mxData: Create MxData Object

Description

This function creates a new MxData object.

Usage

mxData(observed, type, means = NA, numObs = NA, acov=NA, fullWeight=NA, thresholds=NA, ..., sort=NA, primaryKey = as.character(NA))

Arguments

observed

A matrix or data.frame which provides data to the MxData object.

type

A character string defining the type of data in the ‘observed’ argument. Must be one of “raw”, “cov”, or “cor”.

means

An optional vector of means for use when ‘type’ is “cov”, or “cor”.

numObs

The number of observations in the data supplied in the ‘observed’ argument. Required unless ‘type’ equals “raw”.

acov

Asymptotic covariance matrix of observed, means, and thresholds. Used for weighted least squares at weight matrix.

fullWeight

Full asymptotic covariance matrix of observed, means, and thresholds. Used for weighted least squares in standard error and quasi-chi-squared calculation.

thresholds

Observed thresholds. Used for weighted least squares with ordinal data.

...

Not used. Forces remaining arguments to be specified by name.

sort

Whether to sort raw data prior to use (default NA)

primaryKey

The column name of the primary key used to uniquely identify rows (default NA)

Value

Returns a new MxData object.

Details

The mxData function creates MxData objects, which can be used as arguments in MxModel objects. The ‘observed’ argument may take either a data frame or a matrix, which is then described with the ‘type’ argument. Data types describe compatibility and usage with expectation functions in MxModel objects. Four different data types are supported (a fifth, sscp, is not yet implemented):

raw: The contents of the ‘observed’ argument are treated as raw data. Missing values are permitted and must be designated as the system missing value. The ‘means’ and ‘numObs’ arguments cannot be specified, as the ‘means’ argument is not relevant and the ‘numObs’ argument is automatically populated with the number of rows in the data. Data of this type may use fit functions such as mxFitFunctionML function in MxModel objects, which will automatically use covariance estimation under full-information maximum likelihood for this data type.

cov

The contents of the ‘observed’ argument are treated as a covariance matrix. The ‘means’ argument is not required, but may be included for estimations involving means. The ‘numObs’ argument is required, which should reflect the number of observations or rows in the data described by the covariance matrix. Data of this type may use the fit functions such as mxFitFunctionML, depending on the specified model.

cor

The contents of the ‘observed’ argument are treated as a correlation matrix. The ‘means’ argument is not required, but may be included for estimations involving means. The ‘numObs’ argument is required, which should reflect the number of observations or rows in the data described by the covariance matrix. Data of this type may use the fit functions such as mxFitFunctionML functions, depending on the specified model.

acov

The best way to have data of the type is to use the mxDataWLS function. The contents of the ‘observed’ argument are treated as the polychoric correlation matrix of the ordinal variables. The ‘means’ argument is not required, but may be included for estimations involving means. The ‘thresholds’ argument is not required, but may be included for estimation involving thresholds and ordinal variables. The ‘numObs’ argument is required, which should reflect the number of observations or rows in the data described by the polychoric correlation matrix. Data of this type almost certainly use the mxFitFunctionWLS function, but may depend on the specified model.

MxData objects may not be included in MxAlgebra objects or use the mxFitFunctionAlgebra function. If these capabilities are desired, data should be appropriately input or transformed using the mxMatrix and mxAlgebra functions.

While column names are stored in the ‘observed’ slot of MxData objects, these names are not recognized as variable names in MxPath objects. Variable names must be specified using the ‘manifestVars’ argument of the mxModel function prior to use in MxPath objects.

The mxData function does not currently place restrictions on the size, shape, or symmetry of matrices input into the ‘observed’ argument. While it is possible to specify MxData objects as covariance or correlation matrices that do not have the properties commonly associated with these matrices, failure to correctly specify these matrices will likely lead to problems in model estimation.

OpenMx uses the names of variables to map them onto the expectation functions and other elements associated with your model. For data.frames, ensure you have set the names(). For matrices set names using, for instance, row.names=c(“your”, “columns”). Covariance and correlation matrices need to have both the row and column names set and these must be identical, for instance by using dimnames=list(varNames, varNames).

When a primary key is provided, sorting is disabled. Otherwise, sort defaults to TRUE.

References

The OpenMx User's guide can be found at http://openmx.psyc.virginia.edu/documentation.

Examples

Run this code

    
library(OpenMx)

#Create a covariance matrix
covMatrix <- matrix( c(0.77642931, 0.39590663, 
    0.39590663, 0.49115615), 
    nrow = 2, ncol = 2, byrow = TRUE)
covNames <- c("x", "y")
dimList <- list(covNames, covNames)
dimnames(covMatrix) <- dimList

#Create an MxData object including that covariance matrix
testData <- mxData(observed=covMatrix, type="cov", numObs = 100)

testModel <- mxModel(model="testModel",
                mxMatrix(type="Symm", nrow=2, ncol=2, values=c(.2,.1,.2), 
                         free=TRUE, name="expCov", dimnames=dimList),
                mxExpectationNormal(covariance="expCov", dimnames=covNames),
                mxFitFunctionML(),
                testData) 

outModel <- mxRun(testModel)

summary(outModel)

Run the code above in your browser using DataLab