simulate_moderated_nonlinear_factor_analysis
simulate_moderated_nonlinear_factor_analysis.Rdsimulate data for a moderated nonlinear factor analysis.
Value
data set with variables x1-x3 and y1-y3 representing repeated measurements of an affect measure. It is assumed that the autoregressive effect is different depending on covariate k
Examples
library(mxsem)
set.seed(123)
dataset <- simulate_moderated_nonlinear_factor_analysis(N = 2000)
model <- "
xi =~ x1 + x2 + x3
eta =~ y1 + y2 + y3
eta ~ a*xi
# we need two new parameters: a0 and a1. These are created as follows:
!a0
!a1
# Now, we redefine a to be a0 + k*a1, where k is found in the data
a := a0 + data.k*a1
"
mod <- mxsem(model = model,
data = dataset) |>
mxTryHard()
#> Running untitled32 with 20 parameters
#>
#> Beginning initial fit attempt
#> Running untitled32 with 20 parameters
#>
#> Lowest minimum so far: 9354.67567512738
#>
#> Solution found
#>
#>
#> Solution found! Final fit=9354.6757 (started at 63250.836) (1 attempt(s): 1 valid, 0 errors)
#> Start values from best fit:
#> 0.798644787140878,0.907904236613599,0.803838142013948,0.900396358534138,0.0423202738274926,0.0419256359832653,0.0370993849926502,0.0410547496618837,0.041974968940025,0.0377186342526869,0.983486182403335,0.248565838931859,0.0132141364668449,0.00300610847335311,0.0101745706855508,-0.00432472158982143,-0.00060509160768298,-0.00278202909173598,0.679955375785379,-0.172459318949147
omxGetParameters(mod)
#> xi→x2 xi→x3 eta→y2 eta→y3 x1↔x1
#> 0.7986447871 0.9079042366 0.8038381420 0.9003963585 0.0423202738
#> x2↔x2 x3↔x3 y1↔y1 y2↔y2 y3↔y3
#> 0.0419256360 0.0370993850 0.0410547497 0.0419749689 0.0377186343
#> xi↔xi eta↔eta one→x1 one→x2 one→x3
#> 0.9834861824 0.2485658389 0.0132141365 0.0030061085 0.0101745707
#> one→y1 one→y2 one→y3 a0 a1
#> -0.0043247216 -0.0006050916 -0.0027820291 0.6799553758 -0.1724593189