ED 06-2 AN INTRODUCTION TO LATENT CLASS METHODS FOR LONGITUDINAL DATA

2016 ◽  
Vol 34 (Supplement 1) ◽  
pp. e188
Author(s):  
Juned Siddique
Keyword(s):  
Longitudinal Data ◽  
Latent Class ◽  
Latent Class Methods

scholarly journals E-bike user groups and substitution effects: evidence from longitudinal travel data in the Netherlands

2021 ◽  
Author(s):  
Mathijs de Haas ◽  
Maarten Kroesen ◽  
Caspar Chorus ◽  
Sascha Hoogendoorn-Lanser ◽  
Serge Hoogendoorn
Keyword(s):  
The Netherlands ◽  
Longitudinal Data ◽  
Latent Class ◽  
Good Alternative ◽  
Substitution Effects ◽  
Or Education ◽  
Cross Sectional ◽  
User Groups ◽  
Using Data ◽  
Mode Of Transport

AbstractIn recent years, the e-bike has become increasingly popular in many European countries. With higher speeds and less effort needed, the e-bike is a promising mode of transport to many, and it is considered a good alternative for certain car trips by policy-makers and planners. A major limitation of many studies that investigate such substitution effects of the e-bike, is their reliance on cross-sectional data which do not allow an assessment of within-person travel mode changes. As a consequence, there is currently no consensus about the e-bike’s potential to replace car trips. Furthermore, there has been little research focusing on heterogeneity among e-bike users. In this respect, it is likely that different groups exist that use the e-bike for different reasons (e.g. leisure vs commute travel), something which will also influence possible substitution patterns. This paper contributes to the literature in two ways: (1) it presents a statistical analysis to assess the extent to which e-bike trips are substituting trips by other travel modes based on longitudinal data; (2) it reveals different user groups among the e-bike population. A Random Intercept Cross-Lagged Panel Model is estimated using five waves of data from the Netherlands Mobility Panel. Furthermore, a Latent Class Analysis is performed using data from the Dutch national travel survey. Results show that, when using longitudinal data, the substitution effects between e-bike and the competing travel modes of car and public transport are not as significant as reported in earlier research. In general, e-bike trips only significantly reduce conventional bicycle trips in the Netherlands, which can be regarded an unwanted effect from a policy-viewpoint. For commuting, the e-bike also substitutes car trips. Furthermore, results show that there are five different user groups with their own distinct behaviour patterns and socio-demographic characteristics. They also show that groups that use the e-bike primarily for commuting or education are growing at a much higher rate than groups that mainly use the e-bike for leisure and shopping purposes.

Bayesian nonparametric latent class model for longitudinal data

2020 ◽  
Vol 29 (11) ◽  
pp. 3381-3395
Author(s):  
Wonmo Koo ◽  
Heeyoung Kim
Keyword(s):  
Longitudinal Data ◽  
Latent Class ◽  
Latent Class Model ◽  
Latent Class Models ◽  
Model Parameters ◽  
Latent Classes ◽  
Bayesian Nonparametric ◽  
Class Model ◽  
Proposed Model ◽  
Class Models

Latent class models have been widely used in longitudinal studies to uncover unobserved heterogeneity in a population and find the characteristics of the latent classes simultaneously using the class allocation probabilities dependent on predictors. However, previous latent class models for longitudinal data suffer from uncertainty in the choice of the number of latent classes. In this study, we propose a Bayesian nonparametric latent class model for longitudinal data, which allows the number of latent classes to be inferred from the data. The proposed model is an infinite mixture model with predictor-dependent class allocation probabilities; an individual longitudinal trajectory is described by the class-specific linear mixed effects model. The model parameters are estimated using Markov chain Monte Carlo methods. The proposed model is validated using a simulated example and a real-data example for characterizing latent classes of estradiol trajectories over the menopausal transition using data from the Study of Women’s Health Across the Nation.

scholarly journals Bayesian Latent-Class Mixed-Effect Hybrid Models for Dyadic Longitudinal Data with Non-Ignorable Dropouts

Biometrics ◽  
2013 ◽  
Vol 69 (4) ◽  
pp. 914-924 ◽  
Author(s):  
Jaeil Ahn ◽  
Suyu Liu ◽  
Wenyi Wang ◽  
Ying Yuan
Keyword(s):  
Longitudinal Data ◽  
Latent Class ◽  
Hybrid Models ◽  
Mixed Effect

scholarly journals Evaluating and optimizing the use of diagnostics during epidemics: Application to the 2017 plague outbreak in Madagascar

2021 ◽  
Author(s):  
Quirine Bosch ◽  
Voahangy Andrianaivoarimanana ◽  
Beza Ramasindrazana ◽  
Guillain Mikaty ◽  
Rado JL Rakotonanahary ◽  
...  
Keyword(s):  
Yersinia Pestis ◽  
Test Performance ◽  
Diagnostic Tests ◽  
Latent Class ◽  
Clinical Presentation ◽  
Analytical Framework ◽  
Rural Settings ◽  
Latent Class Methods ◽  
Diagnostic Outcomes ◽  
Case Classification

During outbreaks, the lack of diagnostic “gold standard” can mask the true burden of infection in the population and hamper the allocation of resources required for control. Here, we present an analytical framework to evaluate and optimize the use of diagnostics when multiple yet imperfect diagnostic tests are available. We apply it to laboratory results of 2,136 samples, analyzed with three diagnostic tests (based on up to seven diagnostic outcomes), collected during the 2017 pneumonic (PP) and bubonic plague (BP) outbreak in Madagascar, which was unprecedented both in the number of notified cases, clinical presentation, and spatial distribution. The extent of this outbreaks has however remained unclear due to non-optimal assays. Using latent class methods, we estimate that 7%-15% of notified cases were Yersinia pestis-infected. Overreporting was highest during the peak of the outbreak and lowest in the rural settings endemic to Yersinia pestis. Molecular biology methods offered the best compromise between sensitivity and specificity. The specificity of the rapid diagnostic test was relatively low (PP: 82%, BP: 85%), particularly for use in contexts with large quantities of misclassified cases. Comparison with data from a subsequent seasonal Yersinia pestis outbreak in 2018 reveal better test performance (BP: specificity 99%, sensitivity: 91%), indicating that factors related to the response to a large, explosive outbreak may well have affected test performance. We used our framework to optimize the case classification and derive consolidated epidemic trends. Our approach may help reduce uncertainties in other outbreaks where diagnostics are imperfect.

scholarly journals Youth in a pandemic: a longitudinal examination of youth mental health and substance use concerns during COVID-19

BMJ Open ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. e049209
Author(s):  
Lisa D Hawke ◽  
Peter Szatmari ◽  
Kristin Cleverley ◽  
Darren Courtney ◽  
Amy Cheung ◽  
...  
Keyword(s):  
Mental Health ◽  
Substance Use ◽  
Longitudinal Data ◽  
Young Women ◽  
Latent Class ◽  
Youth Mental Health ◽  
Health Concerns ◽  
Response Strategies ◽  
Mood Symptoms ◽  
Mental Health Concerns

ObjectiveThis study analyses longitudinal data to understand how youth mental health and substance use are evolving over the course of the COVID-19 pandemic, which is critical to adjusting mental health response strategies.SettingParticipants were recruited from among existing participants in studies conducted in an urban academic hospital in Ontario, Canada.ParticipantsA total of 619 youth aged 14–28 years participated in the study (62.7% girls/young women; 61.4% Caucasian).MeasuresData on mood, substance use and COVID-19-related worries were collected over four time points, that is, every 2 months beginning in the early stages of the pandemic in April 2020. Latent class analyses were conducted on the longitudinal data to identify distinct groups of youth who have different trajectory profiles of pandemic impact on their mood, substance use and COVID-19-related worries.ResultsFor the majority of participants, mood concerns increased early in the pandemic, declined over Canada’s summer months and subsequently increased in autumn. Among the youth with the highest level of mood symptoms at the beginning of the pandemic, increases in mental health concerns were sustained. Substance use remained relatively stable over the course of the pandemic. COVID-19-related worries, however, followed a trajectory similar to that of mood symptoms. Girls/young women, youth living in urban or suburban areas, in larger households, and with poorer baseline mental and physical health are the most vulnerable to mental health concerns and worries during the pandemic.ConclusionsYouth mental health symptom levels and concerns are evolving over the course of the COVID-19 pandemic, in line with the evolution of the pandemic itself, and longitudinal monitoring is therefore required. It is also essential that we engage directly with youth to cocreate pandemic response strategies and mental health service adaptations to best meet the needs of young people.

scholarly journals Joint latent class model for longitudinal data and interval‐censored semi‐competing events: Application to dementia

Biometrics ◽  
2016 ◽  
Vol 72 (4) ◽  
pp. 1123-1135 ◽  
Author(s):  
Anaïs Rouanet ◽  
Pierre Joly ◽  
Jean‐François Dartigues ◽  
Cécile Proust‐Lima ◽  
Hélène Jacqmin‐Gadda
Keyword(s):  
Longitudinal Data ◽  
Latent Class ◽  
Latent Class Model ◽  
Class Model ◽  
Interval Censored ◽  
Competing Events

Cancer patients’ trade-offs for efficacy, toxicity, and cost.

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. 6021-6021
Author(s):  
Yu-Ning Wong ◽  
Brian Egleston ◽  
Kush Sachdeva ◽  
Olivia Hamilton ◽  
Naa Eghan ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Cost Sharing ◽  
Latent Class ◽  
Individual Characteristics ◽  
Health Plans ◽  
Trade Offs ◽  
Costly Treatment ◽  
College Educated ◽  
Latent Class Methods ◽  
Out Of Pocket Costs

6021 Background: When making treatment decisions, cancer patients (pts) must make trade-offs between efficacy, toxicity (tox) and cost. However, little is known about how individual characteristics influence these decisions, particularly as many face high out of pocket costs. Methods: We presented cancer pts with hypothetical scenarios that asked them to choose between 2 treatments of varying levels of efficacy, tox and cost. Each scenario included 9 choice pairs. Pts were given 2 of 3 scenarios described in the Table. Tox was also varied. Demographics, cost concerns and numeracy were assessed. Within each scenario, we used latent class methods to distinguish pt groups with discrete preferences. We then used regressions with group membership probabilities as covariates to identify associations. Results: We enrolled 400 pts. Median age was 61 years (range 27-90). 63% were female. 41% were college educated. 51% had an annual income ≥$60K. 25% were enrolled at a community hospital. 98% were insured. Within each of the 3 scenarios, we identified 3 pt classes with preferences for survival or aversion to high cost or toxicity. Across each of the scenarios, <6% of pts in the group averse to high cost chose the costlier treatment. >92% of pts in the group that favored survival chose the highest efficacy treatment. >65% of pts in the group with aversion to tox chose the lower tox treatment. Within each of the scenarios, pts in the group with preference for survival were more likely to have an income of >$60K (p<.05) and greater numeracy skills (p<.05). In scenarios 2 and 3, pts with concerns about treatment costs were more likely to be in the class that was averse to high cost (p<.05 for both). Conclusions: Even in hypothetical scenarios presented to insured pts, socioeconomic status was predictive of treatment choice. Higher income pts may be more likely to focus on survival when making decisions while those with greater cost concerns may be more likely to avoid costly treatment, regardless of survival or tox. This raises the possibility that health plans with greater cost-sharing may have the unintended consequence of increasing disparities in care. [Table: see text]

Sign in / Sign up

Export Citation Format

Share Document