semtree (version 0.9.12)

evaluateDataLikelihood: Evaluate Data Likelihood

Description

Evaluate Fitted Model Likelihood for Dataset. This helper function is used in the semforest varimp and proximity aggregate functions.

Usage

evaluateDataLikelihood(model, data, data_type = "raw")

Arguments

model

A OpenMx model as used in semtree and semforest.

data

Data set to apply to a fitted model.

data_type

Type of data ("raw", "cov", "cor")

Value

Returns a -2LL model fit for the model

References

Brandmaier, A.M., Oertzen, T. v., McArdle, J.J., & Lindenberger, U. (2013). Structural equation model trees. Psychological Methods, 18(1), 71-86.

See Also

semtree, semforest

Examples

# NOT RUN {
##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (model, data, data_type = "raw") 
{
    model <- omxSetParameters(model, labels = names(omxGetParameters(model)), 
        free = F)
    if (data_type == "raw") {
        data <- full_mxdata <- mxData(observed = data, type = "raw")
    }
    else if (data_type == "cov") {
        data <- full_mxdata <- mxData(observed = cov(data), type = "cov", 
            numObs = dim(data)[1])
    }
    else if (data_type == "cor") {
        data <- full_mxdata <- mxData(observed = cor(data), type = "cor", 
            numObs = dim(data)[1])
    }
    else {
        warning("data type is not supported!")
        return(NULL)
    }
    model <- setData(model, data)
    run <- OpenMx::mxRun(model, silent = T, useOptimizer = F, 
        suppressWarnings = T)
    result <- OpenMx::mxEval(objective, run)
    return(result)
  }
# }