gradlam_bet_dbb {bbreg}

gradlam_bet

Description

Gradient of the Q-function (adapted for the discrimination test between bessel and beta - DBB) to calculate the gradient required for optimization via optim. This option is related to the beta regression.

Usage

gradlam_bet_dbb(lam, phiold, z, v, mu, link.precision)

Arguments

lam

coefficients in lambda related to the covariates in v.

phiold

previous value of the precision parameter (phi).

z

response vector with 0 < z_i < 1.

v

matrix containing the covariates for the precision submodel. Each column is a different covariate.

mu

mean parameter (vector having the same size of z).

link.precision

a string containing the link function the precision parameter. The possible link functions for the precision parameter are "identity", "log", "sqrt", "inverse".

Value

Scalar representing the output of this auxiliary gradient function for the beta case.