mxDescribeDataWLS: Determine whether a dataset will have weights and summary statistics for the means if used with mxFitFunctionWLS

Description

Given either a data.frame or an mxData of type raw, this function determines whether mxFitFunctionWLS will generate expectations for means.

Usage

mxDescribeDataWLS(
  data,
  allContinuousMethod = c("cumulants", "marginals"),
  verbose = FALSE
)

Arguments

data

the (currently raw) data being used in a mxFitFunctionWLS model.

allContinuousMethod

the method used to process data when all columns are continuous.

verbose

logical. Whether to report diagnostics.

Value

- list describing the data.

Details

All-continuous data processed using the "cumulants" method lack means, while all continuous data processed with allContinuousMethod = "marginals" will have means.

When data are not all continuous, allContinuousMethod is ignored, and means are modelled.

Examples

Run this code

# NOT RUN {
# ====================================
# = All continuous, data.frame input =
# ====================================

tmp = mxDescribeDataWLS(mtcars, allContinuousMethod= "cumulants", verbose = TRUE)
tmp$hasMeans # FALSE - no means with cumulants
tmp = mxDescribeDataWLS(mtcars, allContinuousMethod= "marginals") 
tmp$hasMeans # TRUE we get means with marginals

# ==========================
# = mxData object as input =
# ==========================
tmp = mxData(mtcars, type="raw")
mxDescribeDataWLS(tmp, allContinuousMethod= "cumulants", verbose = TRUE)$hasMeans # FALSE
mxDescribeDataWLS(tmp, allContinuousMethod= "marginals")$hasMeans  # TRUE

# =======================================
# = One var is a factor: Means modelled =
# =======================================
tmp = mtcars
tmp$cyl = factor(tmp$cyl)
mxDescribeDataWLS(tmp, allContinuousMethod= "cumulants")$hasMeans # TRUE - always has means
mxDescribeDataWLS(tmp, allContinuousMethod= "marginals")$hasMeans # TRUE

# }