Latent Class Analysis With Sampling Weights

Often quantities of interest in psychology cannot be observed directly. These unobservable quantities, known as latent variables, tend to be complex, often multidimensional, constructs. In many cases these constructs are categorical, such that individuals belong to mutually exclusive and exhaustive unobservable subgroups. Latent class analysis (LCA) is a statistical approach to modeling a discrete latent variable using multiple, discrete observed variables as indicators. Examples of latent class variables that appear in the psychology literature include temperament type, substance use behavior, teaching style, stages of change in the transtheoretical model, and latent classes of risk. The first section of this chapter provides a conceptual introduction to the concept of a latent class followed by a technical introduction to the mathematical model, including multiple-groups LCA and LCA with covariates. This is followed by a discussion of parameter restrictions, model selection, and goodness-of-fit. The second section demonstrates LCA using the empirical example of depression subtypes in adolescence. Five latent classes were identified based on responses to eight questionnaire items assessing depression symptoms: Non-depressed (characterized by a low probability of reporting all eight depression symptoms), sad, disliked, sad + disliked, and depressed (characterized by a high probability of reporting all eight depression symptoms). The third section presents longitudinal extensions of the model, including repeated-measures LCA and latent transition analysis (LTA). The empirical example is extended to examine change in depression subtypes over time. The final sections describe recent extensions to the latent class model and areas that merit additional research in the future. Keywords: latent class analysis; latent transition analysis; latent variable model; categorical data

Background: Over the last two decades, latent class analysis (LCA) has been extensively used to statistically identify phenotypes of childhood wheeze; however, less has been discussed on the external factors affecting the outcomes of LCA models in phenotype identification research. Objective: To understand the potential cause of variability in the number/types of wheeze phenotypes identified by means of LCA and to assess the performance of these models under different conditions. Methods: Here, we examined the effects of several data characteristics (sample size, data collection age and intervals), and model dimensionality (number of latent classes) on the classification of wheeze phenotypes by means of latent class and transition analysis. We also identified critical and redundant data collection points in discriminating phenotypes of wheeze using two different variable selection methods, stepwise-backward elimination, and genetic algorithm. Results: Small sample sizes suggested fewer wheeze sub-groups as they were underpowered to detect less frequently observed wheeze phenotypes. There was a strong interplay between sample size, number of data collection points and the optimal number of wheeze phenotypes extracted. A variable selection algorithm applied to LCA resulted in the exclusion of 6 redundant/non-informative time points (Month 6, Month 30, Month 69, Month 91, Month 140 and Month 198) as they contained very little discriminative and/or extra information about the wheeze classes. Conclusions: Input data characteristics and model complexity were found to be very influential on the classification of wheeze phenotypes and prevalence of each class in the population.

Using three waves of data from the European Community Household Panel, this paper estimates demand for physician services equations for 12 European countries. We focus on the selection of the most appropriate econometric specification for visits to general practitioners and to specialists among two-part and latent class models. The distinction between the demand of services from these two types of physicians allows us to distinguish cases in which two-part perform better than latent class models, evidence which is different from previous findings in the literature. The results suggest that latent class models are more appropriate than two-part models to estimate general practitioners utilisation while the opposite is found for visits to the specialists.

Purpose Our objectives were to (a) identify oral and pharyngeal physiologic swallowing impairment severity classes based on latent class analyses (LCAs) of the Modified Barium Swallow Impairment Profile (MBSImP) swallow task scores and (b) quantify the probability of severity class membership given composite MBSImP oral total (OT) and pharyngeal total (PT) scores. Method MBSImP scores were collected from a patient database of 319 consecutive modified barium swallow studies. Because of missing swallow task scores, LCA was performed using 25 multiply imputed data sets. Results LCA revealed a three-class structure for both oral and pharyngeal models. We identified OT and PT score intervals to assign subjects to oral and pharyngeal impairment latent severity classes, respectively, with high probability (probability of class membership ≥ 0.9 given OT or PT scores within specified ranges) and high confidence (95% credible interval [CI] widths ≤ 0.24 for all total scores within specified ranges). OT scores ranging from 0 to 10 and from 14 to 18 yielded assignments in Oral Latent Classes 1 and 2, respectively, while OT = 22 was assigned to Oral Latent Class 3. PT scores ranging from 0 to 13 and from 18 to 24 yielded assignments in Pharyngeal Latent Classes 1 and 2, respectively, while PT = 26 was assigned to Pharyngeal Latent Class 3. Conclusions LCA of MBSImP task-level data revealed significant underlying oral and pharyngeal ordinal class structures representing increasingly severe gradations of physiologic swallow impairment. Clinically meaningful OT and PT score ranges were derived facilitating latent class assignment. Supplemental Material https://doi.org/10.23641/asha.12315677.

As artificial intelligence (AI) becomes increasingly integrated into workplaces, understanding the factors that shape employee engagement is essential. This study examines how personality traits and demographic/professional characteristics influence AI adoption, focusing on employees’ willingness to engage with AI technologies and their perceptions of AI’s usefulness and ease of use. Data from 878 employed adults were analyzed using Latent Profile and Latent Class Analyses, identifying four personality and five demographic profiles. Cross-tabulations revealed a significant, moderately strong association between these profiles. AI engagement varied across groups: individuals high in negative emotionality and conscientiousness reported the highest usage, while emotionally stable, highly conscientious individuals showed lower engagement. Younger, educated professionals expressed the most favorable AI perceptions, whereas older public-sector employees reported limited use. Multinomial regressions and ANOVAs confirmed significant group differences. The findings highlight the importance of aligning AI implementation strategies with both psychological and contextual employee factors.

Data on stage of change was collected between 1997–1999 on 4125 adolescent nonsmokers and smokers from central England who completed two versions of the stage of change algorithm for smoking acquisition and cessation. The fit of the latent variable defined by the spiral of change to adolescents' responses to the staging questions was examined using latent class analysis. Whether a model of sequential transition across stages fitted the observed transitions was tested with latent transition analysis (LTA). There was reasonable support for the staging algorithm but no evidence of sequential stage transition. The research was funded by Cancer Research UK.

The theory of the cultural omnivore has been applied to many cultural domains. However, given the pervasiveness of professional sport in contemporary societies, less is known about omnivorous behaviour when it comes to consuming this cultural form. This study sets out to find if indeed there is an omnivorous consumption profile for professional sport. Using a latent class and regression analysis of survey data on five major professional sports leagues from Canada, this paper seeks to determine if this professional sport omnivore exists, how prevalent it might be, and if it maps onto wider socio-economic differentiations. The latent class analysis does show that there is an omnivorous consumption profile. However, it is the second smallest professional sport profile and does not map onto wider socio-economic differentiations, even as other patterns of professional sports’ consumption do display such distinctions.

BackgroundLifestyle risk factors, such as unhealthy diet, physical inactivity or tobacco smoking can have detrimental effects on health and well-being. Therefore, it is important to examine multiple lifestyle risk factors instead of single ones. Cluster analysis allows the combination of single health behaviors in order to recognize distinguished behavior patterns. This study aimed to evaluate lifestyle patterns of general adult population in northwest of Iran with particular focus on dietary patterns, physical activity, and smoking status.MethodsThe current cross-sectional study consists of 525 adults aged 18–64 years from East-Azarbaijan Iran. Latent class analysis (LCA) was applied to recognize patterns of lifestyle behaviors with ingredients of diet, physical activity, and smoking status. Dietary intake was assessed using a validated food frequency questionnaire and dietary patterns were derived using factor analysis. Biochemical parameters including fasting blood sugar (FBS), serum lipids, liver enzyme and serum 25(OH)-D3 were measured with commercial ELIZA kits.ResultsMean ages of participants were 42.90 ± 11.89 years. Using principal component analysis (PCA) three major dietary patterns were extracted including traditional dietary pattern (e.g. nuts and dry fruits), unhealthy dietary pattern (e.g. fast foods, refined grains) and the healthy dietary patterns (e.g. fruits, vegetables). Using LCA, three classes of lifestyles pattern were identified: 1st class was characterized by a healthy dietary pattern, moderate physical activity, and low probability of smoking. 2nd class was characterized by a traditional dietary pattern, low level of physical activity and low probability of smoking and 3rd class was characterized by a unhealthy dietary pattern, low level of physical activity and low probability of smoking and further analysis found that there were significant differences in body mass index (BMI), Waist-to-hip ratio (WHR), FBS, Hemoglobin (Hb), education levels and anxiety status between classes (P <0.05).ConclusionThis study attempts to classify Iranian adults by their own health behavior. Healthcare professionals should be aware of associations between different lifestyle risk factors and health promotion strategies should further focus on multiple behaviors at the same time. In our country, more studies about the adult population are needed to support the observed findings of our study and therefore allow for a certain generalization of the observations.

Rigorous studies repeatedly have demonstrated the negative effects of parental divorce on outcomes for families. However, very few studies have examined the quality of the marital relationship within intact families or how the quality of the marital relationship interacts with the quality of the parent–adolescent relationship. The present study examines how aspects of parent marital quality, such as marital support and conflict between the couple, existed within married families and examines how patterns of mother–adolescent and father–adolescent relationships quality varied longitudinally from 1997 to 1999. The study uses data from the NLSY97 cohort, a nationally representative sample of adolescents who are being followed into adulthood. Four profiles of parent marital quality were developed using latent class analyses. Four growth profiles for the mother–adolescent relationship and for the father–adolescent relationship were created using latent growth class analysis in Mplus. To examine how the parent marital quality profiles and the parent–adolescent relationship quality interact, we examined how they overlapped. Six distinct groups were evident from this examination: (1) high marital quality and good relationships with both parents, (2) high marital quality and a good relationship with only one parent, (3) high support and high conflict marital quality and a good relationship with at least one parent, (4) low marital quality and a good relationship with at least one parent, (5) high marital quality and bad relationships with both parents, and (6) low marital quality and bad relationships with both parents.

Despite the recognized benefits of the COVID-19 vaccination, vaccine hesitancy (VH) remains one of the biggest challenges of the mass vaccination campaign. Most studies investigating VH determinants focused on socio-demographics and direct relationships. In this study, we aimed at: 1) identifying subgroups of people differently affected by the pandemic, in terms of psychological status; 2) investigating the role of psychological status and trust in information as possible mediators of the relationship between individual characteristics and VH. To this purpose, a latent class analysis (LCA) followed by a mediation analysis were carried out on data from a survey conducted in January 2021 on 1011 Italian citizens. LCA identified four different subgroups characterized by a differential psychological impact of the pandemic: the extremely affected (21.1%), the highly affected (49.1%), the moderately affected (21.8%) and the slightly affected (8%). We found that VH decreased with the increase of psychological impact (from 59.3% to 23.9%). In the mediation analysis, past vaccination refusal, age 45-54 years and lower-than-average income, were all indirectly related to higher VH through mistrust in COVID-19 information. Differently, the psychological impact counteracted the greater VH in females, the negative effect of social media among youngest (<35 years) and the negative effect of mistrust in the lower-than-average-income subgroup. Knowledge of psychological profile of hesitant individuals, their level of trust and the sources of information they access, together with their sociodemographic characteristics provides a more comprehensive picture of VH determinants that can be used by public health stakeholders to effectively design and adapt communication campaigns.

Missing data and especially dropouts frequently arise in longitudinal data. Maximum likelihood estimates are consistent when data are missing at random (MAR) but, as this assumption is not checkable, pattern mixture models (PMM) have been developed to deal with informative dropout. More recently, latent class models (LCM) have been proposed as a way to relax PMM assumptions. The aim of this paper is to compare PMM and LCM in order to tackle informative dropout in a longitudinal study of cognitive ageing measured by several psychometric tests. Using a multivariate longitudinal model with a latent process, a sensitivity analysis was performed to compare estimates under the MAR assumption, from a PMM and from two LCM. In the PMM, dropout patterns are included as covariates in the multivariate longitudinal model. In the simple LCM, they are predictors of the class membership probabilities while, in the joint LCM, the dropout time is jointly modeled using a proportional hazard model depending on latent classes. We show that parameter interpretation is different in the two kinds of models and thus can lead to different estimated values. PMM parameters are adjusted on the dropout patterns while LCM parameters are adjusted on the latent classes. This difference is highlighted in our data set because the latent classes exhibit much more heterogeneity than dropout patterns. We suggest several complementary analyses to investigate the characteristics of latent classes in order to understand the meaning of the parameters when using LCM to deal with informative dropout.

Flexible methods that relax restrictive conditional independence assumptions of latent classanalysis (LCA) are described. Dichotomous and ordered category manifest variables are viewed asdiscretized latent continuous variables. The latent continuous variables are assumed to have a mixtureofmultivariate-normals distribution. Within a latent class, conditional dependence is modeled as the mutual association of all or some latent continuous variables with a continuous latent trait (or in special cases, multiple latent traits). The relaxation of conditional independence assumptions allows LCA to better model natural taxa. Comparisons of specific restricted and unrestricted models permit statistical tests of specific aspects of latent taxonic structure. Latent class, latent trait, and latent distribution analysis can be viewed as special cases of the mixed latent trait model. The relationship between the multivariate probit mixture model proposed here and Rost’s mixed Rasch (1990, 1991) model is discussed. Two studies illustrate different uses of the proposed model.

We propose using latent class analysis as an alternative to log-linear analysis for the multiple imputation of incomplete categorical data. Similar to log-linear models, latent class models can be used to describe complex association structures between the variables used in the imputation model. However, unlike log-linear models, latent class models can be used to build large imputation models containing more than a few categorical variables. To obtain imputations reflecting uncertainty about the unknown model parameters, we use a nonparametric bootstrap procedure as an alternative to the more common full Bayesian approach. The proposed multiple imputation method, which is implemented in Latent GOLD software for latent class analysis, is illustrated with two examples. In a simulated data example, we compare the new method to well-established methods such as maximum likelihood estimation with incomplete data and multiple imputation using a saturated log-linear model. This example shows that the proposed method yields unbiased parameter estimates and standard errors. The second example concerns an application using a typical social sciences data set. It contains 79 variables that are all included in the imputation model. The proposed method is especially useful for such large data sets because standard methods for dealing with missing data in categorical variables break down when the number of variables is so large.

Accommodating taste heterogeneity in railway passenger choice models based on internet booking data

A choice to use a seat belt is largely dependent on the psychology of the vehicles’ occupants, and thus those decisions are expected to be characterized by preference heterogeneity. Despite the importance of seat belt use on the safety of the roadways, the majority of existing studies ignored the heterogeneity in the data and used a very standard statistical or descriptive method to identify the factors of using a seatbelt. Application of the right statistical method is of crucial importance to unlock the underlying factors of the choice being made by vehicles’ occupants. Thus, this study was conducted to identify the contributory factors to the front-seat passengers’ choice of seat belt usage, while accounting for the choice preference heterogeneity. The latent class model has been offered to replace the mixed logit model by replacing a continuous distribution with a discrete one. However, one of the shortcomings of the latent class model is that the homogeneity is assumed across a same class. A further extension is to relax the assumption of homogeneity by allowing some parameters to vary across the same group. The model could still be extended to overlay some attributes by considering attributes non-attendance (ANA), and aggregation of common-metric attributes (ACMA). Thus, this study was conducted to make a comparison across goodness of fit of the discussed models. Beside a comparison based on goodness of fit, the share of individuals in each class was used to see how it changes based on various model specifications. In summary, the results indicated that adding another layer to account for the heterogeneity within the same class of the latent class (LC) model, and accounting for ANA and ACMA would improve the model fit. It has been discussed in the content of the manuscript that accounting for ANA, ACMA and an extra layer of heterogeneity does not just improve the model goodness of fit, but largely impacts the share of class allocation of the models.