Package index • tseLCA

One-call interface

Fit a complete three-step model from one formula.

tseLCA(): Three-step latent class analysis in one call
measurement() classification() covariate() distal(): Components of a fitted tseLCA model

Estimate the latent classes and choose the number of classes.

tse_lca(): Fit a latent class measurement model (Step 1)
as_tse_lca(): Use a measurement model with given parameters (Step 1)
best_model() `[[`(<tseLCA_select>) as.data.frame(<tseLCA_select>) print(<tseLCA_select>) plot(<tseLCA_select>): Class enumeration results
predict(<tseLCA_measurement>) fitted(<tseLCA_measurement>): Class membership predictions from a measurement model
class_sizes() item_probs(): Class sizes and item-response probabilities of the measurement model

Assign observations to classes and estimate the classification error.

tse_classify() print(<tseLCA_classify>): Assign observations to latent classes (Step 2)
posterior() classes(): Posterior class-membership probabilities and modal class assignments

Relate the classes to covariates and distal outcomes.

tse_covariate(): Relate latent classes to covariates (Step 3)
tse_distal(): Relate latent classes to a distal outcome (Step 3)
tse_twostep(): Two-step estimates of covariate effects
predict(<tseLCA_covariate>): Class-membership probabilities from a covariate model
relevel(<tseLCA_covariate>): Change the reference class of a covariate model
anova(<tseLCA_covariate>): Wald tests of covariate terms
omnibus_test(): Omnibus Wald test of class equality for a distal outcome

summary(<tseLCA_structural>) coef(<summary.tseLCA_structural>) print(<summary.tseLCA_structural>) print(<tseLCA_structural>) summary(<tseLCA_measurement>) print(<summary.tseLCA_measurement>) print(<tseLCA_measurement>): Summarize a fitted tseLCA model
coef(<tseLCA_structural>) coef(<tseLCA_measurement>): Coefficients of a fitted tseLCA model
vcov(<tseLCA_structural>) vcov(<tseLCA_measurement>): Variance-covariance matrix of a fitted tseLCA model
logLik(<tseLCA>) nobs(<tseLCA>): Log-likelihood, number of observations, and information criteria
plot(<tseLCA>): Plot item-response probability profiles for a tseLCA model

Data from the design of Bakk and Kuha (2018), used in the simulation study.

generate_data(): Generate one dataset following the Bakk & Kuha (2018) simulation design
generate_all_conditions(): Generate datasets for all 18 conditions in the simulation design
bk2018_params: Default population parameters for the Bakk & Kuha (2018) simulation
draw_Zo(): Draw a continuous distal outcome given true class memberships (scenario "distal")
draw_Zp(): Draw the covariate Zp ~ Uniform{1, 2, 3, 4, 5}
draw_classes(): Draw latent class memberships from their marginal distribution
draw_classes_given_Zp(): Draw latent classes conditional on the covariate (scenario "covariate")
draw_indicators(): Draw binary indicators given true class memberships
make_rho(): Build the item-response probability matrix for the simulation
mnl_probs(): Compute multinomial logistic class probabilities given covariates

The tseLCA 1.x interface. These functions keep working but will be removed in a future version.

three_step(): Three-step LCA estimation with covariates and/or distal outcomes
lca_step1(): Fit the LCA measurement model (Step 1)
fitZ_from_fit0(): Estimate covariate effects with measurement parameters fixed (two-step EM)
fitZ_from_multiLCA(): Estimate two-step covariate model with multilevLCA (optional reference path)