Clustering of longitudinal data: A tutorial on a variety of approaches (2021-11-10T00:00:00.000000Z)

TL;DR

A selection of methods that take different approaches to clustering longitudinal data, based on cross‐sectional clustering, distance‐based clustering, feature‐based clustering, feature‐based clustering, and mixture modeling are presented.

Abstract

During the past two decades, methods for identifying groups with different trends in longitudinal data involving a single numeric outcome have become of increasing interest across many areas of research. To support researchers, we summarize the guidance from literature regarding the clustering of such data. Moreover, we present a selection of methods that take different approaches to clustering longitudinal data, based on cross‐sectional clustering, distance‐based clustering, feature‐based clustering, and mixture modeling. The methods are introduced at a basic level, and strengths, limitations, and model extensions are listed. Following the recent developments in data collection, attention is given to the applicability of these methods to intensive longitudinal data (ILD). We demonstrate the application of the methods on a synthetic dataset using packages available in R.

Authors

N. D. Teuling

1 papers

S. Pauws

1 papers

E. Heuvel

1 papers

TL;DR

Abstract

Authors

References176 items

Recent Advances in Group-Based Trajectory Modeling for Clinical Research.

Clustering longitudinal data using R: A Monte Carlo Study

Development of a Mixture Model (SMM) Allowing for Smoothing Functions of Trajectories

Covariance pattern mixture models: Eliminating random effects to improve convergence and performance

A review of psychosocial factors and personality in the treatment of obstructive sleep apnoea

Finite mixture of varying coefficient model: Estimation and component selection

Statistical Analysis with Missing Data, Third Edition

A novel methodological framework for multimodality, trajectory model-based prognostication.

On the performance of MixTVEM: a simulation study

Latent Class Trees with the Three-Step Approach

Using the Beta distribution in group-based trajectory models

Piecewise Growth Mixture Model with More than One Unknown Knot: An Application in Reading Development.

Cluster analysis for repeated data with dropout: Sensitivity analysis using a distal event

Statistical Inference and Applications of Mixture of Varying Coefficient Models

Group-based multi-trajectory modeling

Framework to construct and interpret latent class trajectory modelling

Building Latent Class Growth Trees

Class Identification Efficacy in Piecewise GMM with Unknown Turning Points

Analyzing Longitudinal Data Using Natural Cubic Smoothing Splines

A Comparison of One-Step and Three-Step Approaches for Including Covariates in the Shared Parameter Growth Mixture Model

Person‐specific versus multilevel autoregressive models: Accuracy in parameter estimates at the population and individual levels

Detecting Multiple Random Changepoints in Bayesian Piecewise Growth Mixture Models

Introducing the fit-criteria assessment plot – A visualisation tool to assist class enumeration in group-based trajectory modelling

brms: An R Package for Bayesian Multilevel Models Using Stan

Nonlinear Growth Mixture Models With Fractional Polynomials: An Illustration With Early Childhood Mathematics Ability

The Effect of Model Misspecification on Growth Mixture Model Class Enumeration

Extending Growth Mixture Models Using Continuous Non-Elliptical Distributions

Model Selection in Finite Mixture Models: A k-Fold Cross-Validation Approach

Comparison of Criteria for Choosing the Number of Classes in Bayesian Finite Mixture Models

Stan: A Probabilistic Programming Language.

Just Another Gibbs Sampler (JAGS)

The relationship between multilevel models and non-parametric multilevel mixture models: Discrete approximation of intraclass correlation, random coefficient distributions, and residual heteroscedasticity.

Additional Information: The GRoLTS-checklist: Guidelines for Reporting on Latent Trajectory Studies

A Dirichlet process mixture model for clustering longitudinal gene expression data

Fitting Unstructured Finite Mixture Models in Longitudinal Design: A Recommendation for Model Selection and Estimation of the Number of Classes

mclust 5: Clustering, Classification and Density Estimation Using Gaussian Finite Mixture Models

Using Group-Based Trajectory and Growth Mixture Modeling to Identify Classes of Change Trajectories

Smoothing Group-Based Trajectory Models Through B-Splines

Criminal Careers: Discrete or Continuous?

Time-series clustering - A decade review

Modeling intensive longitudinal data with mixtures of nonparametric trajectories and time-varying effects.

Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC

Time series analysis for psychological research: examining and forecasting change

kml and kml3d: R Packages to Cluster Longitudinal Data

Pre- and in-therapy predictive score models of adult OSAS patients with poor adherence pattern on nCPAP therapy

Evaluation of a Bayesian Approach to Estimating Nonlinear Mixed-Effects Mixture Models

Growth Mixture Models Outperform Simpler Clustering Algorithms When Detecting Longitudinal Heterogeneity, Even With Small Sample Sizes

A comparison of indices for identifying the number of clusters in hierarchical clustering: A study on cognition in schizophrenia patients

Growth mixture modeling with non‐normal distributions

Estimation of extended mixed models using latent classes and latent processes: the R package lcmm

Group-based modeling of ecological trajectories in restored wetlands.

Identifying Longitudinal Patterns for Individuals and Subgroups: An Example with Adherence to Treatment for Obstructive Sleep Apnea

Latent class analysis was accurate but sensitive in data simulations

Capabilities of R Package mixAK for Clustering Based on Multivariate Continuous and Discrete Longitudinal Data

Model-based clustering based on sparse finite Gaussian mixtures

Bayesian analysis of nonlinear mixed‐effects mixture models for longitudinal data with heterogeneity and skewness

Auxiliary Variables in Mixture Modeling: Three-Step Approaches Using Mplus

Group-based Criminal Trajectory Analysis Using Cross-validation Criteria

The deviance information criterion: 12 years on

Modeling Change in the Presence of Nonrandomly Missing Data: Evaluating a Shared Parameter Mixture Model

Heterogeneity of treatment changes after psychodynamic therapy within a one year follow-up: a replication study.

Typology of alcohol users based on longitudinal patterns of drinking.

Highly Comparative Feature-Based Time-Series Classification

Modeling Unobserved Heterogeneity Using Latent Profile Analysis: A Monte Carlo Simulation

Group-based Trajectory Models: A New Approach to Classifying and Predicting Long-Term Medication Adherence

Estimating the Association between Latent Class Membership and External Variables Using Bias-adjusted Three-step Approaches

Highly comparative time-series analysis: the empirical structure of time series and their methods

Mixture class recovery in GMM under varying degrees of class separation: frequentist versus Bayesian estimation.

Clustering in linear mixed models with approximate Dirichlet process mixtures using EM algorithm

Classifying developmental trajectories over time should be done with great caution: a comparison between methods.

Factors Affecting the Adequacy and Preferability of Semiparametric Groups-Based Approximations of Continuous Growth Trajectories

A Note on a Stata Plugin for Estimating Group-based Trajectory Models

Investigating Stage-Sequential Growth Mixture Models with Multiphase Longitudinal Data

Finite mixture varying coefficient models for analyzing longitudinal heterogenous data

A time-varying effect model for intensive longitudinal data.

Poisson Growth Mixture Modeling of Intensive Longitudinal Data: An Application to Smoking Cessation Behavior