varcovgecub function

Variance-covariance matrix of a CUB model without covariates

Compute the variance-covariance matrix of parameter estimates of a CUB model without covariates.

varcovgecub(ordinal,Y,W,X,bet,gama,omega,shelter)

Arguments

• ordinal: Vector of ordinal responses
• Y: Matrix of selected covariates to explain the uncertainty component (default: no covariate is included in the model)
• W: Y Matrix of selected covariates to explain the feeling component (default: no covariate is included in the model)
• X: Matrix of selected covariates to explain the shelter component (default: no covariate is included in the model)
• bet: Parameter vector for the Uncertainty component
• gama: Parameter vector for the Feeling component
• omega: Parameter vector for the shelter component
• shelter: Cateogry corresponding to the shelter effect

Details

The function checks if the variance-covariance matrix is positive-definite: if not, it returns a warning message and produces a matrix with NA entries.

See Also

probgecub