umx (version 4.59.0)

umxHetCor: Create a matrix of correlations for variables of diverse types (binary, ordinal, continuous)

Description

umxHetCor is a helper to:

1. return just the correlations from John Fox's polycor::hetcor function

2. If you give it a covariance matrix, return the nearest positive-definite correlation matrix.

Usage

umxHetCor(
  data,
  ML = FALSE,
  use = c("pairwise.complete.obs", "complete.obs"),
  treatAllAsFactor = FALSE,
  verbose = FALSE,
  return = c("correlations", "hetcor object"),
  std.err = FALSE
)

Value

• A matrix of correlations

Arguments

data

A data.frame() of columns for which to compute heterochoric correlations. OR an existing covariance matrix.

ML

Whether to use Maximum likelihood computation of correlations (default = FALSE)

use

How to handle missing data: Default= "pairwise.complete.obs". Alternative ="complete.obs".

treatAllAsFactor

Whether to treat all columns as factors, whether they are or not (Default = FALSE)

verbose

How much to tell the user about what was done.

return

Return just the correlations (default) or the hetcor object (contains, method, SEs etc.)

std.err

Compute the SEs? (default = FALSE)

See Also

Other Data Functions: noNAs(), prolific_anonymize(), prolific_check_ID(), prolific_read_demog(), umx, umxFactor(), umx_as_numeric(), umx_cont_2_quantiles(), umx_lower2full(), umx_make_MR_data(), umx_make_TwinData(), umx_make_fake_data(), umx_make_raw_from_cov(), umx_merge_randomized_columns(), umx_polychoric(), umx_polypairwise(), umx_polytriowise(), umx_read_lower(), umx_rename(), umx_reorder(), umx_score_scale(), umx_select_valid(), umx_stack(), umx_strings2numeric()

Other Miscellaneous Stats Functions: FishersMethod(), SE_from_p(), geometric_mean(), harmonic_mean(), oddsratio(), reliability(), umx, umxCov2cor(), umxParan(), umxWeightedAIC(), umx_apply(), umx_cor(), umx_means(), umx_r_test(), umx_round(), umx_scale(), umx_var()

Examples

umxHetCor(mtcars[,c("mpg", "am")])
umxHetCor(mtcars[,c("mpg", "am")], treatAllAsFactor = TRUE, verbose = TRUE)