Latent Interaction Model Research Articles

Attitude, Habit Strength, and the Relationship Between Intention and Leisure-Time Physical Activity Behavior Among College Students

ABSTRACT According to the dual-process theories, many scholars proposed that physical activity behavior tends to be governed by an interplay of intentional planning and habitual action. The major purpose of this study was to determine the moderation effects of habit strength on the relationship between leisure time moderate-to-vigorous physical activity (MVPA) intention and behavior and the impacts of cognitive and affective attitude on PA habit strength, utilizing a latent interaction modeling approach. A total of 1803 undergraduate students completed this study. All variables were measured using validated self-report questionnaires. Structural equation modeling and Hayes’ PROCESS program (model 1) were conducted to address the research questions. Habit strength significantly and positively moderated the effects of intention on leisure time MVPA behavior (β = .08, p < .01). The association between intention and PA behavior became stronger as habit strength increased. Affective attitude positively and significantly influenced habit strength (β = .71, p < .01). The effect of cognitive attitude on habit strength was significant and negative with a small effect size (β = –.08, p < .01). Findings indicated that habit strength positively moderated the relationship between PA intention and behavior, suggesting that stronger habit strength may amplify the association between PA intention and actual PA behavior. Affective attitude toward PA significantly influenced habit strength, whereas cognitive attitude exhibited minimal negative impact on habit strength. These findings contribute to our understanding of the interaction effects between deliberative and automatic processes in regulating PA behavior, as well as the nuanced relationship between attitude and habit development.

Supplemental Material for Normality Assumption in Latent Interaction Models

Supplemental Material for Normality Assumption in Latent Interaction Models

Cognitive Reappraisal Moderates the Longitudinal Relationship between Adolescents' Peer Victimization and Self-Esteem. A Latent Interaction Model.

Poor self-esteem relates closely to youth maladjustment and appears to be predicted by peer victimization experiences. However, not all peer victimized adolescents face the same risk for self-esteem erosion over time. Drawing upon the Bi-Dimensional Framework for resilience and extant research, the present study examined the potential moderating role of cognitive reappraisal in the prospective relationship from peer victimization to self-esteem. To increase precision of findings the long-term impact of self-esteem on peer victimization was also tested. Self-reported data were collected from 285 early adolescents (Mage = 10.53 years, SD = 0.16; 54.0% girls) at two waves, spaced 1-year. Latent moderated structural equation analysis showed that peer victimization was negatively related to later self-esteem, but only for youth displaying low levels of cognitive reappraisal. For adolescents with high levels of cognitive reappraising, peer victimization was not found to predict any changes in self-esteem over time. The long-term impact of self-esteem on peer victimization was not supported. Overall the present study suggests that enhancing cognitive reappraisal could be a promising avenue for lowering risk for poor self-esteem in young individuals experiencing peer victimization.

Covariate-Informed Latent Interaction Models: Addressing Geographic & Taxonomic Bias in Predicting Bird–Plant Interactions

Reductions in natural habitats urge that we better understand species’ interconnection and how biological communities respond to environmental changes. However, ecological studies of species’ interactions are limited by their geographic and taxonomic focus which can distort our understanding of interaction dynamics. We focus on bird–plant interactions that refer to situations of potential fruit consumption and seed dispersal. We develop an approach for predicting species’ interactions that accounts for errors in the recorded interaction networks, addresses the geographic and taxonomic biases of existing studies, is based on latent factors to increase flexibility and borrow information across species, incorporates covariates in a flexible manner to inform the latent factors, and uses a meta-analysis dataset from 85 individual studies. We focus on interactions among 232 birds and 511 plants in the Atlantic Forest, and identify 5% of pairs of species with an unrecorded interaction, but posterior probability that the interaction is possible over 80%. Finally, we develop a permutation-based variable importance procedure for latent factor network models and identify that a bird’s body mass and a plant’s fruit diameter are important in driving the presence of species interactions, with a multiplicative relationship that exhibits both a thresholding and a matching behavior. Supplementary materials for this article are available online.

Parceling Ordinal Items in Latent Interaction Modeling

"Parceling Ordinal Items in Latent Interaction Modeling." Multivariate Behavioral Research, ahead-of-print(ahead-of-print), pp. 1–2

Simple view of reading among Slovenian English foreign language learners: A latent interaction modeling approach

An estimated 700 million people learn how to read in English as a foreign language (EFL). This highlights the need to better understand the components influencing EFL reading. We tested to what degree EFL decoding and linguistic comprehension influenced EFL reading comprehension within the realm of three variants of the Simple View of Reading (SVR) model – the multiplicative, the additive, and the combined variants. Moreover, we estimated the extent to which first language reading contributed to EFL reading comprehension over and above EFL components. Participants were 690 Slovenian seventh graders (Mage = 12.76 years; SD = 0.43). Utilizing a latent interaction model, results supported the SVR additive variant. EFL decoding was a stronger contributor than EFL linguistic comprehension. First language reading did not seem to influence EFL reading comprehension. Our findings suggest that EFL instruction should focus on practicing EFL decoding and linguistic comprehension independently.

Latent Logistic Interaction Modeling: A Simulation and Empirical Illustration of Type D Personality

ABSTRACT This study focuses on three popular methods to model interactions between two constructs containing measurement error in predicting an observed binary outcome: logistic regression using (1) observed scores, (2) factor scores, and (3) Structural Equation Modeling (SEM). It is still unclear how they compare with respect to bias and precision in the estimated interaction when item scores underlying the interaction constructs are skewed and ordinal. In this article, we investigated this issue using both a Monte Carlo simulation and an empirical illustration of the effect of Type D personality on cardiac events. Our results indicated that the logistic regression using SEM performed best in terms of bias and confidence interval coverage, especially at sample sizes of 500 or larger. Although for most methods bias increased when item scores were skewed and ordinal, SEM produced relatively unbiased interaction effect estimates when items were modeled as ordered categorical.

Violation of Distributional Assumptions in Latent Interaction Models

Violating the distributional assumptions of latent interaction models can lead to biased estimates and invalid inference. However, no statistical procedure is readily available to verify whether these assumptions hold. We develop several specification tests contrasting consistent latent interaction estimators—which are robust to violations of distributional assumptions (i.e., Extended Unconstrained Indicator Approach and Model-Implied Instrumental Variables method)—to an efficient estimator (i.e., Latent Moderated Structural Equations), which is inconsistent under non-normally distributed linear latent variables. We compare these estimators under a variety of conditions. The robust Hausman test we propose works well in identifying misspecifications due to violations of distributional assumptions of the latent variables. Moreover, our results indicate that the Latent Moderated Structural Equations method is severely bias under non-ideal conditions. Thus, it should not be used as the default approach and its results should always be compared to consistent estimators that are robust to distributional assumptions.

Comparing estimators for latent interaction models under structural and distributional misspecifications.

Estimation methods for structural equation models with interactions of latent variables were compared in several studies. Yet none of these studies examined models that were structurally misspecified. Here, the model-implied instrumental variable 2-stage least square estimator (MIIV-2SLS; Bollen, 1995; Bollen & Paxton, 1998), the 2-stage method of moments estimator (2SMM; Wall & Amemiya, 2003), the nonlinear structural equation mixture model approach (NSEMM; Kelava, Nagengast, & Brandt, 2014), and the unconstrained product indicator approach (UPI; Marsh, Wen, & Hau, 2004) were compared in a Monte Carlo simulation. The design included structural misspecifications in the measurement model involving the scaling indicator or not, the size of the misspecification, normal and nonnormal data, the indicators' reliability, and sample size. For the structural misspecifications that did not involve the scaling indicator, we found that MIIV-2SLS' parameter estimates were less biased compared with 2SMM, NSEMM, and UPI. If the reliability was high, the RMSE for all approaches was very similar; for low reliability, MIIV-2SLS' RMSE became larger compared with the other approaches. If the structural misspecification involved the scaling indicator, all estimators were seriously biased, with the largest bias for MIIV-2SLS. In most scenarios, this bias was more severe for the linear effects than for the interaction effect. The RMSE for conditions with misspecified scaling indicators was smallest for 2SMM, especially for low reliability scenarios, but the overall magnitude of bias was such that we cannot recommend any of the estimators in this situation. Our article showed the damage done when researchers omit cross-loadings of the scaling indicator and the importance of giving more attention to these indicators particularly if the indicators' reliability is low. It also showed that no one estimator is superior to the others across all conditions. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Latent Interaction Modeling with Planned Missing Data Designs

ABSTRACT Planned missing data (PMD) designs allow researchers to collect additional data under time constraints and to reduce participant burden, both of which can occur in social, behavioral, and educational research settings. The imposed missing data patterns, however, can hamper the efficiency of statistical models implemented to test hypotheses that are of interest to substantive researchers, including whether a treatment works the same for all students. Typically, PMD designs result in a modest power deficiency; however, this tenet has not been extended to latent interaction models. Such models are of increasing importance as researchers investigate moderated relationships involving continuous latent variables. Monte Carlo simulations were used to assess the efficacy of various latent interaction estimation methods under PMD designs.

Motivational Climate in Physical Education, Achievement Motivation, and Physical Activity: A Latent Interaction Model

Purpose: To assess if high school students’ leisure-time physical activity is predicted by their perception of the motivational climate, their perceived competence, and their achievement goals in physical education (PE) and if these variables interact with each other.Methods: A sample of 843 high school students completed self-reported questionnaires in the middle and at the end of the school year. The data were analyzed by structural equation modeling and latent moderated structural equations.Results: Leisure-time physical activity was positively predicted by students’ performance-approach goals and perceived competence in PE and by the interaction between their perceived competence and their adoption of mastery goals.Discussion/Conclusion: Only individual variables in PE were related to leisure-time physical activity. The significant interaction effect between students’ mastery goals and perceived competence in PE suggests that teachers need to foster students’ perceptions of competence. The authors therefore discuss the scope of the results with regard to pedagogical practices.

Automatic Bayesian Density Analysis

Making sense of a dataset in an automatic and unsupervised fashion is a challenging problem in statistics and AI. Classical approaches for exploratory data analysis are usually not flexible enough to deal with the uncertainty inherent to real-world data: they are often restricted to fixed latent interaction models and homogeneous likelihoods; they are sensitive to missing, corrupt and anomalous data; moreover, their expressiveness generally comes at the price of intractable inference. As a result, supervision from statisticians is usually needed to find the right model for the data. However, since domain experts are not necessarily also experts in statistics, we propose Automatic Bayesian Density Analysis (ABDA) to make exploratory data analysis accessible at large. Specifically, ABDA allows for automatic and efficient missing value estimation, statistical data type and likelihood discovery, anomaly detection and dependency structure mining, on top of providing accurate density estimation. Extensive empirical evidence shows that ABDA is a suitable tool for automatic exploratory analysis of mixed continuous and discrete tabular data.

What types of racial messages protect Asian American adolescents from discrimination? A latent interaction model.

In this brief report, the authors investigate how different types of parental racial-ethnic socialization messages (i.e., cultural socialization/pluralism, promotion of mistrust, and preparation for racial bias) moderate the relationship between racial discrimination and psychological distress in a sample of 187 Asian American adolescents. Results indicated a significant positive relationship between racial discrimination and psychological distress. Cultural socialization/pluralism and promotion of mistrust also moderated the racial discrimination and psychological distress link. Specifically, for adolescents reporting low frequencies of cultural socialization/pluralism messages, discrimination was positively associated with psychological distress, suggesting cultural socialization/pluralism messages may be a protective factor. Discrimination was also positively associated with psychological distress for adolescents reporting high frequencies of promotion of mistrust, suggesting that promotion of mistrust may be a risk factor. Overall, the findings emphasize the important role that racial-ethnic socialization messages can have on psychological distress among Asian American adolescents who experience racial discrimination. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Moderating Effects of Community Social Capital on Depression in Later Years of Life: A Latent Interaction Model

ABSTRACTObjective: This study tested the stress-buffering model and examined the buffering role of community social capital on late-life depression.Methods: This study used the data from the second wave of National Social Life, Health, and Aging Project (NSHAP, 2010–2012). In the present study, a total of 2,362 older adults aged 65 and older (Mage = 74.5, SD = 6.69) were included. Latent moderated structural equations model was tested by comparing the main effect model and interaction model. Depression, stress, and community social capital were constructed as latent variables for the analyses.Results: The main effect model was acceptable: χ2 (df = 334) = 1596.4, p = .000; RMSEA = .04 (.038 - .042); CFI = .91; and SRMR = .05. And interaction model was significant (D = 35.0, p < .001). The latent constructs of stress (β = . 50, p < .001) and community social capital (β = −.14, p < .001) not only had a direct effect on depression, but their interaction was also significant (β = −.21, p < .01).). The group with a high level of social capital presented a relatively stable slope in the prediction of stress on depression, suggesting their resilience, while the group with a low level of community social capital demonstrated a steep slope, indicating heighten vulnerability to depression when faced with stress.Conclusions: The findings support the hypothesis of stress buffering model and identify the protective effects of community social capital on depression of older adults.Clinical Implications: Older adults with lower community social capital are particularly vulnerable to depression. The results highlight that practitioners and policymakers should pay more attention to finding ways to enhance community resources to improve older adults’ mental health.

The moderation of culturally normative coping strategies on Taiwanese adolescent peer victimization and psychological distress

The current study aimed to investigate the moderation effects of coping strategies on the association between perceived peer victimization and psychological distress including loneliness and depression. Applying the person-context fit developmental model, this research hypothesized that adaptive coping strategies, which are normative in Taiwan's culture (i.e., social support seeking), would buffer the link between peer victimization and psychological distress (i.e., depression and loneliness) in comparison with the culturally non-normative coping (i.e., problem-solving strategies). We also expected maladaptive coping strategies (i.e., internalizing strategies) would exacerbate the link between peer victimization and psychological distress. A latent interaction model was conducted with a sample of 730 Taiwanese adolescents attending one middle school. The results indicated that both support seeking strategies and problem-solving strategies buffered Taiwanese adolescents from loneliness and depression. Internalizing coping strategies placed Taiwanese adolescents at great risk of depression and loneliness. Support seeking strategies that are aligned with interdependent cultural contexts appeared to have greater protective effects than the culturally non-normative problem-solving strategies for adolescents who perceived high levels of victimization. The implications for prevention and intervention were discussed.

Supplemental Material for What Types of Racial Messages Protect Asian American Adolescents From Discrimination? A Latent Interaction Model

Supplemental Material for What Types of Racial Messages Protect Asian American Adolescents From Discrimination? A Latent Interaction Model

The role of social capital in the relationship between physical constraint and mental distress in older adults: a latent interaction model

ABSTRACTObjective: Building upon the widely known link between physical and mental health, the present study explored the buffering effects of social capital (indicated by social cohesion, social ties, and safety) in the relationship between physical constraint (indicated by chronic conditions and functional disability) and mental distress (indicated by symptoms of depression and anxiety).Method: Using data from 2,264 community-dwelling older adults in the National Social Life, Health, and Aging Project (NSHAP) Wave 2 (Mage = 74.51, SD = 6.67), a latent interaction model was tested. The model of mental distress, including both the main effect of physical constraint and social capital and their latent interaction, presented an excellent fit.Results: The latent constructs of physical constraint (β = .54, p < .001) and social capital (β = –.11, p < .01) not only had a direct effect on mental distress, but their interaction was also significant (β = –.26, p < .001). Subgroup analysis showed that the group with a low level of social capital had a heightened vulnerability to mental distress when faced with physical constraint, whereas the group with a high level of social capital demonstrated resilience.Conclusion: Findings call attention to ways to enhance older individuals' social capital in efforts to promote their health and well-being.

Peer Victimization and Depressive Symptoms Among Rural-to-Urban Migrant Children in China: The Protective Role of Resilience.

Peer victimization can have a profound effect on children’s wellbeing and is a known risk factor for depression in childhood. Migrant children experience peer victimization at higher rates than non-migrant peers; however, limited research has examined psychological factors that may serve to reduce depression risk for this group. In particular, no studies have yet investigated whether resilience, including personal characteristics, and a strong social support network, may moderate the relationship between peer victimization and depressive symptoms for migrant children. This study utilized a latent interaction model to examine the effect of resilience on the relationship between peer victimization and depressive symptoms among 721 rural-to-urban migrant children in Beijing, China. Results indicated that peer victimization was positively associated with depressive symptoms. Resilience was found to be a protective factor for depressive symptoms and also mitigated the effects of peer victimization on depressive symptoms. Exploratory analyses suggest that enrollment in private migrant schools may be linked with poorer psychosocial outcomes for Chinese migrant children. Strengthening the internal resilience and social supports for all migrant children may be an effective strategy to lower their risk for depression. Implications for intervention are discussed.

Belief incongruence and the intention–behavior gap in persons with at-risk alcohol use

IntroductionWhen intentions are expressed, e.g., when filling in a health questionnaire, people may have unrealistic beliefs towards behavior change resulting in strong intentions to change. These may fail to correspond to reality when the behavior actually should be performed. Belief incongruence was tested as a possible source of the intention–behavior gap. MethodsThe study sample consisted of 433 job agency clients with at-risk alcohol use (64% men, mean age=30.6 (SD=11.6) years). Behavioral, normative, and control beliefs, intention, and alcohol use were assessed at baseline and three months later. The influence of belief incongruence on the intention–behavior gap was examined using latent interaction models. ResultsThe gap between stated intentions and at-risk alcohol use three months later was larger when the according normative beliefs were incongruent (total effect: b=−0.44, p<0.05 for persons with congruent beliefs vs. b=−0.06, p>0.10 for persons with incongruent beliefs). When controlling for the mediating effect of changes in intentions, the association between belief incongruence and intention–behavior gap was attenuated (direct effect: b=−0.56, p<0.01 for persons with congruent beliefs vs. b=−0.28, p<0.05 for persons with incongruent beliefs). Neither behavioral belief incongruence nor control belief incongruence was significantly associated with the intention–behavior gap. ConclusionsNormative belief incongruence may contribute to the gap between intentions to adhere to recommended drinking limits and subsequent at-risk alcohol use. Focusing on the reduction of misperceptions about drinking norms could help to increase the proportion of persons who succeed in translating their intentions into behavior.

A Note on the Specification of Error Structures in Latent Interaction Models.

Latent interaction models have motivated a great deal of methodological research, mainly in the area of estimating such models. Product-indicator methods have been shown to be competitive with other methods of estimation in terms of parameter bias and standard error accuracy, and their continued popularity in empirical studies is due, in part, to their straightforward implementation and relative ease of estimation in mainstream structural equation modeling software. In recent years, the impact of different specifications of the mean structure of the structural model has been the focus of a fair amount of investigation in this area. Yet the effects of misspecification of the error structure of the observed variables implied by the model have not been investigated. In this study, the authors demonstrate algebraically the ramifications of misspecifying these error structures for the unconstrained product-indicator approach. Recommendations to practitioners based on these results are discussed.