Skip to contents

Extract factor loadings from galamm object

Usage

# S3 method for galamm
factor_loadings(object)

Arguments

object

Object of class galamm returned from galamm.

Value

A matrix containing the estimated factor loadings with corresponding standard deviations.

Details

This function has been named factor_loadings rather than just loadings to avoid conflict with stats::loadings.

See also

fixef.galamm() for fixed regression coefficients, confint.galamm() for confidence intervals, and coef.galamm() for coefficients more generally.

Other details of model fit: VarCorr(), coef.galamm(), confint.galamm(), deviance.galamm(), family.galamm(), fitted.galamm(), fixef(), formula.galamm(), llikAIC(), logLik.galamm(), nobs.galamm(), predict.galamm(), print.VarCorr.galamm(), ranef.galamm(), residuals.galamm(), sigma.galamm(), vcov.galamm()

Author

The example for this function comes from PLmixed, with authors Nicholas Rockwood and Minjeong Jeon (Rockwood and Jeon 2019) .

Examples

# Logistic mixed model with factor loadings, example from PLmixed
data("IRTsim", package = "PLmixed")

# Reduce data size for the example to run faster
IRTsub <- IRTsim[IRTsim$item < 4, ]
IRTsub <- IRTsub[sample(nrow(IRTsub), 300), ]
IRTsub$item <- factor(IRTsub$item)

# Fix loading for first item to 1, and estimate the two others freely
loading_matrix <- matrix(c(1, NA, NA), ncol = 1)

# Estimate model
mod <- galamm(y ~ item + (0 + ability | sid) + (0 + ability | school),
  data = IRTsub, family = binomial, load.var = "item",
  factor = "ability", lambda = loading_matrix
)

# Show estimated factor loadings, with standard errors
factor_loadings(mod)
#>           ability        SE
#> lambda1 1.0000000        NA
#> lambda2 0.4491323 0.2570172
#> lambda3 0.4875508 0.2993875