Littérature scientifique sur le sujet « Random Intercept Cross Lagged Panel Model (RI-CLPM) »

Are feelings of not mattering an antecedent of depressive symptoms, a consequence, or both? Most investigations focus exclusively on feelings of not mattering as an antecedent of depressive symptoms. Our current study examines a vulnerability model, a complication model, and a reciprocal relations model according to a cross-lagged panel model (CLPM) and a random-intercept cross-lagged panel model (RI-CLPM). A sample of 197 community adults completed the General Mattering Scale (GMS), the Anti-Mattering Scale (AMS), and a depression measure at three time points (i.e., baseline, 3 weeks, and 6 weeks). GMS and AMS scores were associated robustly with depressive symptoms at each time point. Other results highlighted the need to distinguish levels of anti-mattering and mattering. CLPM analyses supported a reciprocal relations model of anti-mattering (assessed by the AMS) and depressive symptoms and a complication model linking mattering (assessed by the GMS) and depressive symptoms. The RI-CLPM analyses provided tentative support only for a complication model of anti-mattering and depressive symptoms. Our findings highlight the differences between measures of the mattering construct and the need to adopt a temporal perspective that considers key nuances and the interplay among feelings of mattering, feelings of not mattering, and depression.

Many longitudinal studies have investigated whether self–esteem predicts depressive symptoms (vulnerability model) or the other way around (scar model) in adolescents. The most common method of analysis has been the cross–lagged panel model (CLPM). The CLPM does not separate between–person effects from within–person effects, making it unclear whether the results from previous studies actually reflect the within–person effects or whether they reflect differences between people. We investigated the associations between self–esteem and depressive symptoms at the within–person level, using random intercept cross–lagged panel models (RI–CLPMs). To get an impression of the magnitude of possible differences between the RI–CLPM and the CLPM, we compared the results of both models. We used data from three longitudinal adolescent samples (age range: 7–18 years; study 1: N = 1948; study 2: N = 1455; study 3: N = 316). Intervals between the measurements were 1–1.5 years. Single–paper meta–analyses showed support for small within–person associations from self–esteem to depressive symptoms, but not the other way around, thus only providing some support for the vulnerability model. The cross–lagged associations in the aggregated RI–CLPM and CLPM showed similar effect sizes. Overall, our results show that over 1– to 1.5–year time intervals, low self–esteem may negatively influence depressive symptoms over time within adolescents, but only weakly so. © 2018 The Authors. European Journal of Personality published by John Wiley & Sons Ltd on behalf of European Association of Personality Psychology

This longitudinal study investigated transactional relationships between violent media use and attention-deficit/hyperactivity disorder (ADHD)–related behaviors among young children (ages 4-8 years). To investigate study hypotheses, we employed a random intercept cross-lagged panel model (RI-CLPM) using structural equation modeling with panel data from 890 children. Results provided evidence in support of a media selection process rather than media effects process, whereby an increase in a child’s ADHD-related behaviors predicted an increase in the child’s violent media use 1 year later. Results indicated that this longitudinal relationship was accounted for by within-child fluctuations over time rather than stable between-child differences. The findings highlight the importance of investigating transactional relationships as well as distinguishing between-person and within-person relationships.

Abstract. Student well-being is considered as both an enabling condition for positive learning outcomes and an essential educational outcome itself. Previous studies have investigated the relationship between student well-being and academic achievement cross-sectionally, leaving unclear the direction of causality. Employing 3 waves of data spaced 1 year apart, this longitudinal study used a random intercept cross-lagged panel model (RI-CLPM) to account for between-person effects and segregate within-person effects between positive and negative dimensions of student well-being and academic achievement. Participants were 404 secondary school students in Switzerland in grades 7–9. The RI-CLPMs suggested that over 1-year time intervals students’ academic achievement may positively influence positive dimensions of student well-being (i.e., positive attitudes toward school, enjoyment in school, positive academic self-concept) within secondary school students. Negative dimensions of student well-being (i.e., worries in school, physical complaints, and social problems) were not associated with academic achievement.

Abstract Objective Depression and chronic pain are major problems in American veterans, yet there is limited long-term research examining how they relate to one another in this population. This study examined the relationship between depressive symptoms and pain in U.S. veterans 50 years of age or older. Methods This study used data on veterans from the 2002–2016 waves of the Health and Retirement Study (n = 4,302), a large-scale observational study of Americans 50 years of age or older. Measures included a short form of the Center for Epidemiologic Studies Depression scale and two items assessing the presence and degree of pain. Analyses included random-intercept cross-lagged panel models (RI-CLPM). Results In the RI-CLPM, there were roughly equivalent cross-lagged effects between depressive symptoms and pain. There was also evidence that depressive symptoms and pain have a trait-like component and that these trait-like characteristics are associated. Conclusions These findings indicate that depressive symptoms and pain in veterans are stable characteristics in American veterans 50 years of age or older. There appear to be reciprocal effects between the two, whereby deviations in one’s typical depressive symptoms predict subsequent deviations in one’s pain level and vice versa; however, the size of these effects is very small. These findings suggest that clinicians should treat both depressive symptoms and pain, rather than assume that treatment benefits in one domain will lead to major benefits in another.

Abstract This study investigates the interplay between online and face-to-face (FtF) feedback on stress during an important life event. We present data on a two-month, six-wave longitudinal study of 468 Chilean adolescents across three important stages of a competitive national university selection test (Prueba de Selección Universitaria [PSU]) to assess longitudinal and reciprocal relationships. Random intercept cross-lagged panel models (RI-CLPM) showed that online feedback had a small effect in decreasing stress during the three short-termed waves, before and after the three main events of the test: test taking, test scores, and final selection. No intrapersonal effects were found for FtF feedback on stress, and vice versa. At the interpersonal level, only feedback variables were related. Results suggest that prosocial replies on social media may slightly help to downregulate stress from important life events at the intrapersonal level, an effect which appears to be short-lived (e.g., only a few days), rather than long-lived (e.g., three weeks).

Mixed findings in the literature on the effects of older adult employment on well-being and the reciprocal influence of well-being on employment suggest the need for more careful methodology in teasing out this relationship. Moreover, as previous research has shown that different domains of well-being relate to constructs differently, more nuanced definitions of well-being may be appropriate. The present study examined the longitudinal bidirectional associations of employment and different domains of well-being, controlling for stable within-person variables. The present study sampled older adults from the Midlife Development in the US study at three timepoints on employment status and well-being, specifically psychological, social, and subjective well-being. A Random-Intercept Cross-lagged Panel Model (RI-CLPM) approach was employed to determine the longitudinal bidirectional influence of employment and domains of well-being. Results showed that employment status was not associated with various well-being domains at a later time point. Results also showed that greater well-being, specifically in meaningfulness of society and personal growth, was associated with being employed at a later time point.

Objectives: This study aimed to examine the longitudinal relationship between two central concepts in aging research—self-perceptions of aging (SPA) and perceived control of life (COL). Method: The data came from three measurement points over a 9-year period in the Health and Retirement Study (HRS). A random intercepts cross-lagged panel model (RI-CLPM) was estimated. Results: The covariations between SPA and COL across 9 years were evident at both the between-person level and the within-person within-time level. The results revealed a reciprocal relationship between SPA and COL: Higher than usual negative SPA predicted within-person decreases in COL 4 years later, and lower than usual COL predicted future within-person increases in negative SPA. Furthermore, SPA were found to have a somewhat larger effect on COL than the corresponding influence of COL on SPA. Discussion: This study enriches the stereotype embodiment theory and the practice by documenting a reciprocal interrelationship between SPA and COL.

Abstract The purpose of this study is to examine if there are reciprocal effects between social network size and purpose in life among older adults using data from the National Health and Aging Trends Study. A second aim is to assess whether there are moderated effect of gender on this relationship. The sample included 1,485 male and 2,058 female adults 65 years and older. In order to examine the reciprocal effects between social network size and purpose in life over four time points (2017, 2018, 2019, and 2020), a random intercept cross-lagged model (Model 1) was computed. Then, two multiple group RI-CLPM analyses (Model 2 and 3) were computed in order to test moderation of gender on the relationship. Model 2 estimates the cross-lagged parameters freed and model 3 estimates the cross-lagged parameters constrained. The results indicated that Model 1 fit the data well, χ2(9) = 26.06, p = .002. The carry-over effects of social network and purpose in life were significant. The spill-over effect from wave 3 purpose in life on wave 4 social network was significant. The variance of the random intercepts were significant, indicating that there are stable, trait-like differences between social network and purpose in life. The results of the multiple group model revealed that there were no significant differences between the freed and constrained models, indicating that lagged effect for male and female appear to be same. Future research should explore if other factors like race or education show moderated effects.

For several decades, cross-lagged panel models (CLPM) have been the dominant statistical model in relationship research for investigating reciprocal associations between two (or more) constructs over time. However, recent methodological research has questioned the frequent usage of the CLPM because, amongst other things, the model commingles within-person associations with between-person associations, while most developmental research questions pertain to within-person processes. Furthermore, the model presumes that there are no third variables that confound the relationships between the longitudinally assessed variables. Therefore, the usage of alternative models such as the Random-Intercept Cross-Lagged Panel Model (RI-CLPM) or the Latent Curve Model with Structured Residuals (LCM-SR) has been suggested. These models separate between-person from within-person variation and they also control for time constant covariates. However, there might also be third variables that are not stable but rather change across time and that can confound the relationships between the variables studied in these models. In the present article, we explain the differences between the two types of confounders and investigate how they affect the parameter estimates of within-person models such as the RI-CLPM and the LCM-SR.

The present dissertation aims to improve our knowledge on the longitudinal development of Non-Suicidal Self-Injury (NSSI) and the role of interpersonal and intrapersonal risk factors associated with it. Non-Suicidal Self-injury (NSSI), defined as the direct and deliberate self-inflicted damage of body tissue without suicidal intent, is a serious public health concern worldwide (Kiekens et al., 2018). Adolescents are the most at-risk group, given that the transition into adolescence may represent a critical vulnerability period for the onset of NSSI behaviors (Lloyd-Richardson, 2008). This phenomenon requires attention not only because of its heavy impact in terms of public health and the high incidence within the population, but also for the consequences that engagement in NSSI entails. The long-term effects of self-injurious behavior can be destructive, with consequences for emotional and cognitive development (Baetens et al., 2011). NSSI is used as a maladaptive means of coping with intense emotions. Both interpersonal (e.g., social interaction with peers and family; Brausch & Gutierrez, 2010) and intrapersonal factors (e.g., emotion regulation, self-efficacy, and self-esteem; Baetens et al., 2011) can serve to initiate and maintain NSSI (Nock, 2009; Nock & Prinstein, 2004; Zetterqvist et al., 2013). In the last ten years, the attention given to this issue has become increasingly important. Most of the existing literature has examined this behavior (e.g., prevalence, risks factors) at the cross-sectional level, while few studies have explored the longitudinal development of NSSI, and the role played by interpersonal and intrapersonal factors at the longitudinal level. For these reasons, the general aim of the present dissertation is to analyze the longitudinal development of NSSI and the association with interpersonal and intrapersonal risk factors. Three empirical studies are presented. They cover three main issues: 1) a meta-analysis on the longitudinal development of NSSI; 2) the reciprocal associations between peer problems and NSSI; 3) the mediational role of Covid-19 related stress in the association between pre-existing vulnerabilities and NSSI. In the first study (Chapter 1), we presented a meta-analysis on the development of NSSI from childhood to young adulthood, using a Bayesian approach. The aim was to examine both the occurrence and the frequency of NSSI over time, considering all studies published up until November 2020. Subsequently, we examined the role of possible moderators, such as gender, mean age during the first wave of data collection, and number of months covered by the assessment. The results show the important role of gender (i.e., females) and age in the explanation of the expected proportion and mean changes of NSSI over time. Specifically, what emerges from the findings is how being female represents an important risk factor for the occurrence of this behavior. As for the frequency of this behavior, a higher percentage of females are associated with higher severity of NSSI, but it tends to decrease over time. The results show that mid-adolescence (i.e., 14/15 years) appears to be the period of highest risk for the occurrence of NSSI over time. Instead, over time, findings suggest that the frequency of this behavior is higher in adolescence, at a mean age of 15-16 years of age, and it decreases in late adolescence (e.g., Plener et al., 2015). In the second study (Chapter 2), we investigated the reciprocal associations between peer problems (e.g., peer victimization, friendship stress, and loneliness) and NSSI throughout adolescence, distinguishing between- and within-person effects. Participants were 866 adolescents (54.5% females; Mage = 13.12 years, SD = 0.78), who took part in six waves of data collection. Random Intercept Cross-Lagged Panel Models (RI-CLPM) were used to estimate within-person cross-lagged effects between each peer problem and NSSI from Grade 7 to 12. After accounting for between-person associations between peer problems and NSSI, results indicated that higher-than-usual levels of NSSI predicted higher-than-usual levels of adolescents’ own friendship stress, loneliness, and peer victimization at the subsequent time point. Yet, sensitivity analyses revealed that most of these effects were strongly attenuated and explained by within-person fluctuations in depressive symptoms. No within-person cross-lagged effects from peer problems to NSSI were found. In the third study (Chapter 3), we examined the role of Covid-19 related stress in the association between pre-existing vulnerabilities and the engagement in NSSI during the pandemic. Specifically, the study aimed to examine if adolescents with pre-existing vulnerabilities, including a prior history of NSSI, higher levels of internalizing symptoms, and poorer regulatory emotional self-efficacy, were more likely to show increases in NSSI across the pandemic period through higher levels of Covid-19 related stress. The analysis was conducted on 1061 adolescents (52.4% females; Mage = 15.49 years, SD = 0.76), enrolled in the 9th and 10th grade in Tuscany, Italy, who took part in two waves of data collection. Results showed that adolescents with pre-existing vulnerabilities were at higher risk of engaging in NSSI through the role of Covid-19 related stress. Specifically, adolescents with a prior history of NSSI, higher levels of anxious and depressive symptoms, and poorer regulatory emotional self-efficacy showed a higher level of Covid-19 related stress, which in turn it was associated with an increased risk of occurrence of NSSI. In the final chapter (Chapter 4), the results of the previous three studies have been discussed highlighting their contribution to the literature on the longitudinal development of NSSI, strengths and limitations, and the implications for future studies.