scholarly journals Variance constraints strongly influenced model performance in growth mixture modeling: a simulation and empirical study

2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Jitske J. Sijbrandij ◽  
Tialda Hoekstra ◽  
Josué Almansa ◽  
Margot Peeters ◽  
Ute Bültmann ◽  
...  
Keyword(s):  
Small Sample Size ◽  
Random Effect ◽  
Model Performance ◽  
Growth Mixture Modeling ◽  
Mixture Modeling ◽  
Small Sample ◽  
Growth Mixture ◽  
Variance Parameters ◽  
Residual Variances ◽  
Over Time

Abstract Background Growth Mixture Modeling (GMM) is commonly used to group individuals on their development over time, but convergence issues and impossible values are common. This can result in unreliable model estimates. Constraining variance parameters across classes or over time can solve these issues, but can also seriously bias estimates if variances differ. We aimed to determine which variance parameters can best be constrained in Growth Mixture Modeling. Methods To identify the variance constraints that lead to the best performance for different sample sizes, we conducted a simulation study and next verified our results with the TRacking Adolescent Individuals’ Lives Survey (TRAILS) cohort. Results If variance parameters differed across classes and over time, fitting a model without constraints led to the best results. No constrained model consistently performed well. However, the model that constrained the random effect variance and residual variances across classes consistently performed very poorly. For a small sample size (N = 100) all models showed issues. In TRAILS, the same model showed substantially different results from the other models and performed poorly in terms of model fit. Conclusions If possible, a Growth Mixture Model should be fit without any constraints on variance parameters. If not, we recommend to try different variance specifications and to not solely rely on the default model, which constrains random effect variances and residual variances across classes. The variance structure must always be reported Researchers should carefully follow the GRoLTS-Checklist when analyzing and reporting trajectory analyses.

scholarly journals Trajectories of Distress Following the Great East Japan Earthquake: A Multiwave Prospective Study

2020 ◽  
Vol 8 (6) ◽  
pp. 1062-1068
Author(s):  
Robin Goodwin ◽  
Kemmyo Sugiyama ◽  
Shaojing Sun ◽  
Masahito Takahashi ◽  
Jun Aida
Keyword(s):  
Social Support ◽  
Psychological Distress ◽  
Growth Mixture Modeling ◽  
Mixture Modeling ◽  
Great East Japan Earthquake ◽  
Targeted Intervention ◽  
Growth Mixture ◽  
Recovery Group ◽  
Time Specific ◽  
Over Time

The March 2011 Great East Japan Earthquake, tsunami, and nuclear leak were complex traumas. We examined psychological distress in the years following the earthquake using growth mixture modeling to classify responses from 2,599 linked respondents (2012–2016). We identified four classes of trajectories following the disaster: resilient (76% of respondents), delayed distress (8%), recovery (8%), and chronic distress (7%). Compared with the resilient class, other class members were less likely to be female and had less social support. Survivors in the recovery group were more likely to live in prefabricated housing. Although distress has decreased over time, specific populations continue to require targeted intervention.

scholarly journals Associations Between Engagement and Outcomes in the SmokefreeTXT Program: A Growth Mixture Modeling Analysis

2018 ◽  
Vol 21 (5) ◽  
pp. 663-669 ◽  
Author(s):  
Kisha I Coa ◽  
Kara P Wiseman ◽  
Bryan Higgins ◽  
Erik Augustson
Keyword(s):  
Smoking Cessation ◽  
Real World ◽  
Text Messaging ◽  
Growth Mixture Modeling ◽  
Mixture Modeling ◽  
The Other ◽  
Potential Effectiveness ◽  
Growth Mixture ◽  
The Impact ◽  
Over Time

Abstract Introduction Smoking continues to be a leading cause of preventable death. Mobile health (mHealth) can extend the reach of smoking cessation programs; however, user dropout, especially in real-world implementations of these programs, limit their potential effectiveness. Research is needed to understand patterns of engagement in mHealth cessation programs. Methods SmokefreeTXT (SFTXT) is the National Cancer Institute’s 6–8 week smoking cessation text-messaging intervention. Latent growth mixture modeling was used to identify unique classes of engagement among SFTXT users using real-world program data from 7090 SFTXT users. Survival analysis was conducted to model program dropout over time by class, and multilevel modeling was used to explore differences in abstinence over time. Results We identified four unique patterns of engagement groups. The largest percentage of users (61.6%) were in the low-engagers declining group; these users started off with low level of engagement and their engagement decreased over time. Users in this group were more likely to drop out from the program and less likely to be abstinent than users in the other groups. Users in the high engagers–maintaining group (ie, the smallest but most engaged group) were less likely to be daily smokers at baseline and were slightly older than those in the other groups. They were most likely to complete the program and report being abstinent. Conclusions Our findings show the importance of maintaining active engagement in text-based cessation programs. Future research is needed to elucidate predictors of the various levels of engagement, and to assess whether strategies aimed at increasing engagement result in higher abstinence rates. Implications The current study enabled us to investigate differing engagement patterns in non-incentivized program participants, which can help inform program modifications in real-world settings. Lack of engagement and dropout continue to impede the potential effectiveness of mHealth interventions, and understanding patterns and predictors of engagement can enhance the impact of these programs.

Social stressors and irritability over time: Modeling the relationship via growth mixture modeling

2013 ◽  
Author(s):  
Ivana Igic ◽  
Norbert K. Semmer ◽  
Anita Keller ◽  
Wolfgang Kalin ◽  
Achim Elfering ◽  
...  
Keyword(s):  
Growth Mixture Modeling ◽  
Mixture Modeling ◽  
Social Stressors ◽  
Growth Mixture ◽  
Time Modeling ◽  
The Relationship ◽  
Over Time

Identifying subgroups: Part 2: Trajectories of change over time

2020 ◽  
Vol 19 (5) ◽  
pp. 444-450
Author(s):  
Christopher S Lee ◽  
Kenneth M Faulkner ◽  
Jessica H Thompson
Keyword(s):  
Growth Mixture Modeling ◽  
Mixture Modeling ◽  
Latent Growth ◽  
Change Over Time ◽  
Growth Mixture ◽  
Worked Example ◽  
Latent Growth Mixture Modeling ◽  
Trajectories Of Change ◽  
Analytic Strategy ◽  
Over Time

Methods to identify multiple trajectories of change over time are of great interest in nursing and in related health research. Latent growth mixture modeling is a data-centered analytic strategy that allows us to study questions about distinct trajectories of change in key measures or outcomes of interest. In this article, a worked example of latent growth mixture modeling is presented to help expose researchers to the use and appeal of this analytic strategy.

Die Identifikation früher Veränderungsmuster in der ambulanten Psychotherapie

2007 ◽  
Vol 36 (2) ◽  
pp. 93-104 ◽  
Author(s):  
Wolfgang Lutz ◽  
Niklaus Stulz ◽  
David W. Smart ◽  
Michael J. Lambert
Keyword(s):  
Growth Mixture Modeling ◽  
Mixture Modeling ◽  
Growth Mixture

Zusammenfassung. Theoretischer Hintergrund: Im Rahmen einer patientenorientierten Psychotherapieforschung werden Patientenausgangsmerkmale und Veränderungsmuster in einer frühen Therapiephase genutzt, um Behandlungsergebnisse und Behandlungsdauer vorherzusagen. Fragestellung: Lassen sich in frühen Therapiephasen verschiedene Muster der Veränderung (Verlaufscluster) identifizieren und durch Patientencharakteristika vorhersagen? Erlauben diese Verlaufscluster eine Vorhersage bezüglich Therapieergebnis und -dauer? Methode: Anhand des Growth Mixture Modeling Ansatzes wurden in einer Stichprobe von N = 2206 ambulanten Patienten einer US-amerikanischen Psychotherapieambulanz verschiedene latente Klassen des frühen Therapieverlaufs ermittelt und unter Berücksichtigung unterschiedlicher Patientenausgangscharakteristika als Prädiktoren der frühen Veränderungen mit dem Therapieergebnis und der Therapiedauer in Beziehung gesetzt. Ergebnisse: Für leicht, mittelschwer und schwer beeinträchtigte Patienten konnten je vier unterschiedliche Verlaufscluster mit jeweils spezifischen Prädiktoren identifiziert werden. Die Identifikation der frühen Verlaufsmuster ermöglichte weiterhin eine spezifische Vorhersage für die unterschiedlichen Verlaufscluster bezüglich des Therapieergebnisses und der Therapiedauer. Schlussfolgerungen: Frühe Psychotherapieverlaufsmuster können einen Beitrag zu einer frühzeitigen Identifikation günstiger sowie ungünstiger Therapieverläufe leisten.

scholarly journals The incidence and prevalence of cardiovascular diseases in gout: a systematic review and meta-analysis

2021 ◽  
Author(s):  
Peter Cox ◽  
Sonal Gupta ◽  
Sizheng Steven Zhao ◽  
David M. Hughes
Keyword(s):  
Systematic Review ◽  
Cardiovascular Disease ◽  
Cardiovascular Risk ◽  
Cardiovascular Diseases ◽  
Small Sample Size ◽  
Meta Analysis ◽  
Random Effect ◽  
Small Sample ◽  
Future Research ◽  
Increased Risk

AbstractThe aims of this systematic review and meta-analysis were to describe prevalence of cardiovascular disease in gout, compare these results with non-gout controls and consider whether there were differences according to geography. PubMed, Scopus and Web of Science were systematically searched for studies reporting prevalence of any cardiovascular disease in a gout population. Studies with non-representative sampling, where a cohort had been used in another study, small sample size (< 100) and where gout could not be distinguished from other rheumatic conditions were excluded, as were reviews, editorials and comments. Where possible meta-analysis was performed using random-effect models. Twenty-six studies comprising 949,773 gout patients were included in the review. Pooled prevalence estimates were calculated for five cardiovascular diseases: myocardial infarction (2.8%; 95% confidence interval (CI)s 1.6, 5.0), heart failure (8.7%; 95% CI 2.9, 23.8), venous thromboembolism (2.1%; 95% CI 1.2, 3.4), cerebrovascular accident (4.3%; 95% CI 1.8, 9.7) and hypertension (63.9%; 95% CI 24.5, 90.6). Sixteen studies reported comparisons with non-gout controls, illustrating an increased risk in the gout group across all cardiovascular diseases. There were no identifiable reliable patterns when analysing the results by country. Cardiovascular diseases are more prevalent in patients with gout and should prompt vigilance from clinicians to the need to assess and stratify cardiovascular risk. Future research is needed to investigate the link between gout, hyperuricaemia and increased cardiovascular risk and also to establish a more thorough picture of prevalence for less common cardiovascular diseases.

A Monte Carlo evaluation of growth mixture modeling

2021 ◽  
pp. 1-14
Author(s):  
Tiffany M. Shader ◽  
Theodore P. Beauchaine
Keyword(s):  
Monte Carlo ◽  
Growth Mixture Modeling ◽  
Mixture Modeling ◽  
Fit Indices ◽  
Linear Quadratic ◽  
Growth Mixture ◽  
True Number ◽  
Monte Carlo Evaluation ◽  
Wrong Number ◽  
State Of Affairs

Abstract Growth mixture modeling (GMM) and its variants, which group individuals based on similar longitudinal growth trajectories, are quite popular in developmental and clinical science. However, research addressing the validity of GMM-identified latent subgroupings is limited. This Monte Carlo simulation tests the efficiency of GMM in identifying known subgroups (k = 1–4) across various combinations of distributional characteristics, including skew, kurtosis, sample size, intercept effect size, patterns of growth (none, linear, quadratic, exponential), and proportions of observations within each group. In total, 1,955 combinations of distributional parameters were examined, each with 1,000 replications (1,955,000 simulations). Using standard fit indices, GMM often identified the wrong number of groups. When one group was simulated with varying skew and kurtosis, GMM often identified multiple groups. When two groups were simulated, GMM performed well only when one group had steep growth (whether linear, quadratic, or exponential). When three to four groups were simulated, GMM was effective primarily when intercept effect sizes and sample sizes were large, an uncommon state of affairs in real-world applications. When conditions were less ideal, GMM often underestimated the correct number of groups when the true number was between two and four. Results suggest caution in interpreting GMM results, which sometimes get reified in the literature.

Sign in / Sign up

Export Citation Format

Share Document