omxParallelCI

omxParallelCI

Wiki home page

[toc list: ol; title: Table of Contents; minlevel: 1; maxlevel: 4; attachments: 1;]

Usage

Function to calculate confidence intervals in parallel in a model.

omxParallelCI(model, run = TRUE)

Arguments

model a fitted MxModel object.
run a boolean indicating if model should be run. Set to TRUE by default

Examples

data(demoOneFactor)
 
manifests <- names(demoOneFactor)
latents <- c("factor")
nManifest <- length(manifests)
nVars <- nManifest + length(latents)
 
factorModel <- mxModel("One Factor", type="RAM",
    manifestVars = manifests,
    latentVars = latents,
    mxPath(from=latents, to=manifests, free=c(FALSE,TRUE,TRUE,TRUE,TRUE), values=1),
    mxPath(from=manifests, arrows=2, lbound=.0001),
    mxPath(from=latents, arrows=2, free=TRUE, values=1.0),
    mxData(cov(demoOneFactor), type="cov", numObs=500),
    # mxPath(from="one", to=manifests, arrows=1, free=T, values=mean(demoOneFactor)),
    # mxData(demoOneFactor, type="raw"),
    mxMatrix("Iden", nrow=nVars, name="I"),
    mxMatrix("Full", free=FALSE, values=diag(nrow=nManifest, ncol=nVars), name="Eff"),
    mxAlgebra(Eff%*%solve(I-A), name="Z"),
    mxAlgebra(Z%*%S%*%t(Z), name="C"),
    mxAlgebra(sqrt(diag2vec(C)), name="P"),
    mxCI(c("P"))
)
factorFit <- mxRun(factorModel, intervals=FALSE)
factorParallel <- omxParallelCI(factorFit)
 
	<em># See the results...</em>
print(factorParallel@output$confidenceIntervals)
 
	                     lbound    ubound
	One Factor.P[1,1] 0.4193000 0.4747328
	One Factor.P[2,1] 0.5082290 0.5754222
	One Factor.P[3,1] 0.5755068 0.6515979
	One Factor.P[4,1] 0.6871788 0.7780409
	One Factor.P[5,1] 0.7704188 0.8722923

Please add material here as you learn... If you have questions not answers, then add those here: That's how a wiki works.