Class Model Research Articles

Identifying subgroups of teacher burnout in elementary and secondary schools: the effects of teacher experience, age and gender

IntroductionTeacher burnout is a serious problem that requires quick attention and management since it not only compromises educational quality but also strains schools’ financial resources.Research objectiveThe purpose of the present study was to profile burnout indicators for teachers in the Kingdom of Saudi Arabia. A secondary goal was to evaluate the consistency of burnout profiles between elementary and secondary school teachers.MethodParticipants were 703 teachers who participated in the Trends in International Mathematics and Science Study (TIMSS 2019) and were part of the measurement in Saudi Arabia and participated in this study. A series of nested latent class models were run using 1–6 classes to identify an optimal number of interpretable subgroups (latent classes) that best describe the latent construct of teacher burnout in the elementary and high school setting.ResultsThe most important finding was that more than one-third of the teachers reported high levels of burnout irrespective of education level or gender. Furthermore, teachers’ experience and age were positive predictors of burnout with older teachers having significantly elevated levels of burnout. Gender on the other hand did not play a significant moderating role in teachers’ levels of burnout.ImplicationsReducing the number of students in each class, reorganizing the administrative work that has to be done, adding more support personnel to classrooms, and increasing time management skills and tactics via professional development programs are all potential solutions that might help alleviate the problem of teacher burnout.

Bayesian estimation of diagnostic accuracy of fecal smears, fecal PCR and serum ELISA for detecting Mycobacterium avium subsp. paratuberculosis infections in four domestic ruminant species in Saudi Arabia.

Paratuberculosis, a chronic wasting disease affecting domestic and wild ruminants worldwide, is caused by Mycobacterium avium subsp. paratuberculosis (MAP). Various diagnostic tests exist for detecting MAP infection; however, none of them possess perfect accuracy to be qualified as a reference standard test, particularly due to their notably low sensitivity. Therefore, we used Bayesian latent class models (BLCMs) to estimate diagnostic accuracy of fecal smears (FS), fecal PCR and serum ELISA for detecting MAP infections in sheep, goats, cattle, and camels older than 2 years in Saudi Arabia. Data from a cross-sectional study conducted in the Eastern Province of Saudi Arabia on 31 different farms with a history of MAP infection were analyzed. Fecal and blood samples from all animals older than 2 years in each farm were collected, resulting in a total of 220 sheep, 123 goats, 66 cattle, and 240 camels sampled. FS and IS900-PCR were performed on fecal samples to detect acid-fast bacilli and MAP DNA, respectively. The IDEXX ELISA kit was used to detect MAP antibodies in serum samples. For each ruminant species population, a BLCM was fitted to obtain posterior estimates [medians and 95 % Bayesian credible intervals (95 % BCI)] for sensitivity (Se) and specificity (Sp) of the three tests. We assumed FS and PCR to be conditionally dependent on the true animal MAP status. Prior distributions for test accuracy were used if available. FS had the highest Se among all tests and across all species with median values around 80 % in sheep, goats and camels, and near 50 % in cattle. Median Sp estimates of ELISA and PCR were higher than 90 % for all species. FS yielded the lowest Sp of the study when applied in camels, sheep, and goats. Using the prevalence observed in this study, median positive predictive value (PPV) was higher for PCR and ELISA than FS for camels, sheep, and goats. In cattle, PPV of all tests was similar with median estimates > 95 %. In camels, sheep, and goats, median negative predicative value (NPV) of all tests were > 60 %. The lowest median NPV for all tests were observed in cattle (<30 %). Our results suggest that ELISA is a suitable option to identify MAP infected animals in farms with previous history of MAP in the Eastern region of Saudi Arabia.

통제요인들이 아동·청소년기 범죄피해 궤적에 미치는 영향

The purpose of this study is to examine the influence of control factors on the process of victimization over time based on the phenomenon of multiple victimization and repeat victimization of children and adolescents. This study hypothesizes that the types of victimization based on the category of poly-victimization can vary by the developmental stage of children and adolescents; the types of victimization based on the category of poly-victimization can exist in various groups over time; parental supervision, parental bonds, peer bonds, and self-control can affect victimization and victimization trajectories. The hypotheses were tested using data from the Korean Children &amp; Youth Panel Survey(KCYPS), focusing on the period from the sixth grade of elementary school to the second grade of middle school. Frequency analysis, growth model analysis, latent class model analysis, and growth mixture model analysis were conducted to test hypotheses. The results show that the types of victimization are decreasing over time; victimization trajectories can be classified as risk group and general group; the most influential control factor on victimization trajectories is self-control. The findings suggest that the elementary school period is the most vulnerable period based on the types of victimization; there is a group that is vulnerable to victimization during the developmental stage of children and adolescents; victimization trajectories are better explained by the heterogeneity perspective than the event-dependence perspective; one of the risk factors for victimization is low self-control.

Cross-sectional associations between patterns of cultural engagement and indicators of biological dysregulation

Background Research has shown that cultural activities may bring about improved health. However, large-scale quantitative analyses on cultural engagement and biomarkers are lacking to date. As a result, the mechanisms through which cultural activities may be associated with health are unclear. Aim Test quantitative associations between cultural engagement pattern (including active and passive engagement in arts, sports, and heritage activities) and indicators of biological dysregulation in a large dataset. Subjects and methods Understanding Society data were used to conduct cross-sectional linear regression analyses between a data-driven latent class model of cultural engagement and indicators of anthropometric, cardiovascular, metabolic, immune, and neuroendocrine function. Analyses were adjusted for age, gender, ethnicity, childcare responsibility, urbanicity, leisure time satisfaction, capacity-related factors, socioeconomic position, social and economic capital indicators, physical activity, and medication use. Results More culturally participants had better indicators of biological health, such as lower waist circumference and fibrinogen blood concentration. Specific associations between cultural engagement pattern and the different biological outcomes were also observed. The associations were explained in part by correlated factors (accounting for around half of the association). Conclusions Cultural engagement is cross-sectionally associated with biomarkers, although the characteristics of people who engage with culture are an important consideration when interpreting these findings.

A sparse latent class model incorporating response times.

Diagnostic models (DM) have been widely used to classify respondents' latent attributes in cognitive and non-cognitive assessments. The integration of response times (RTs) with DM presents additional evidence to understand respondents' problem-solving behaviours. While recent research has explored using sparse latent class models (SLCM) to infer the latent structure of items based on item responses, the incorporation of RT data within these models remains underexplored. This study extends the SLCM framework to include RT, relaxing the conditional independence assumption between RT and latent attributes given individual speed. This adaptation provides a more flexible framework for jointly modelling RT and item responses. While the proposed model holds promise for applications in educational assessment, this study applied the model to the Fisher Temperament Inventory, yielding findings that provide a novel perspective on utilizing DM with RT in personality assessments. Additionally, a Gibbs sampling algorithm is proposed for parameter estimation. Results from Monte Carlo simulations demonstrate the algorithm's accuracy and efficiency.

Lipid-mediated resolution of inflammation and survival in amyotrophic lateral sclerosis

Abstract Neuroinflammation impacts on the progression of amyotrophic lateral sclerosis (ALS), a fatal neurodegenerative disorder. Specialized pro-resolving mediators trigger the resolution of inflammation. We investigate the specialized pro-resolving mediator blood profile and their receptors’ expression in peripheral blood mononuclear cells in relation to survival in ALS. People living with ALS (pwALS) were stratified based on bulbar versus limb onset and on key progression metrics using a latent class model, to separate faster progressing from slower progressing ALS. Specialized pro-resolving mediator blood concentrations were measured at baseline and in one additional visit in 20 pwALS and 10 non-neurological controls (Cohort 1). Flow cytometry was used to study the GPR32 and GPR18 resolvin receptors’ expression in peripheral blood mononuclear cells from 40 pwALS and 20 non-neurological controls (Cohort 2) at baseline and in two additional visits in 17 pwALS. Survival analysis was performed using Cox proportional hazards models, including known clinical predictors and GPR32 and GPR18 mononuclear cell expression. Differential expression and linear discriminant analyses showed that plasma resolvins were able to distinguish phenotypic variants of ALS from non-neurological controls. RvE3 was elevated in blood from pwALS, whilst RvD1, RvE3, RvT4 and RvD1n-3 DPA were upregulated in A-S and RvD2 in A-F. Compared to non-neurological controls, GPR32 was upregulated in monocytes expressing the active inflammation-suppressing CD11b+ integrin from fast-progressing pwALS, including those with bulbar onset disease (P &amp;lt; 0.0024), whilst GPR32 and GPR18 were downregulated in most B and T cell subtypes. Only GPR18 was upregulated in naïve double positive Tregs, memory cytotoxic Tregs, senescent late memory B cells and late senescent CD8+ T cells from pwALS compared to non-neurological controls (P &amp;lt; 0.0431). Higher GPR32 and GPR18 median expression in blood mononuclear cells was associated with longer survival, with GPR32 expression in classical monocytes (hazard ratio: 0.11, P = 0.003) and unswitched memory B cells (hazard ratio: 0.44, P = 0.008) showing the most significant association, along with known clinical predictors. Low levels of resolvins and downregulation of their membrane receptors in blood mononuclear cells are linked to a faster progression of ALS. Higher mononuclear cell expression of resolvin receptors is a predictor of longer survival. These findings suggest a lipid-mediated neuroprotective response that could be harnessed to develop novel therapeutic strategies and biomarkers for ALS.

Signaling Model Misspecification in Latent Class Analysis

Modification indices, common in structural equation modeling, are not applicable to latent class analysis due to differences in estimation and fit assessment. To address this, we propose using gradient descent optimization to identify sensitive parameters. By aligning predictions with observed data through iterative adjustments, gradient descent reveals inadequacies in the original model’s representation of relationships, prompting alternative specifications. Our method primarily detects misspecifications in latent class models related to variable selection but also aids in class enumeration. Gradient descent shows promise for offering a robust tool to mitigate issues like omitted variable bias and improve the accuracy of study conclusions.

Material Hardship, Forced Displacement, and Negative Health Outcomes Among Unhoused People Who Use Drugs in Los Angeles, California and Denver, Colorado: A Latent Class Analysis.

Homelessness is a growing concern in the United States, especially among people who use drugs (PWUD). The degree of material hardship among this population may be linked to worse health outcomes. PWUD experiencing homelessness in urban areas are increasingly subjected to policies and social treatment, such as forced displacement, which may worsen material hardship. It is critical to describe hardship among PWUD and examine if it is linked to health outcomes. Data were collected as part of a prospective cohort study of PWUD in Los Angeles, California and Denver, Colorado (n = 476). Analysis sample size was smaller (N = 395) after selecting for people experiencing homelessness and for whom data were complete. Five indicators assessing hardship (difficulty finding food, clothing, restrooms, places to wash/shower, and shelter) in the past three months were obtained from participants at baseline and were used in latent class analysis (LCA). We chose a base latent class model after examination of global fit statistics. We then built three auxiliary models using the three-step Bolck-Croon-Hagenaars (BCH) method to test the relationship of latent class membership to several hypothesized social and health variables in this same three month time period. Fit statistics, minimum classification probabilities, and ease of interpretation indicated a three-class solution for level of material difficulty. We termed these classes "High Difficulty" (n = 82), "Mixed Difficulty" (n = 215), and "Low Difficulty" (n = 98). Average classification probabilities indicated good class separability. "High Difficulty" participants had high probabilities of usually having difficulty accessing all five resources. "Mixed Difficulty" participants indicated a range of difficulty accessing all resources, with restrooms and bathing facilities being the most difficult. "Low Difficulty" participants were defined by high probabilities of never having access difficulty. In auxiliary analyses, there were significant (p < 0.05) differences in experiences of displacement, opioid withdrawal symptoms, nonfatal overdose, and violent victimization between classes. This LCA indicates that among PWUD experiencing homelessness there exist distinct differences in resource access and material hardship, and that these differences are linked with political, social, substance use, and other health outcomes. We add to the literature on the relationship between poverty and health among PWUD. Policies which increase difficulty accessing necessary material resources may negatively impact health in this population.

Modeling Passengers’ Reserved Time Before High-Speed Rail Departure

The pre-departure reserved time (PDRV) for high-speed railway (HSR) passengers, which encompasses all the time between passengers leaving their origin and the departure of the HSR train they are going to take, is a crucial factor in planning intercity travel. Understanding how passengers select their PDRV is not only important for developing effective strategies to improve HSR efficiency but also for optimizing the integration between HSR hubs and urban transportation networks. However, analyzing passenger choice behavior regarding PDRV is complex due to numerous influencing factors. Despite this, few studies have explored how HSR passengers make their PDRV choices. This paper, using Nanjingnan Railway Station as a case study, presents a novel investigation into the PDRV choice behavior of HSR passengers. An integrated latent class model (LCM) and ordered probit model (OPM) are applied to identify the factors affecting passengers’ PDRV choices. The sample data are segmented based on individual characteristics using the LCM, and OPM models are then constructed for each segment to analyze PDRV choice behavior. The results reveal that several factors—such as travel purpose, the number of times passengers used HSR at Nanjingnan Station in the previous year, the duration of HSR travel, the number of companions, feeder trip duration, and departure time—significantly impact PDRV choices. The integrated LCM and OPM approach also uncovers choice heterogeneity among different passenger groups. These insights can serve as a valuable reference for forecasting HSR passenger demand and for designing integrated HSR hubs and urban transport systems.

Exploring clinical chemistry markers in amyotrophic lateral sclerosis: insights into survival and disease trajectories

ObjectiveCommonly measured clinical chemistry markers might be indicative of survival and disease progression in amyotrophic lateral sclerosis (ALS).MethodsIn a cohort study of 270 ALS patients diagnosed from April 2014 to May 2021 in Stockholm, Sweden, we examined the link between 29 clinical chemistry markers at diagnosis and mortality risk at 6 months, 1 year, and 3 years after diagnosis. Summary variables from exploratory factor analysis (EFA) assessed the markers’ collective impact on survival. We integrated ALS functional rating scale-revised (ALSFRS-R) scores with survival data using a joint latent class model to identify patterns of functional decline. Multinomial logistic regression determined how the EFA-derived factors predicted the decline trajectories post-diagnosis.ResultsHigher levels of total cholesterol, low-density lipoprotein cholesterol (LDL-C), apolipoprotein B, and albumin at diagnosis were linked to lower mortality in ALS patients, while increased neurofilament light chain (NfL), leukocyte count, mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), and carbon dioxide (CO2) levels indicated higher mortality. The ‘Red blood cell profile’ factor, derived from EFA, emerged as a significant predictor of survival, independent of other prognostic indicators. The joint latent class model identified three distinct patient groups based on functional decline, with ‘Red blood cell profile’ suggesting a lower likelihood of being in the groups with slower progression.ConclusionClinical chemistry markers, including NfL, lipids, albumin, leukocyte count, MCV, MCH, CO2, and the ‘Red blood cell profile,’ were associated with ALS survival. As these markers represent broader bodily functions, integrating them in ALS patient care could improve disease management.

A Bayesian latent class approach to causal inference with longitudinal data.

Bayesian methods are becoming increasingly in demand in clinical and public health comparative effectiveness research. Limited literature has explored parametric Bayesian causal approaches to handle time-dependent treatment and time-dependent covariates. In this article, building on to the work on Bayesian g-computation, we propose a fully Bayesian causal approach, implemented using latent confounder classes which represent the patient's disease and health status. Our setting is suitable when the latent class represents a true disease state that the physician is able to infer without misclassification based on manifest variables. We consider a causal effect that is confounded by the visit-specific latent class in a longitudinal setting and formulate the joint likelihood of the treatment, outcome and latent class models conditionally on the class indicators. The proposed causal structure with latent classes features dimension reduction of time-dependent confounders. We examine the performance of the proposed method using simulation studies and compare the proposed method to other causal methods for longitudinal data with time-dependent treatment and time-dependent confounding. Our approach is illustrated through a study of the effectiveness of intravenous immunoglobulin in treating newly diagnosed juvenile dermatomyositis.

Value of Innovative Multiple Myeloma Treatments from Patient and Healthcare Provider Perspectives: Evidence from a Discrete Choice Experiment.

Although innovation generally provides measurable improvements in disease characteristics and patient survival, some benefits can remain unclear. This study aimed to investigate patient and healthcare provider (HCP) preferences for the innovative attributes of multiple myeloma (MM) treatments. A cross-sectional, web-based, discrete choice experiment (DCE) survey was conducted among 200 patients with MM and 30 HCPs of patients with MM in the USA. A literature review, followed by interviews with patients with MM and HCPs, was undertaken to select five attributes (progression-free survival [PFS], chance of severe side effects, how patients live with MM treatments, scientific innovation, and monthly out-of-pocket [OOP] cost) and their levels. A Bayesian efficient design was used to generate DCE choice sets. Each choice set comprised two hypothetical MM treatment alternatives described by the selected attributes and their levels. Each patient and HCP was asked to choose a preferred alternative from each of the 11 choice sets. Mixed logit and latent class models were developed to estimate patient and HCP preferences for the treatment attributes. Overall, patients and HCPs preferred increased PFS, less chance of severe side effects, a treatment that offered life without treatment, scientific innovation, and lower OOP cost. From patients' perspectives, PFS had the highest conditional relative importance (44.7%), followed by how patients live with MM treatments (21.6%) and scientific innovation (16.0%). In addition to PFS, patients and HCPs also valued innovative MM treatments that allowed them to live without treatments and/or offered scientific innovation. These attributes should be considered when evaluating MM treatments.

Detecting departures from the conditional independence assumption in diagnostic latent class models: a simulation study

BackgroundLatent class models can be used to estimate diagnostic accuracy without a gold standard test. Early studies often assumed independence between tests given the true disease state, however this can lead to biased estimates when there are inter-test dependencies. Residual correlation plots and chi-squared statistics have been commonly utilized to assess the validity of the conditional independence assumption and, when it does not hold, identify which test pairs are conditionally dependent. We aimed to assess the performance of these tools with a simulation study covering a wide range of scenarios.MethodsWe generated data sets from a model with four tests and a dependence between tests 1 and 2 within the diseased group. We varied sample size, prevalence, covariance, sensitivity and specificity, with 504 combinations of these in total, and 1000 data sets for each combination. We fitted the conditional independence model in a Bayesian framework, and reported absolute bias, coverage, and how often the residual correlation plots, G2 and χ2 statistics indicated lack-of-fit globally or for each test pair.ResultsAcross all settings, residual correlation plots, pairwise G2 and χ2 detected the correct correlated pair of tests only 12.1%, 10.3%, and 10.3% of the time, respectively, but incorrectly suggested dependence between tests 3 and 4 64.9%, 49.7%, and 49.5% of the time. We observed some variation in this across parameter settings, with these tools appearing to perform more as intended when tests 3 and 4 were both much more accurate than tests 1 and 2. Residual correlation plots, G2 and χ2 statistics identified a lack of overall fit in 74.3%, 64.5% and 67.5% of models, respectively. The conditional independence model tended to overestimate the sensitivities of the correlated tests (median bias across all scenarios 0.094, 2.5th and 97.5th percentiles -0.003, 0.397) and underestimate prevalence and the specificities of the uncorrelated tests.ConclusionsResidual correlation plots and chi-squared statistics cannot be relied upon to identify which tests are conditionally dependent, and also have relatively low power to detect lack of overall fit. This is important since failure to account for conditional dependence can lead to highly biased parameter estimates.

SHAP-Instance Weighted and Anchor Explainable AI: Enhancing XGBoost for Financial Fraud Detection

This research aims to enhance financial fraud detection by integrating SHAP-Instance Weighting and Anchor Explainable AI with XGBoost, addressing challenges of class imbalance and model interpretability. The study extends SHAP values beyond feature importance to instance weighting, assigning higher weights to more influential instances. This focuses model learning on critical samples. It combines this with Anchor Explainable AI to generate interpretable if-then rules explaining model decisions. The approach is applied to a dataset of financial statements from the listed companies on the Stock Exchange of Thailand. The method significantly improves fraud detection performance, achieving perfect recall for fraudulent instances and substantial gains in accuracy while maintaining high precision. It effectively differentiates between non-fraudulent, fraudulent, and grey area cases. The generated rules provide transparent insights into model decisions, offering nuanced guidance for risk management and compliance. This research introduces instance weighting based on SHAP values as a novel concept in financial fraud detection. By simultaneously addressing class imbalance and interpretability, the integrated approach outperforms traditional methods and sets a new standard in the field. It provides a robust, explainable solution that reduces false positives and increases trust in fraud detection models. Doi: 10.28991/ESJ-2024-08-06-016 Full Text: PDF

Evaluation of a point-of-care immunochromatographic assay for enteric fever in Dhaka, Bangladesh: a prospective diagnostic accuracy study

There is a shortage of rapid, accurate, and low-cost assays for diagnosing enteric fever. The dual-path platform for typhoid (DPPT) assay had high accuracy in retrospective studies with banked plasma samples. We aimed to evaluate the diagnostic accuracy of the DPPT assay in a prospective study using fingerstick capillary blood. For this prospective diagnostic accuracy study, we enrolled children younger than 18years, who presented at the Bangladesh Shishu Hospital and Institute (Dhaka, Bangladesh) with at least 3days of fever. We collected blood and nasal swabs, and did the following assays to assess the accuracy of DPPT: blood culture, serological assays for typhoid fever (DPPT assay, Widal, and Test-it), and molecular assays to identify alternative aetiologies (eg, respiratory syncytial virus [RSV], influenza, dengue virus, and Rickettsia spp). The primary outcomes of the study were the sensitivity and specificity of the DPPT assay for diagnosis of enteric fever. We evaluated the accuracy of combined anti-haemolysin Eand anti-lipopolysaccharide IgA readings using the DPPT assay in distinguishing culture-confirmed enteric fever from alternative aetiologies using receiver operating characteristic area under the curve (AUC). Given the imperfect reference standard diagnostics for enteric fever, we used Bayesian latent class models, incorporating results from the typhoid and alternative aetiology diagnostics, to estimate the sensitivity and specificity of the DPPT assay. We also did subgroup analyses for the assay across multiple biological variables. Between Aug 17, 2021, and July 16, 2022, we enrolled 501participants who presented with at least 3days of fever. 223 (45%) of 501participants were female and 278 (55%) were male. 77participants had culture-confirmed enteric fever (62 Salmonella entericaserotype Typhi and 15 Salmonella entericaserotype Paratyphi A) and 70were culture-negative with PCR-confirmed alternative aetiology (34 influenza Aor B, 22dengue virus, seven Rickettsia spp, six RSV, and one participant co-infected with RSV and dengue virus). The AUC for DPPT on fingerstick capillary blood in distinguishing typhoid from alternative aetiologies was 0·969 (95% CI 0·943-0·994). In latent class analysis, the sensitivity of DPPT was 93%(95% credible interval [CrI] 87-97) and specificity was 89% (85-93). The balanced accuracy was higher for DPPT (91%, 95% CrI 87-94) than blood culture (81%, 78-85), Test-it (77%,74-79), or Widal (70%, 67-73). Assay performance did not vary by sex, age, duration of fever at presentation, antibiotic use before presentation, Salmonella serotype, or sample type. The point-of-care DPPT assay achieved high diagnostic accuracy for enteric fever in a highly endemic community. This assay has the potential to improve clinical outcomes for enteric fever, allowing rapid diagnosis and treatment, and could facilitate more appropriate antimicrobial use. National Institute of Health, Bill & Melinda Gates Foundation, and Child Health Research Foundation.

Patterns of HIV Treatment Preferences Among People With Diverse Demographic, Social, and Behavioral Characteristics Who Are Living With HIV in the United States.

New dosage form and frequency options may improve HIV treatment outcomes and reduce disparities in access and use. People with HIV in the United States completed a demographic and discrete choice experiment survey of preference for 13 hypothetical HIV treatment options: daily and weekly oral tablets; 1-, 3-, or 6-monthly injections by self or a health care provider (HCP); yearly implant; or combinations. Best-Worst Scaling and a latent class model were used to analyze overall preference choices and for groups of individuals with similar patterns of preferences; the model also predicted uptake of products. Among the diverse 829 respondents, weekly oral tablets and 6-monthly injections by an HCP were significantly more favored than daily oral tablets. Convenience of the treatment and being tired of taking pills were the top drivers of preference responses. Latent class analysis identified 4 groups of respondents with distinct preference patterns; approximately two-thirds belonged to groups strongly preferring products other than daily oral tablets. The modelled uptake of a weekly pill, yearly implant, 6-monthly HCP injection, oral daily pill, and 3-monthly HCP injections were 24%, 24%, 24%, 18%, and 11%, respectively. Patterns of HIV medication preference can inform development of new forms of HIV therapy products because the majority of patients do not prefer the currently most available treatment option of daily oral tablets. Looking beyond population-level preferences and into similar groups of people with HIV increases the ability to develop patient-centered products to fill gaps in care and increase treatment effectiveness.

Revealing accessibility disparities: A latent class analysis linking objective and subjective accessibility measures

The last decade denoted a growing interest in perceived accessibility, yet the link between perceived and objective accessibility measures is understudied. This paper aims to address accessibility poverty by identifying groups with different levels of perceived accessibility. To achieve this aim, we develop a latent class model that relates perceived accessibility patterns to social, transport, and geographical conditions encountered by individuals. To support the specification of the latent class model, we develop a theoretical framework that links transport, social, and geographical conditions with perceived inaccessibility. Data is obtained from the Dutch National Travel Survey, which includes information on travel patterns and preferences. In total, 20,020 participants are included in the analysis. The latent class model identified six social groups with varying levels of perceived accessibility. Notably, while 89% of the individuals perceive excellent accessibility, a minority of 11% experiences different forms of inaccessibility. In addition, the latent class model showed that social rather than transport or spatial conditions encountered by individuals determine perceived inaccessibility. The results lend support to tailored policies aimed at reducing accessibility poverty and social exclusion for specific segments of the population.

Statistical Learning Theory and Occam’s Razor: The Core Argument

Statistical learning theory is often associated with the principle of Occam’s razor, which recommends a simplicity preference in inductive inference. This paper distills the core argument for simplicity obtainable from statistical learning theory, built on the theory’s central learning guarantee for the method of empirical risk minimization. This core “means-ends” argument is that a simpler hypothesis class or inductive model is better because it has better learning guarantees; however, these guarantees are model-relative and so the theoretical push towards simplicity is checked by our prior knowledge.

Latent class choice models with an error structure: Investigating potential unobserved associations between latent segmentation and behavior generation

Latent class choice modeling has gained great popularity in the transportation and choice modeling communities across the years. However, discussion of principles associated with the specification of the class membership model has barely appeared in the literature. Related to this issue, this study questions whether one of the basic assumptions of latent class choice modeling, that of independence between latent segmentation and the behavior generation process, is tenable. We formulate latent class choice models where the unobserved influences on latent segmentation and behavior generation are correlated, by introducing an error structure reflecting that supposition. The proposed method is applied to two empirical settings. In the first application, the dependent variable is an ordinal variable measuring willingness to share autonomous vehicle rides with strangers. In the second application, the dependent variable is a binary indicator of whether a person has used ridehailing services for social purposes. In both applications, error correlations were statistically significant, indicating that the segmentation and behavior generation processes are jointly determined. Although goodness of fits and parameter estimates per se are similar to those of the standard latent class choice models for these particular applications, allowing an error structure leads to a subtle change in model implications. In particular, our scenario analyses, which present marginal effects, illustrate the value of the proposed model for considering jointness arising from correlated errors, in contrast to standard latent class models. Lastly, we propose several avenues for future research.

Male lone wolves and sociable females – Preferences for shared and AV transport services

This paper examines preferences for future transports, focusing specifically on shared transports and autonomous vehicles, in a national context. A choice experiment approach is applied in which respondents are asked to choose between individual and shared transport services, each associated with different attribute levels (driver/autonomous, waiting and travel times, and costs) for a trip to go grocery shopping. Data are analysed by applying latent class modelling, which facilitates the analysis of heterogeneity in preferences for the attributes across different groups in the sample. The results reveal three groups with considerable heterogeneity in preferences: the group accepting trade-offs, the lone-wolves, and the sociable. The trade-off group do not want to share transport, but are positive towards autonomous vehicles, and make trade-offs between these characteristics and costs. The members in the lone-wolves group are only concerned about not travelling in a shared transport. Members in the smallest sociable group are positive about sharing transports but reject autonomous vehicles. Women are overrepresented in the sociable group, as are people with environmental concern and those who lack a driver's licence. Overall, we find that a majority of the sample does not want to share transport services, which potentially constitutes a major challenge for policy makers regarding reaching environmental transport policy goals.