idiographic psychological networks based on intensive longitudinal data are increasingly employed in clinical practice. However, these models mainly focus on the associations among psychological variables and changes in these associations, whereas the underlying factors for those changes are not taken into account. The factors contributing to change can be studied with moderation analyses, but although such analyses are standard in clinical research, they are hardly applied in the domain of idiographic networks. Therefore, we implement the fixed moderated time series model to study how networks change depending on context factors. Fixed moderated time series analysis is a vector autoregressive based model, in which all parameters of the model can be moderated, including the innovation structure. As the model is based on the state space framework, it can also directly estimate changes in the mean levels of the variables in the network. With two empirical examples, we demonstrate how the fixed moderated time series model can reveal changing network structures. We show that this idiographic moderation approach not only provides a new way to look at what parameters in a network change over time, but also offers tools to see which factors are associated with the change.

Supplemental Material for Compliance and Response Consistency in a Lengthy Intensive Longitudinal Data Protocol

Supplemental Material for Compliance and Response Consistency in a Lengthy Intensive Longitudinal Data Protocol

System Identification of User Engagement in mHealth Behavioral Interventions

Digital behavior change interventions (DBCIs) such as “just-in-time” adaptive interventions (JITAIs) have demonstrated efficacy for increasing physical activity behavior. However, the effectiveness of these interventions is heavily dependent upon user engagement. Despite the inherent dynamic nature of engagement, as it varies over time based on an individual’s changing environment, context, and psychological state, the current understanding of engagement primarily comes from static snapshots of the behavior. The availability of intensive longitudinal data from JITAIs provides a unique opportunity to build and test dynamic models of behavior change from a process systems lens, relying on prediction-error methods from system identification. However, data missingness is a significant practical consideration in this process. Therefore, in this work we address missingness using a Bayesian imputation approach, which we evaluate using data from the HeartSteps II JITAI. Ultimately, the methods presented support the discovery of key factors that impact engagement behavior over time and can play an important role in the development of large-scale personalized interventions.

Curb the spread: Leveraging intensive longitudinal data to unravel within- and between-person processes in adherence to nonpharmaceutical interventions during COVID-19.

Adhering to behavioral recommendations and nonpharmaceutical interventions (NPIs) is a key to control COVID-19 infection rates. However, rates have decreased globally, and potentially modifiable determinants of ongoing adherence and their interaction with social and physical momentary environments are still poorly understood. Here, we comprehensively examine within-person variations and between-person differences in known behavioral determinants (capability and motivation), as well as the moderating role of situational variable environmental factors (opportunity) in predicting adherence to hygiene and social distancing behaviors. Ecological momentary assessment study over 6 months with monthly assessment bouts (4 days each and five daily assessments) in 623 German adults. Repeated daily assessments of capability, opportunity, motivation, and behavior (COM-B) model factors. Bayesian multilevel logistic regression models were estimated to examine main effects of COM-B factors and moderating effects of momentary environmental factors. Momentary adherence to NPIs was predicted by within-person changes in COM-B factors (motivation: intentions, goal conflict, and control beliefs; opportunities: regulations and norms). Between-person differences in capabilities (habit strength) and motivation (intentions and control beliefs) predicted adherence across situations. Situation-specific environmental factors moderated the motivation-behavior association (regulation measures increased; goal conflict and nonadherent others decreased the association). Individual momentary (within-person) and stable (between-person) motivation indicators predicted adherence. However, situational environmental factors such as regulations or norms have strong main effects and moderate the motivation-behavior translation. These findings have policy implications, supporting recent claims to not rely on the narrative of "personal responsibility," but instead combine health education measures to increase individual motivation with consistent regulation. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Dynamic Structural Equation Models: Promising Yet Concerning

Dynamic Structural Equation Model (DSEM) is a powerful statistical modeling approach that has recently gained popularity among researchers studying intensive longitudinal data. Despite its exciting potential, the stability and replicability of DSEM is yet to be closely examined. This study empirically investigates DSEM using recently published data to explore its strengths and potential limitations. The results show that while some of its parameter estimates are stable, others are characterized by substantial variation as a function of seemingly innocuous initial model estimation conditions. Indeed, some parameters fluctuate between significance and non-significance for the same model estimated using the same data. The instability of DSEM estimates poses a serious threat to the internal and external validity of conclusions drawn from its analyses, challenging the reproducibility of findings from applied research. Given the recent focus on the replication crisis in psychology, it is critical to address these issues as the popularity of DSEM in psychological research continues to rise. Several potential solutions are investigated to address this problem and recommendations of best practice are offered to applied researchers who plan to use DSEM in intensive longitudinal data analysis. KEYWORDS: Dynamic Structural Equation Model; Bayesian; Robust Estimation; Intensive Longitudinal Data

From cross-lagged effects to feedback effects: Further insights into the estimation and interpretation of bidirectional relations.

Bidirectional relations have long been of interest in psychology and other social behavioral sciences. In recent years, the widespread use of intensive longitudinal data has provided new opportunities to examine dynamic bidirectional relations between variables. However, most previous studies have focused on the effect of one variable on the other (i.e., cross-lagged effects) rather than the overall effect representing the dynamic interplay between two variables (i.e., feedback effects), which we believe may be due to a lack of relevant methodological guidance. To quantify bidirectional relations as a whole, this study attempted to provide guidance for the estimation and interpretation of feedback effects based on dynamic structural equation models. First, we illustrated the estimation procedure for the average and person-specific feedback effects. Then, to facilitate the interpretation of feedback effects, we established an empirical benchmark by quantitatively synthesizing the results of relevant empirical studies. Finally, we used a set of empirical data to demonstrate how feedback effects can help (a) test theories based on bidirectional relations and (b) reveal correlates of individual differences in bidirectional relations. We also discussed the broad application prospects of feedback effects from a dynamic systems perspective. This study provides guidance for applied researchers interested in further examining feedback effects in bidirectional relations, and the shift from focusing on cross-lagged effects only to a comprehensive consideration of feedback effects may provide new insights into the study of bidirectional relations.

Introduction to the Special Issue: Novel Insights into the Externalizing Psychopathology Spectrum in Childhood and Adolescence from Intensive Longitudinal Data.

Externalizing psychopathology is highly prevalent in children and adolescents. Yet, current understanding of the externalizing psychopathology spectrum is predominantly founded on cross-sectional and conventional longitudinal designs. Compared to these designs, intensive longitudinal data have greater ecological validity and provide insight into within-person fluctuations and short-term developmental dynamics. In this Special Issue, we bring together a selection of 10 innovative and original empirical articles to demonstrate the benefits of intensive longitudinal data for understanding the development of the externalizing psychopathology spectrum during childhood and adolescence, as well as one thoughtful commentary from leaders in the externalizing psychopathology field. In this Introduction to the Special Issue, we describe the articles included in this Special Issue in relation to study designs, timescales, samples, and statistical modeling techniques. We conclude by considering the implications of intensive longitudinal data for informing and enhancing our understanding of externalizing psychopathology with child and adolescent samples, as well as critical future research directions.

Supplemental Material for Unlocking Nonlinear Dynamics and Multistability From Intensive Longitudinal Data: A Novel Method

Supplemental Material for Unlocking Nonlinear Dynamics and Multistability From Intensive Longitudinal Data: A Novel Method

An Intensive time series investigation of the relationships across eating disorder-specific fear responses and behavior urges in partially remitted anorexia nervosa

Anorexia nervosa (AN) is a serious and persistent psychiatric illness. Many individuals with AN cycle between stages of remission (i.e., relapse), with research documenting that cognitive remission generally lags behind nutritional/weight restoration. Yet, little is known about which mechanisms promote movement from partial remission in AN (defined as nutritional, but not cognitive, recovery) to full remission. Fear-based processes, including avoidance and approach behaviors, likely contribute to the persistence of cognitive-behavioral AN symptoms after nutritional restoration. The current study used intensive longitudinal data to characterize these processes during partial remission (N = 41 participants with partially remitted AN; 4306 total observations). We aimed to a) characterize frequency of fear-based processes in real-time, b) investigate associations across fear-based processes and behavioral urges, and c) test if real-time associations among symptoms differed across commonly feared stimuli (e.g., food, social situations). On average, participants endorsed moderate fear and avoidance, with weight-gain fears rated higher than other feared stimuli. Momentary fear, avoidance, approach, and distress were all positively associated with AN behavior urges at one time-point and prospectively. Central symptoms and symptom connections differed across models with different feared stimuli. These findings provide empirical support for the theorized fear-avoidance-urge cycle in AN, which may contribute to the persistence of eating pathology during partial remission. Fear approach may be associated with temporary increases in urges, which should be considered during treatment. Future research should explore these associations in large, heterogeneous samples, and test the effectiveness of exposure-based interventions during partial remission.

A novel approach for constructing personalized networks from longitudinal perceived causal relations

Personalized networks of psychological symptoms aim to advance therapy by identifying treatment targets for specific patients. Statistical relations in such networks can be estimated from intensive longitudinal data, but their causal interpretation is limited by strong statistical assumptions. An alternative is to create networks from patient perceptions, which comes with other limitations such as retrospective bias. We introduce the Longitudinal Perceived Causal Problem Networks (L-PECAN) approach to address both these concerns. 20 participants screening positive for depression completed 4 weeks day of brief daily assessments of perceived symptom interactions. Quality criteria of this new method are introduced, answering questions such as “Which symptoms should be included in networks?”, “How many datapoints need to be collected to achieve stable networks?”, and “Does the network change over time?”. Accordingly, about 40% of respondents achieved stable networks and only few respondents exhibited network structure that changed during the assessment period. The method was time-efficient (on average 7.4 min per day), and well received. Overall, L-PECAN addresses several of the prevailing issues found in statistical networks and therefore provides a clinically meaningful method for personalization.

Investigating Moderation Effects at the Within-Person Level Using Intensive Longitudinal Data: A Two-Level Dynamic Structural Equation Modelling Approach in Mplus

Recent technological advances have provided new opportunities for the collection of intensive longitudinal data. Using methods such as dynamic structural equation modeling, these data can provide new insights into moment-to-moment dynamics of psychological and behavioral processes. In intensive longitudinal data (t > 20), researchers often have theories that imply that factors that change from moment to moment within individuals act as moderators. For instance, a person’s level of sleep deprivation may affect how much an external stressor affects mood. Here, we describe how researchers can implement, test, and interpret dynamically changing within-person moderation effects using two-level dynamic structural equation modeling as implemented in the structural equation modeling software Mplus. We illustrate the analysis of within-person moderation effects using an empirical example investigating whether changes in spending time online using social media affect the moment-to-moment effect of loneliness on depressive symptoms, and highlight avenues for future methodological development. We provide annotated Mplus code, enabling researchers to better isolate, estimate, and interpret the complexities of within-person interaction effects.

Need Fulfillment During Intergroup Contact: Three Experience Sampling Studies.

One challenge of modern intergroup contact research has been the question of when and why an interaction is perceived as positive and improves intergroup relations. We propose to consider the perceived fulfillment of the situationally most relevant need. We conducted three intensive longitudinal studies with recent migrants to capture their interactions with the majority out-group (Nmeasurements = 10,297; Nparticipants = 207). The situational need fulfillment mechanism is consistently a strong predictor of perceived interaction quality and positive out-group attitudes following intergroup interactions. The model is specific to out-group contact, robust to various need types, and works at least as well as Allport's contact conditions. As one of the first studies to test intergroup contact theory using intensive longitudinal data, we offer insight into the mechanisms of positive intergroup contact during real-life interactions and find situational motivations to be a key building block for understanding and addressing positive intergroup interactions.Public significance statement: In this article, we provide evidence that the fulfillment of situational needs during real-life intergroup contacts meaningfully predicts perceived interaction quality and positive outgroup attitudes. Methodologically, this offers a testament to the emerging practice of capturing real-life interactions using intensive longitudinal data. Theoretically, our results give weight to motivational fulfillment as a flexible and effective mechanism for understanding positive intergroup contact.

College Students' Day-to-Day Maladaptive Drinking Responses to Stress Severity and Stressor-Related Guilt and Anger.

Stress is a common part of college students' daily lives that may influence their physical activity (PA) and alcohol use. Understanding features of daily stress processes that predict health behaviors could help identify targets for just-in-time interventions. This study used intensive longitudinal data to examine whether prior day stress processes predict current day PA or alcohol use. Participants (N=58, Mage=20.5, 59% women, 70% White) were 18-to-25-year-old students who engaged in binge drinking at least twice monthly and used cannabis or tobacco in the past year. They wore activity (activPAL4) and alcohol (Secure Continuous Remote Alcohol Monitor) monitors for 11 days to assess daily PA (e.g., step counts) and alcohol use (e.g., drinking day), and completed daily surveys about yesterday's stress, including number of stressors (i.e., frequency), stressor intensity (i.e., severity), and frequency of affective states (e.g., guilt). Multilevel models examined prior day stress predicting current day PA or alcohol use. Participants had higher odds of current day drinking (odds ratio=1.21) and greater area under the curve (B=0.08) when they experienced greater than usual stress severity the prior day. Participants had higher current day peak transdermal alcohol concentration (B=0.12) and area under the curve (B=0.11) when they more frequently experienced guilt due to stressors the prior day. College students' unhealthy response of increasing alcohol use due to stress could adversely impact health outcomes. There is a critical need for interventions addressing students' ability to effectively manage and respond to the stress-inducing, daily demands of student life.