penfaPredict: Compute the factor scores from a fitted `penfa` model

Description

The penfaPredict function estimates the factor scores from a fitted penalized factor model. The factor scores are the estimated values ("predictions") of the common factors.

Usage

penfaPredict(
  object,
  newdata = NULL,
  method = "regression",
  label = TRUE,
  append.data = FALSE,
  assemble = FALSE
)

Arguments

object

An object of class '>penfa.

newdata

An optional data frame containing the same variables as the ones appearing in the original data frame used for fitting the model in object.

method

Character indicating the method for computing the factor scores. Possible options are "regression" and "bartlett". For the normal linear continuous case, the regression method is equivalent to the Empirical Bayes Method (EBM), whereas Bartlett's strategy is equivalent to maximum likelihood's method.

label

Logical. If TRUE, the columns are labeled.

append.data

Logical. If TRUE, the original data set (or the data set provided in the newdata argument) is appended to the factor scores.

assemble

Logical. If TRUE, the factor scores from each group are assembled in a single data frame of the same dimensions as the original data set and with a group column defining the groups.

Value

A matrix with the factor scores from a fitted penfa model.

References

Geminiani E. (2020), "A penalized likelihood-based framework for single and multiple-group factor analysis models" (Doctoral dissertation, University of Bologna). Available at http://amsdottorato.unibo.it/9355/.

Examples

Run this code

# NOT RUN {
data(ccdata)

syntax = 'help  =~   h1 + h2 + h3 + h4 + h5 + h6 + h7 + 0*v1 + v2 + v3 + v4 + v5
          voice =~ 0*h1 + h2 + h3 + h4 + h5 + h6 + h7 +   v1 + v2 + v3 + v4 + v5'

alasso_fit <- penfa(## factor model
                    model  = syntax,
                    data   = ccdata,
                    std.lv = TRUE,
                    ## penalization
                    pen.shrink = "alasso",
                    eta = list(shrink = c("lambda" = 0.01), diff = c("none" = 0)),
                    ## automatic procedure
                    strategy = "auto",
                    gamma = 4)

fscores <- penfaPredict(alasso_fit)

# }