OpenMx (version 2.21.13)

mxRAMObjective: DEPRECATED: Create MxRAMObjective Object

Description

WARNING: Objective functions have been deprecated as of OpenMx 2.0.

Please use mxExpectationRAM() and mxFitFunctionML() instead. As a temporary workaround, mxRAMObjective returns a list containing an MxExpectationNormal object and an MxFitFunctionML object.

All occurrences of

mxRAMObjective(A, S, F, M = NA, dimnames = NA, thresholds = NA, vector = FALSE, threshnames = dimnames)

Should be changed to

mxExpectationRAM(A, S, F, M = NA, dimnames = NA, thresholds = NA, threshnames = dimnames) mxFitFunctionML(vector = FALSE)

Value

Returns a list containing an MxExpectationRAM object and an MxFitFunctionML object.

Arguments

A

A character string indicating the name of the 'A' matrix.

S

A character string indicating the name of the 'S' matrix.

F

A character string indicating the name of the 'F' matrix.

M

An optional character string indicating the name of the 'M' matrix.

dimnames

An optional character vector to be assigned to the column names of the 'F' and 'M' matrices.

thresholds

An optional character string indicating the name of the thresholds matrix.

vector

A logical value indicating whether the objective function result is the likelihood vector.

threshnames

An optional character vector to be assigned to the column names of the thresholds matrix.

Details

NOTE: THIS DESCRIPTION IS DEPRECATED. Please change to using mxExpectationRAM and mxFitFunctionML as shown in the example below.

Objective functions were functions for which free parameter values are chosen such that the value of the objective function was minimized. The mxRAMObjective provided maximum likelihood estimates of free parameters in a model of the covariance of a given MxData object. This model is defined by reticular action modeling (McArdle and McDonald, 1984). The 'A', 'S', and 'F' arguments must refer to MxMatrix objects with the associated properties of the A, S, and F matrices in the RAM modeling approach.

The 'dimnames' arguments takes an optional character vector. If this argument is not a single NA, then this vector be assigned to be the column names of the 'F' matrix and optionally to the 'M' matrix, if the 'M' matrix exists.

The 'A' argument refers to the A or asymmetric matrix in the RAM approach. This matrix consists of all of the asymmetric paths (one-headed arrows) in the model. A free parameter in any row and column describes a regression of the variable represented by that row regressed on the variable represented in that column.

The 'S' argument refers to the S or symmetric matrix in the RAM approach, and as such must be square. This matrix consists of all of the symmetric paths (two-headed arrows) in the model. A free parameter in any row and column describes a covariance between the variable represented by that row and the variable represented by that column. Variances are covariances between any variable at itself, which occur on the diagonal of the specified matrix.

The 'F' argument refers to the F or filter matrix in the RAM approach. If no latent variables are included in the model (i.e., the A and S matrices are of both of the same dimension as the data matrix), then the 'F' should refer to an identity matrix. If latent variables are included (i.e., the A and S matrices are not of the same dimension as the data matrix), then the 'F' argument should consist of a horizontal adhesion of an identity matrix and a matrix of zeros.

The 'M' argument refers to the M or means matrix in the RAM approach. It is a 1 x n matrix, where n is the number of manifest variables + the number of latent variables. The M matrix must be specified if either the mxData type is “cov” or “cor” and a means vector is provided, or if the mxData type is “raw”. Otherwise the M matrix is ignored.

The MxMatrix objects included as arguments may be of any type, but should have the properties described above. The mxRAMObjective will not return an error for incorrect specification, but incorrect specification will likely lead to estimation problems or errors in the mxRun function.

mxRAMObjective evaluates with respect to an MxData object. The MxData object need not be referenced in the mxRAMObjective function, but must be included in the MxModel object. mxRAMObjective requires that the 'type' argument in the associated MxData object be equal to 'cov' or 'cor'.

To evaluate, place MxRAMObjective objects, the mxData object for which the expected covariance approximates, referenced MxAlgebra and MxMatrix objects, and optional MxBounds and MxConstraint objects in an MxModel object. This model may then be evaluated using the mxRun function. The results of the optimization can be found in the 'output' slot of the resulting model, and may be obtained using the mxEval function..

References

McArdle, J. J. and MacDonald, R. P. (1984). Some algebraic properties of the Reticular Action Model for moment structures. British Journal of Mathematical and Statistical Psychology, 37, 234-251.

The OpenMx User's guide can be found at https://openmx.ssri.psu.edu/documentation/.

Examples

   

# Create and fit a model using mxMatrix, mxAlgebra,
#  mxExpectationNormal, and mxFitFunctionML

library(OpenMx)

# Simulate some data

x=rnorm(1000, mean=0, sd=1)
y= 0.5*x + rnorm(1000, mean=0, sd=1)
tmpFrame <- data.frame(x, y)
tmpNames <- names(tmpFrame)

# Define the matrices

matrixS <- mxMatrix(type = "Full", nrow = 2, ncol = 2, values=c(1,0,0,1), 
              free=c(TRUE,FALSE,FALSE,TRUE), labels=c("Vx", NA, NA, "Vy"),
              name = "S")
matrixA <- mxMatrix(type = "Full", nrow = 2, ncol = 2, values=c(0,1,0,0), 
              free=c(FALSE,TRUE,FALSE,FALSE), labels=c(NA, "b", NA, NA),
              name = "A")
matrixF <- mxMatrix(type="Iden", nrow=2, ncol=2, name="F")
matrixM <- mxMatrix(type = "Full", nrow = 1, ncol = 2, values=c(0,0), 
              free=c(TRUE,TRUE), labels=c("Mx", "My"), name = "M")

# Define the expectation

expFunction <- mxExpectationRAM(M="M", dimnames = tmpNames)

# Choose a fit function

fitFunction <- mxFitFunctionML()

# Define the model

tmpModel <- mxModel(model="exampleRAMModel",
                    matrixA, matrixS, matrixF, matrixM,
                    expFunction, fitFunction,
                    mxData(observed=cov(tmpFrame), type="cov", numObs=nrow(tmpFrame),
                              means = colMeans(tmpFrame)))

# Fit the model and print a summary

tmpModelOut <- mxRun(tmpModel)
summary(tmpModelOut)