Skip to contents

Polychoric correlation

Source: R/het_cor.R
polychoric.Rd

Estimates the correlation between two ordinal variables, assuming each arises from cutting an underlying normal variable into categories. Uses the two-step estimator: thresholds from the marginal proportions, then maximum likelihood for the correlation (Olsson 1979).

Usage

polychoric(x, y, max_cor = 0.9999)

Arguments

x, y

Factors of the same length. Their level order is used as the ordinal scale; unordered factors give a warning.

max_cor

Largest absolute correlation searched, between 0 and 1.

Value

The estimated correlation, using cases complete for both variables, or NA if either has fewer than two observed levels.

References

Olsson U (1979). Maximum likelihood estimation of the polychoric correlation coefficient. Psychometrika, 44, 443-460.

See also

het_cor(), polyserial()

Examples

set.seed(1)
z1 <- rnorm(500)
z2 <- 0.6 * z1 + sqrt(1 - 0.6^2) * rnorm(500)
x <- cut(z1, c(-Inf, -0.5, 0.5, Inf), ordered_result = TRUE)
y <- cut(z2, c(-Inf, 0, 1, Inf), ordered_result = TRUE)
polychoric(x, y)
#> [1] 0.5784943