surveymixr: Growth Mixture Models with Complex Survey Design

The surveymixr package implements growth mixture modeling for longitudinal data with full integration of complex survey design features including stratification, clustering, and probability weights.

Details

Growth mixture models identify latent classes with distinct developmental trajectories. This package enables such analyses with proper handling of complex survey data from studies like the Millennium Cohort Study, Add Health, NLSY, and others.

Key Features

Complex survey integration (stratification, clustering, weights)
Bootstrap Likelihood Ratio Test (BLRT) for class enumeration
R3STEP method for auxiliary variable analysis
Multiple random starts (500-1000+) with parallel processing
Sandwich standard errors for survey designs
Comprehensive convergence diagnostics
Publication-ready visualization

Main Functions

gmm_survey: Fit growth mixture model with survey design
gmm_select: Model selection across class solutions
r3step: Auxiliary variable analysis with classification correction
simulate_gmm_survey: Simulate data for testing and validation
diagnose_convergence: Convergence diagnostics
plot_trajectories: Visualize growth trajectories

Getting Started

See vignette("surveymixr-intro") for a comprehensive introduction with examples.

Quick example:


library(surveymixr)

# Simulate data for demonstration
sim_data <- simulate_gmm_survey(
  n_individuals = 500,
  n_times = 4,
  n_classes = 3
)

# Fit 3-class model
fit <- gmm_survey(
  data = sim_data,
  id = "id",
  time = "time",
  outcome = "outcome",
  n_classes = 3,
  strata = "stratum",
  cluster = "psu",
  weights = "weight",
  starts = 100
)

summary(fit)
plot(fit)

References

Muthén, B. (2004). Latent variable analysis: Growth mixture modeling and related techniques for longitudinal data. In D. Kaplan (Ed.), Handbook of quantitative methodology for the social sciences (pp. 345-368). Sage Publications.

Asparouhov, T., & Muthén, B. (2014). Auxiliary variables in mixture modeling: Three-step approaches using Mplus. Structural Equation Modeling, 21(3), 329-341.

Nylund, K. L., Asparouhov, T., & Muthén, B. O. (2007). Deciding on the number of classes in latent class analysis and growth mixture modeling. Structural Equation Modeling, 14(4), 535-569.

Author

Siyang Ni johnni.nj@gmail.com