umxValues: umxValues: Set values in RAM model, matrix, or path

Description

For models to be estimated, it is essential that path values start at credible values. umxValues takes on that task for you. umxValues can set start values for the free parameters in both RAM and Matrix mxModels. It can also take an mxMatrix as input. It tries to be smart in guessing starts from the values in your data and the model type.

Usage

umxValues(obj = NA, sd = NA, n = 1, onlyTouchZeros = FALSE)

Arguments

obj

The RAM or matrix mxModel, or mxMatrix that you want to set start values for.

Optional Standard Deviation for start values

Optional Mean for start values

onlyTouchZeros

Don't alter parameters that appear to have already been started (useful for speeding umxModify)

Value

- mxModel with updated start values

Details

note: If you give umxValues a numeric input, it will use obj as the mean, and return a list of length n, with sd = sd.

References

- http://www.github.com/tbates/umx, https://tbates.github.io

Examples

Run this code

# NOT RUN {
require(umx)
data(demoOneFactor)
latents = c("G")
manifests = names(demoOneFactor)
m1 <- mxModel("One Factor", type = "RAM", 
	manifestVars = manifests, latentVars = latents, 
	mxPath(from = latents, to = manifests),
	mxPath(from = manifests, arrows = 2),
	mxPath(from = latents, arrows = 2, free = FALSE, values = 1.0),
	mxData(cov(demoOneFactor), type = "cov", numObs = 500)
)
mxEval(S, m1) # default variances are 0
m1 = umxValues(m1)
mxEval(S, m1) # plausible variances
umx_print(mxEval(S,m1), 3, zero.print = ".") # plausible variances
umxValues(14, sd = 1, n = 10) # Return vector of length 10, with mean 14 and sd 1
# }

Run the code above in your browser using DataLab

Last chance! 50% off unlimited learning