cluster_mmm: Cluster sequences using Mixed Markov Models

In Nestimate: Network Estimation, Bootstrap, and Higher-Order Analysis

Cluster sequences using Mixed Markov Models

Description

Fits a mixture of Markov chains to sequence data and returns a netobject_group containing per-cluster transition networks. This is the MMM equivalent of cluster_network (which uses distance-based clustering); both functions share the cluster_by = ... surface argument so the call shape stays uniform across clustering families.

Usage

cluster_mmm(
  data,
  k = 2L,
  n_starts = 50L,
  max_iter = 200L,
  tol = 1e-06,
  smooth = 0.01,
  seed = NULL,
  covariates = NULL,
  covariate_effect = c("em", "posthoc"),
  estimator = c("auto", "firth", "multinom", "chisq"),
  cluster_by = "mmm",
  ...
)

Arguments

data	A data.frame (wide format), netobject, or tna model. For tna objects, extracts the stored data.
k	Integer. Whole finite number of mixture components, >= 2. Default: 2.
n_starts	Integer. Positive whole finite number of random restarts. Default: 50.
max_iter	Integer. Positive whole finite maximum EM iterations per start. Default: 200.
tol	Numeric. Finite positive convergence tolerance. Default: 1e-6.
smooth	Numeric. Finite non-negative Laplace smoothing constant. Default: 0.01.
seed	Integer or NULL. Random seed.
covariates	Optional. Covariates integrated into the EM algorithm to model covariate-dependent mixing proportions. Accepts a string, character vector, formula, or data.frame (same forms as build_clusters). For netobject or cograph_network input, names are resolved against $metadata first, so a typical call is build_mmm(net, k = 3, covariates = "session_label"). Unlike the post-hoc analysis in build_clusters(), these covariates directly influence cluster membership during EM estimation (see covariate_effect).
covariate_effect	How covariates enter the model. "em" (default) folds them into the EM as covariate-dependent mixing proportions, so they shape the cluster fit itself (and rows with missing covariates are dropped before fitting). "posthoc" fits a plain mixture on every sequence and uses the covariates only for the after-fit multinomial logit, so covariate values — and their missingness — never change which clusters are found. Ignored when covariates is NULL.
estimator	Multinomial fitter for the post-hoc covariate analysis (does not affect EM): "auto" (default) inspects the cluster x covariate cross-tab and falls back to "firth" only when any cell has fewer than 5 observations (separation risk), otherwise the much faster "multinom"; "firth" forces Firth's penalised likelihood via brglm2::brmultinom (finite under separation); "multinom" forces nnet::multinom (warns about separation risk); "chisq" runs descriptive tests (no logit). See build_clusters for full details.
cluster_by	Character. Accepted only as "mmm" (the default). Present so cluster_mmm() and cluster_network() share the same call shape; any other value raises an error pointing at cluster_network.
...	Unsupported. Supplying unused arguments raises an error.

Details

For the full net_mmm object with posterior probabilities, model fit statistics, and S3 methods, use build_mmm instead.

Value

A netobject_group (list of netobjects, one per cluster). MMM-specific information is stored in attr(, "clustering") (class "net_mmm_clustering"):

assignments

Integer vector of cluster assignments.

k

Number of clusters.

posterior

N x k matrix of posterior probabilities.

mixing

Mixing proportions.

quality

List with AvePP, entropy, classification error.

BIC, AIC, ICL

Model fit statistics.

data

The full N-row sequence frame, matching $assignments – so sequence_plot and distribution_plot can recover both.

See Also

build_mmm for the full MMM object, cluster_network for distance-based clustering

Examples

seqs <- data.frame(V1 = sample(c("A","B","C"), 30, TRUE),
                   V2 = sample(c("A","B","C"), 30, TRUE))
grp <- cluster_mmm(seqs, k = 2, n_starts = 1, max_iter = 10, seed = 1)
grp[[1]]$weights
attr(grp, "clustering")$assignments

# Visualise with sequence_plot
seqs <- data.frame(
  V1 = sample(LETTERS[1:3], 40, TRUE),
  V2 = sample(LETTERS[1:3], 40, TRUE),
  V3 = sample(LETTERS[1:3], 40, TRUE)
)
grp <- cluster_mmm(seqs, k = 2)
sequence_plot(grp, type = "index")

Nestimate documentation built on July 11, 2026, 1:09 a.m.