A note on parameter estimation for Lazarsfeld's latent class analysis

As the literature indicates, no method is presently available which takes explicitly into account that the parameters of Lazarsfeld's latent class analysis are defined as probabilities and are therefore restricted to the interval [0, 1]. In the present paper an appropriate transform on the parameters is performed in order to satisfy this constraint, and the estimation of the transformed parameters according to the maximum likelihood principle is outlined. In the sequel, a numerical example is given for which the basis solution and the usual maximum likelihood method failed. The different results are compared and the advantages of the proposed method discussed.     

Psychometric latent response models

In this paper, some psychometric models will be presented that belong to the larger class oflatent response models (LRMs). First, LRMs are introduced by means of an application in the field ofcomponential item response theory (Embretson, 1980, 1984). Second, a general definition of LRMs (not specific for the psychometric subclass) is given. Third, some more psychometric LRMs, and examples of how they can be applied, are presented. Fourth, a method for obtaining maximum likelihood (ML) and some maximum a posteriori (MAP) estimates of the parameters of LRMs is presented. This method is then applied to theconjunctive Rasch model. Fifth and last, an application of the conjunctive Rasch model is presented. This model was applied to responses to typical verbal ability items (open synonym items).This paper presents theoretical and empirical results of a research project supported by the Research Council [Onderzoeksraad] of the University of Leuven (grant number 89-9) to Paul De Boeck and Luc Delbeke.     

Relating latent class membership to external variables: An overview

In this article we provide an overview of existing approaches for relating latent class membership to external variables of interest. We extend on the work of Nylund-Gibson et al. (Structural Equation Modeling: A Multidisciplinary Journal, 2019, 26, 967), who summarize models with distal outcomes by providing an overview of most recommended modeling options for models with covariates and larger models with multiple latent variables as well. We exemplify the modeling approaches using data from the General Social Survey for a model with a distal outcome where underlying model assumptions are violated, and a model with multiple latent variables. We discuss software availability and provide example syntax for the real data examples in Latent GOLD.     

Latent Profiles of Comorbid Depression as Predictors of PTSD Treatment Outcome

Posttraumatic stress disorder (PTSD) frequently co-occurs with major depressive disorder, and empirically supported PTSD treatments consistently improve depression. However, both diagnoses are heterogeneous and specific patterns of symptom overlap may be related to worse treatment outcome. Two hundred individuals with chronic PTSD participated in a doubly randomized preference trial comparing prolonged exposure and sertraline. Latent Profile Analysis was used to identify classes based on PTSD and depression symptoms prior to starting treatment. A three-class model best fit the data, with a high depression and PTSD severity class (distressed), a moderate depression and low PTSD avoidance class (depressive), and a low depression and high PTSD avoidance class (avoidant). The avoidant class showed the lowest rates of major depressive disorder diagnosis and transdiagnostic vulnerabilities to depression. Patients in the distressed class experienced more robust PTSD treatment response, with no differences between prolonged exposure and sertraline. These findings highlight the role of avoidance in nondepressed PTSD presentations while also demonstrating that co-occurring depression is not contraindicated in evidence-based PTSD treatment.     

Q‐sort methodology: Bridging the divide between qualitative and quantitative. An introduction to an innovative method for psychotherapy research

Q‐methodology offers unique opportunities for counselling and psychotherapy researchers and clinicians. It is an innovative technique capable of bridging the divide between clinical knowledge and the quantitative systematisation of it. It was initially developed by Stephenson as a data collection and data analytic method to empirically study human subjectivity. It was then extended by the British School to study shared viewpoints, thereby adopting a multi‐participant design and a highly unusual form of qualitative analysis. Finally, it was adapted by the Californian School for use as a standardised observer‐rated assessment tool. Its attractiveness stems from its aptitude to produce holistic data as it collects both quantitative and narrative data. This paper will provide an introduction to Q‐statistics and Q‐methodology (person‐centred) by contrasting it to R‐statistics and R‐methodology (variable‐centred). It will then provide an overview of the three schools of Q‐methodology and their various merits demonstrated with an example.     

随机截距潜在转变分析(RI-LTA)——个案自我转变与个案间差异的分离

传统的潜在转变分析属于单水平分析, 但其同样也可以看作二水平分析。Muthén和Asparouhov就以二水平分析的视角在单水平分析框架内提出了随机截距潜在转变分析(RI-LTA), 其中跨时间点产生的自我转变可以看作在水平1进行分析, 跨时间点不变的个案间差异可以看作在水平2进行分析, 使个案的自我转变和个案间的初始差异分离, 避免了高估保留在初始类别的概率。某研究型大学2016级本科生的追踪调查数据被用于演示使用随机截距潜在转变分析的过程。该方法的最大优势是通过引入随机截距避免了高估保留在本类别的转变概率。未来研究可以运用蒙特卡洛模拟研究探究随机截距潜在转变分析模型的适用性, 也可以用多水平分析的思路为灵感, 探究多水平随机截距潜在转变分析在统计软件中的实现。     

父母教养方式与初中生网络受欺负行为的关系:一项追踪研究

以491名初中生为研究对象,对其网络受欺负行为进行为期2年的4次追踪测试,同时测试其父母教养方式。采用潜变量混合增长模型探讨初中生网络受欺负行为的多种发展轨迹,并分析父母教养方式的影响。结果发现：（1）在2年时间内,初中生网络受欺负行为呈显著下降趋势;（2）初中生网络受欺负行为存在两种下降趋势,即快速下降与慢速下降;（3）父亲拒绝、父亲过度保护与母亲拒绝这三种教养方式可增加两组初中生的网络受欺负行为,同时也可降低其网络受欺负行为的下降速度;（4）父亲情感温暖可显著预测快速下降组的初始水平和发展速度,母亲过度保护可显著预测慢速下降组的初始水平和发展速度,母亲情感温暖可显著负向预测慢速下降组的发展速度。上述结果证实父母教养方式对初中生网络受欺负行为发展轨迹的预测作用,支持了Kowalski网络欺负模型。     

大学校长胜任力与职业认同的关系:基于潜在剖面分析

基于个体中心的视角考察大学校长胜任力和职业认同的关系,采用大学校长胜任力量表和职业认同量表对262名大学校长进行问卷调查。运用潜在剖面分析方法进行数据分析,结果表明:(1)大学校长胜任力可以分为四种潜在类别:低胜任力组、中胜任力组、高特质低能力组,高胜任力组,其中,中胜任组人数最多,高特质低能力组人数最少;(2)大学校长的职业认同得分在这四种潜在类别上有显著差异,中胜任力组、高胜任力组的大学校长职业认同得分显著高于高特质低能力组和低胜任力组,低胜任力组的大学校长职业认同显著于高于高特质低能力组。     

Evidence for discrete profiles of children’s physiological activity across three neurobiological system and their transitions over time

The conceptualization of stress‐responsive physiological systems as operating in an integrated manner is evident in several theoretical models of cross‐system functioning. However, limited empirical research has modeled the complexity of multisystem activity. Moreover few studies have explored developmentally regulated changes in multisystem activity during early childhood when plasticity is particularly pronounced. The current study used latent profile analysis (LPA) to evaluate multisystem activity during fall and spring of children's transition to kindergarten in three biological systems: the parasympathetic nervous system (PNS), sympathetic nervous system (SNS), and hypothalamic pituitary adrenal (HPA) axis. Latent transition analysis (LTA) was then used to examine the stability of profile classification across time. Across both timepoints, three distinct profiles of multisystem activity emerged. One profile was characterized by heightened HPA axis activity (HPA Axis Responders), a second profile was characterized by moderate, typically adaptive patterns across the PNS, SNS, and HPA axis (Active Copers/Mobilizers), and a third profile was characterized by heightened baseline activity, particularly in the PNS and SNS (Anticipatory Arousal/ANS Responders). LTA of fall‐to‐spring profile classifications indicated higher probabilities that children remained in the same profile over time compared to probabilities of profile changes, suggesting stability in certain patterns of cross‐system responsivity. Patterns of profile stability and change were associated with socioemotional outcomes at the end of the school year. Findings highlight the utility of LPA and LTA to detect meaningful patterns of complex multisystem physiological activity across three systems and their associations with early adjustment during an important developmental transition.     

Estimation of a Latent Variable Regression Growth Curve Model for Individuals Cross-Classified by Clusters

The cross-classified multiple membership latent variable regression (CCMM-LVR) model is a recent extension to the three-level latent variable regression (HM3-LVR) model which can be utilized for longitudinal data that contains individuals who changed clusters over time (for instance, student mobility across schools). The HM3-LVR model can include the initial status on growth effect as varying across those clusters and allows testing of more flexible hypotheses about the influence of initial status on growth and of factors that might impact that relationship, but only in the presence of pure clustering of participants within higher-level units. This Monte Carlo study was conducted to evaluate model estimation under a variety of conditions and to measure the impact of ignoring cross-classified data when estimating the incorrectly specified HM3-LVR model in a scenario in which true values for parameters are known. Furthermore, results from a real-data analysis were used to inform the design of the simulation. Overall, it would be recommended for researchers to utilize the CCMM-LVR model over the HM3-LVR model when individuals are cross-classified, and to use a bare minimum of more than 100 clustering units in order to avoid overestimation of the level-3 variance component estimates.