lavaan (version 0.5-21)

fsr: Factor Score Regression

Description

Fit a SEM model using factor score regression.

Usage

fsr(model = NULL, data = NULL, cmd = "sem",  fsr.method = "Croon", fs.method = "Bartlett", ...)

Arguments

model

A description of the user-specified model. Typically, the model is described using the lavaan model syntax. See model.syntax for more information. Alternatively, a parameter table (eg. the output of the lavaanify() function) is also accepted.

data

An optional data frame containing the observed variables used in the model. If some variables are declared as ordered factors, lavaan will treat them as ordinal variables.

cmd

Charcater. Which command is used to run the sem models. The possible choices are "sem" or "lavaan", determining how we deal with default options.

fsr.method

Character. Factor score regression method. Possible options are naive, Skrondal-Laake, and Croon.

fs.method

Character. Factor score estimation method. Possible options are Bartlett and regression.

...

Further arguments that we pass to the "cfa", "sem" or "lavaan" functions.

Value

An object of class lavaan, for which several methods are available, including a summary method.

Details

The fsr function implements a two-step procedure to estimate the parameters of the structural (regression) part of a SEM model. In a first step, factor scores are computed for each latent variable. In a second step, the latent variables are replaced by the factor scores, and a path analysis is used to estimate all remaining model parameters. Special techniques are used in order to ensure (approximately) unbiased estimation of point estimates and standard errors.

References

Devlieger, I., Mayer, A., & Rosseel, Y. (2015). Hypothesis Testing Using Factor Score Regression: A Comparison of Four Methods. Educational and Psychological Measurement. http://epm.sagepub.com/content/early/2015/09/29/0013164415607618.abstract

See Also

lavaan, sem, lavPredict

Examples

## The industrialization and Political Democracy Example 
## Bollen (1989), page 332, simplified
model <- ' 
  # latent variable definitions
     ind60 =~ x1 + x2 + x3
     dem60 =~ y1 + y2 + y3 + y4

  # regressions
    dem60 ~ ind60
'

fit <- fsr(model, data = PoliticalDemocracy, fsr.method = "Skrondal-Laake")
summary(fit)