rho_max {holiglm}

Constraint on the Pairwise Correlation of Covariates

Description

Constraint which ensures that only one covariate out of a pair of covariates with a correlation of at least rho will be included in the final model.

Usage

rho_max(
  rho = 0.8,
  exclude = "(Intercept)",
  use = c("everything", "all.obs", "complete.obs", "na.or.complete",
    "pairwise.complete.obs"),
  method = c("pearson", "kendall", "spearman")
)

Arguments

rho

a value in the range [0,1] specifying, the maximum allowed collinearity between pairs of covariates.

exclude

variables to be excluded form the pairwise correlation constraints (default is "(Intercept)").

use

an optional character string giving a method for computing co-variances in the presence of missing values. The parameter is passed to cor, therefore see cor for more information.

method

a character string indicating which correlation coefficient is to be computed. See cor for more information.

Value

A holistic generalized model constraint, object inheriting from class "hglmc".

See Also

Other Constraint-Constructors: group_equal(), group_inout(), group_sparsity(), include(), k_max(), linear(), lower(), pairwise_sign_coherence(), sign_coherence(), upper()

Examples

beta <- 1:3
Sigma <- cov_matrix(k = length(beta) - 1L, 1, 2, 0.9)
dat <- rhglm(100, beta, sigma = Sigma)
hglm(y ~ ., constraints = rho_max(0.8), data = dat)