Stepwise Latent Class Models for Explaining Group-Level Outcomes Using Discrete Individual-Level Predictors

Explaining group-level outcomes from individual-level predictors requires aggregating the individual-level scores to the group level and correcting the group-level estimates for measurement errors in the aggregated scores. However, for discrete variables it is not clear how to perform the aggregation and correction. It is shown how stepwise latent class analysis can be used to do this. First, a latent class model is estimated in which the scores on a discrete individual-level predictor are used to construct group-level latent classes. Second, this latent class model is used to aggregate the individual-level predictor by assigning the groups to the latent classes. Third, a group-level analysis is performed in which the aggregated measures are related to the remaining group-level variables while correcting for the measurement error in the class assignments. This stepwise approach is introduced in a multilevel mediation model with a single individual-level mediator, and compared to existing methods in a simulation study. We also show how a mediation model with multiple group-level latent variables can be used with multiple individual-level mediators and this model is applied to explain team productivity (group level) as a function of job control (individual level), job satisfaction (individual level), and enriched job design (group level).     

Future Expectations Among Adolescents: A Latent Class Analysis

Future expectations have been important predictors of adolescent development and behavior. Its measurement, however, has largely focused on single dimensions and misses potentially important components. This analysis investigates whether an empirically-driven, multidimensional approach to conceptualizing future expectations can substantively contribute to our understanding of adolescent risk behavior. We use data from the National Longitudinal Survey of Youth 1997 to derive subpopulations of adolescents based on their future expectations with latent class analysis. Multinomial regression then determines which covariates from Bronfenbrenner's ecological systems theory are associated with class membership. After modeling these covariates, we examine whether future expectations is associated with delinquency, substance use, and sexual experience. Our analysis suggests the emergence of four distinct classes labeled the Student Expectations, Student/Drinking Expectations, Victim Expectations, and Drinking/Arrest Expectations classes according to their indicator profiles. These classes differ with respect to covariates associated with membership; furthermore, they are all statistically and differentially associated with at least one adolescent risk behavior. This analysis demonstrates the additional benefit derived from using this multidimensional approach for studying future expectations. Further research is needed to investigate its stability and role in predicting adolescent risk behavior over time.     

Urban American Indian Youth Spirituality and Religion: A Latent Class Analysis

This article explores the interconnected spiritual, religious, and cultural worlds of the majority of American Indian (AI) youth who live in urban areas: their patterns of involvement in religion and Native spirituality and associated well‐being. Latent class analysis of data from 205 AI middle school students identified five distinctive classes using survey measures of religious affiliation, attendance at services, adherence to Christian and traditional spiritual beliefs, Native spirituality, and Native cultural practices. Two classes were Christian groups: one attending Christian churches and following Christian beliefs but uninvolved with Native beliefs, spirituality, or cultural practices; and a nominal Christian group affiliated with but not attending church and unattached to belief systems. Two groups followed Native beliefs and spiritual practices, one affiliated with the Native American Church and another unaffiliated with any church. The fifth, nonreligious group, had no religious affiliation, followed neither Christian nor traditional beliefs, and was uninvolved in Native spirituality and cultural practices. The two groups embracing AI spirituality reported better academic performance, more reservation contact, higher AI enculturation, and stronger bicultural orientations.     

Bayesian Latent Class Analysis Tutorial

This article is a how-to guide on Bayesian computation using Gibbs sampling, demonstrated in the context of Latent Class Analysis (LCA). It is written for students in quantitative psychology or related fields who have a working knowledge of Bayes Theorem and conditional probability and have experience in writing computer programs in the statistical language R. The overall goals are to provide an accessible and self-contained tutorial, along with a practical computation tool. We begin with how Bayesian computation is typically described in academic articles. Technical difficulties are addressed by a hypothetical, worked-out example. We show how Bayesian computation can be broken down into a series of simpler calculations, which can then be assembled together to complete a computationally more complex model. The details are described much more explicitly than what is typically available in elementary introductions to Bayesian modeling so that readers are not overwhelmed by the mathematics. Moreover, the provided computer program shows how Bayesian LCA can be implemented with relative ease. The computer program is then applied in a large, real-world data set and explained line-by-line. We outline the general steps in how to extend these considerations to other methodological applications. We conclude with suggestions for further readings.     

Three Subtypes of Internalizing and Externalizing Behaviors in Chinese Adolescents: Results of a Latent Class Analysis

Using latent class analyses (LCA), the present study aimed to test whether meaningful subtypes of internalizing and externalizing behaviors could be found among Chinese community-based adolescents. A total of 5244 adolescents, ages 11–18 years (M?=?15.11, SD?=?1.79) recruited from 16 Chinese middle schools completed the Chinese version of the Strengths and Difficulties Questionnaire (SDQ-C). We examined the data using Latent Class Analysis to identify subtypes of internalizing and externalizing behaviors among the adolescents. Multivariate Logistic regression was subsequently implemented to ascertain the relationships between latent classes and demographic covariates. Three distinct subtypes were uncovered: a high-risk group, a middle-risk group and a low-risk group; the three subtypes accounted for 19.8, 31.1, and 49.1 % of the total sample variance respectively. Youth with elevations in one behavior type were likely to have elevations in the other behavior type. Further analyses revealed that compared to the low-risk group, the adolescents from the high-risk group and middle-risk groups were female and older. Significant heterogeneity in internalizing and externalizing behaviors was revealed in this Chinese adolescent’s sample. Profiling behavior problems patterns is potentially useful as a first step in developing tailored prevention and intervention programs. Suggestions for future research, including cross-national studies, and implications for mental health professionals were discussed.     

潜在类别分析技术在心理学研究中的应用

潜在类别分析是通过对类别型的外显变量和潜在变量之间的关系建立统计模型,根据模型参数得到各种潜在类别的具体外在表现的潜在特征分类技术。该分析方法主要应用于心理行为特征的分类、控制认知心理实验中被试个体差异引起的系统误差、评价临床心理诊断的精确性,以及心理测验中的项目分析、信度分析、结构分析等。对此方法的优劣进行分析比较,表明:该方法可以与其他测量理论相结合进一步拓展其在心理测量中的应用,也可在纵向数据和多水平数据中应用。在应用中亦有提升方法技术的空间。     

The Heterogeneity of Truancy among Urban Middle School Students: A Latent Class Growth Analysis

This longitudinal study explores heterogeneity of middle school students by identifying subgroups of youth characterized by distinct truancy trajectories and by determining disability profiles that distinguish these subgroups. Participants comprised an entire 7th through 9th grade student population, with approximately 58,000 students, in a large urban school district. Latent class growth analysis was used to identify subgroups of truant youth. This analysis yielded five distinct truant subgroups: Very-Low (37 %), Low (43.4 %), Declining (3.3 %), Rising (12.8 %), and Chronic (3.6 %). Further, differential disability profiles were found in each subgroup with the control of demographic characteristics (i.e., gender, race/ethnicity, free/reduced lunch, Limited English Proficiency, grade, and prior school absences), students with serious emotional disturbance and learning disabilities demonstrated amplified risks of being classified in the Chronic or Rising subgroups, which show chronic or incremental upward truant trajectories over time. These findings are discussed in terms of their implications for future research.     

Predicting Latent Class Scores for Subsequent Analysis

Latent class regression models relate covariates and latent constructs such as psychiatric disorders. Though full maximum likelihood estimation is available, estimation is often in three steps: (i) a latent class model is fitted without covariates; (ii) latent class scores are predicted; and (iii) the scores are regressed on covariates. We propose a new method for predicting class scores that, in contrast to posterior probability-based methods, yields consistent estimators of the parameters in the third step. Additionally, in simulation studies the new methodology exhibited only a minor loss of efficiency. Finally, the new and the posterior probability-based methods are compared in an analysis of mobility/exercise.     

Distinguishing Subgroups of Narcissists with Latent Class Analysis

This study investigated grandiose narcissism from a categorical perspective. We tested whether subgroups of narcissists can be distinguished that differ in their expressions of more agentic (narcissistic admiration, ADM) and more antagonistic (narcissistic rivalry, RIV) pathways of narcissism. We analysed three German samples (total N = 2211; M_age = 26; 70% female) and one US sample (N = 971; M_age = 35; 74% female) using latent class analysis. Four subgroups of narcissists were consistently identified across samples from Germany and the United States: low narcissists, moderate narcissists primarily characterized by agentic aspects (ADM), moderate narcissists characterized by both agentic and antagonistic aspects (ADM + RIV), and high narcissists. The subgroups were systematically related to a number of personality traits (e.g. Machiavellianism, impulsivity) and adjustment indicators (e.g. self‐esteem, empathy). Members in the moderate narcissists—ADM subgroup showed the most adaptive characteristics while members in the moderate narcissists—ADM + RIV subgroup showed the most maladaptive characteristics. Investigating grandiose narcissism—a primarily quantitative trait—from a categorical perspective can yield valuable insights that would otherwise be overlooked. In addition, our results underline the utility of a self‐regulatory process approach to grandiose narcissism that distinguishes between agentic and antagonistic dynamics. Copyright © 2016 European Association of Personality Psychology     

A Latent Profile Analysis of Internet use and Its Association with Psychological Well-Being Outcomes among Hong Kong Chinese Early Adolescents

Nowadays, the Internet has penetrated into every aspect of our daily life. The aims of this study were (a) to examine the patterns of Internet use among Hong Kong early adolescents and (b) to explore whether such patterns differed in terms of the psychological well-being (happiness, loneliness, depression and hopelessness), sensation seeking and perceived social support. A total of 1401 Chinese adolescents participated in the study. Results from the latent profile analysis suggested that there were four latent profiles, and different patterns of the Internet use were associated with the psychological well-being, perceived social support and sensation seeking. The present study sheds light on the importance of considering the nature of online activity and the relationship between Internet use and psychosocial well-being. Implications of the study are discussed.     

Using Latent Class Analysis to Model Temperament Types

Mixture models are appropriate for data that arise from a set of qualitatively different subpopulations. In this study, latent class analysis was applied to observational data from a laboratory assessment of infant temperament at four months of age. The EM algorithm was used to fit the models, and the Bayesian method of posterior predictive checks was used for model selection. Results show at least three types of infant temperament, with patterns consistent with those identified by previous researchers who classified the infants using a theoretically based system. Multiple imputation of group memberships is proposed as an alternative to assigning subjects to the latent class with maximum posterior probability in order to reflect variance due to uncertainty in the parameter estimation. Latent class membership at four months of age predicted longitudinal outcomes at four years of age. The example illustrates issues relevant to all mixture models, including estimation, multi-modality, model selection, and comparisons based on the latent group indicators.     

青少年自我伤害行为的潜在转变分析:一项纵向研究

研究采用潜在转变分析探究了青少年自我伤害行为的发展。对3600名青少年进行为期18个月的追踪,对其自我伤害行为进行了三次测量。通过纵向数据分析识别出过渡组这一以往研究未发现的群体,该组被试仅出现程度较轻的自我伤害行为,且占总体的比例随时间快速下降。通过转变矩阵解释了过渡组和高发组的不稳定性是自我伤害行为发生率降低的原因,并发现冲动性、负向情绪等个体易感因素比家庭等人际因素对自我伤害行为存在更为显著的预测作用。在性别差异上,女生比男生更容易产生自我伤害行为,也更容易受到各方面因素的影响。最后,文章针对青少年自我伤害行为的预防和控制工作提出了建议。     

Preliminary Outcomes of a Multi-site,School-based Modular Intervention for Adolescents Experiencing Mood Difficulties

Many evidence-based programs to address the emotional needs of youth experiencing mood difficulties are based on implementing “manualized” interventions. This approach often presents feasibility challenges in the school setting. In contrast, modular strategies, which involve implementing the most effective practices for specific emotional/behavioral problems, may be more feasible. Research, however, on the feasibility, acceptability, and effectiveness of modular approaches in schools to address youth experiencing mood difficulties is lacking. The multi-site current study tested the effectiveness, feasibility, and acceptability of a modular intervention approach delivered in schools for youth presenting with mood disorder symptoms. The pilot study included 20 participants (ages 12–16) and parents/caregivers for each student. Data were collected at baseline, throughout treatment, and following intervention or end of school year. The intervention, called the Student Emotional and Educational Development (SEED) project, included a modularized manual of efficacious and common practice elements for the treatment of mood disorders among adolescents. Decision making protocols guided provision of specific modules based on baseline and treatment data. Statistically significant differences were found between pretest and posttest assessments with modest to large effect sizes for youth and/or parents’ report of mood-related symptoms, including reduced symptoms of depression, anxiety and inattention. Clinically significant findings were also detected with more than 50 % of participants demonstrating reliable improvement on a global assessment of mental health symptoms. With regards to feasibility, these results were achieved with an average of nine, 45-min sessions across 2–3 months, and a subsample of participants overwhelmingly supported the acceptability of SEED. Although limited by the lack of a controlled comparison and small sample size, findings from this pilot study suggest this modular intervention focused on internalizing symptoms in students can be feasibly implemented in the school setting, is acceptable to students, and holds promise for improving their psychosocial functioning.     

Feasibility and Preliminary Outcomes of a School-Based Mindfulness Intervention for Urban Youth

Youth in underserved, urban communities are at risk for a range of negative outcomes related to stress, including social-emotional difficulties, behavior problems, and poor academic performance. Mindfulness-based approaches may improve adjustment among chronically stressed and disadvantaged youth by enhancing self-regulatory capacities. This paper reports findings from a pilot randomized controlled trial assessing the feasibility, acceptability, and preliminary outcomes of a school-based mindfulness and yoga intervention. Four urban public schools were randomized to an intervention or wait-list control condition (n = 97 fourth and fifth graders, 60.8% female). It was hypothesized that the 12-week intervention would reduce involuntary stress responses and improve mental health outcomes and social adjustment. Stress responses, depressive symptoms, and peer relations were assessed at baseline and post-intervention. Findings suggest the intervention was attractive to students, teachers, and school administrators and that it had a positive impact on problematic responses to stress including rumination, intrusive thoughts, and emotional arousal.     

Group Intervention for Adolescent Anxiety and Depression: Outcomes of a Randomized Trial with Adolescents in Kenya

Youth mental health interventions in low-resource communities may benefit from including empirically supported elements, using stigma-free content, and using trained lay-providers. We developed and evaluated such an intervention, targeting adolescent depression and anxiety in Kenya, where mental health care is limited by social stigma and a paucity of providers. Kenyan adolescents (N = 51, ages 14–17, 60.78% female) from a school in an urban slum in Nairobi with self-reported moderate-to-severe symptoms of depression or anxiety were randomized to the 4-week “Shamiri” (“thrive”) group intervention or a study skills control intervention of equal duration. The Shamiri intervention included growth mindset, gratitude, and value affirmation exercises. The content was delivered by recent high school graduates (ages 17–21, 60% male) trained as lay-providers. Participants met in school once-a-week in groups of 9–12 youths (average group size 10). Compared to the study-skills control, Shamiri produced greater reductions in adolescent depression symptoms (p = .038; d = .32) and anxiety symptoms (p = .039; d = .54) from baseline to 4-week follow-up, and greater improvements in academic performance (p = .034; d = .32) from the school-term before versus after the intervention. There were no effects on overall social support or perceived control, but the Shamiri group showed larger increases in perceived social support from friends (p = .028, d = .71). This appears to be the first report that a brief, lay-provider delivered, community-based intervention may reduce internalizing symptoms and improve academic outcomes in high-symptom adolescents in Sub-Saharan Africa. Larger replications with extended follow-ups will help gauge the strength and durability of these effects.     

当代中国青少年校园欺凌受害模式探索:基于潜在剖面分析

采用特拉华欺凌受害量表、病人健康问卷抑郁量表和广泛性焦虑量表对湖南省八个地区20所中学初一到高三3761名学生进行调查,探索学生欺凌受害模式,并对不同模式亚群体的人口学特点及其心理健康状况展开研究。结果发现：（1）校园欺凌中,言语欺凌、身体欺凌、关系欺凌、网络欺凌这四种常见欺凌类型具有较高的共发性,潜在剖面分析表明存在四种典型的校园欺凌受害模式："所有类型欺凌受害组"（1.5%）、"传统类型受害组"（3.9%）、"传统类型轻卷入组"（14.9%）和"未受害组"（79.6%）;（2）欺凌受害模式的人群分布受不同人口学特征（性别、年级、学校位置、自评学习成绩）的影响,男性、初中、乡村学校、成绩较差的学生更易受到欺凌;（3）即使是轻度的欺凌受害卷入,也会对个体心理健康产生较为严重的消极影响,对校园欺凌行为"零容忍"确有依据。     

The Application of Latent Curve Analysis to Testing Developmental Theories in Intervention Research

The effectiveness of a prevention or intervention program has traditionally been assessed using time-specific comparisons of mean levels between the treatment and the control groups. However, many times the behavior targeted by the intervention is naturally developing over time, and the goal of the treatment is to alter this natural or normative developmental trajectory. Examining time-specific mean levels can be both limiting and potentially misleading when the behavior of interest is developing systematically over time. It is argued here that there are both theoretical and statistical advantages associated with recasting intervention treatment effects in terms of normative and altered developmental trajectories. The recently developed technique of latent curve (LC) analysis is reviewed and extended to a true experimental design setting in which subjects are randomly assigned to a treatment intervention or a control condition. LC models are applied to both artificially generated and real intervention data sets to evaluate the efficacy of an intervention program. Not only do the LC models provide a more comprehensive understanding of the treatment and control group developmental processes compared to more traditional fixed-effects models, but LC models have greater statistical power to detect a given treatment effect. Finally, the LC models are modified to allow for the computation of specific power estimates under a variety of conditions and assumptions that can provide much needed information for the planning and design of more powerful but cost-efficient intervention programs for the future.     

A Latent Class Analysis of Childhood Maltreatment: Identifying Abuse Typologies

Multiple forms of abuse may co-occur, resulting in specific abuse typologies. A stratified random probability survey was conducted in Denmark with 4,718 participants, aged 24, from the 1984 birth cohort. A total of 2,980 interviews were successfully conducted. Latent class analysis was implemented using 20 categorical abuse experience items across four domains of childhood maltreatment. Logistic regression was conducted to ascertain whether abuse typologies could be differentiated by child protection status and gender. Four distinct abuse typologies were revealed: a non-abused group, a psychologically maltreated group, a sexually abused group, and a group experiencing multiple abuse types. Child protection status and female gender were predictive of group membership in certain abused groups compared to a non-abused group.     

Chicago Urban Resiliency Building (CURB): An Internet-Based Depression-Prevention Intervention for Urban African-American and Latino Adolescents

Early preventive interventions for depressive disorders in racial/ethnic minorities may help to reduce lifetime depression outcome disparities by improving developmental trajectories and social outcomes. We describe the development process, intervention and evaluation plan for a culturally adapted, low-cost, primary care/Internet-based depression-prevention intervention (CURB, Chicago Urban Resiliency Building). CURB is culturally adapted for socio-economically disadvantaged African-American and Latino adolescents according to the PEN-3 model of health promotion programs (Airhihenbuwa in Health and culture: beyond the Western paradigm, Sage Publishers, Thousand Oaks, 1995). Based on the idea that health behavior is rooted in culture, the PEN-3 model contains three interdependent dimensions that influence health beliefs and behaviors. Within each dimension are factors (using the acronym PEN) that must be considered about the target culture. Application of the PEN-3 model occurred in 3 phases. In each phase, a dimension of the model was explored and subsequent changes were made to the intervention so as to be more culturally suitable. In the CURB clinical trial, adolescents ages 13–17 will be recruited from wait-lists for mental health services at community health care provider organizations and screened for risk of future depressive disorder in the primary care sites. Adolescents screening positive for persistent depressed mood will be randomly assigned to either the CURB intervention group or the wait-list control group. The study aims are to determine if participants in the CURB intervention group will have lower levels of depressive symptoms and/or a lower cumulative incidence of depressive episodes.