pred_accuracy_bes {bbreg}

pred_accuracy_bes

Description

Function to calculate the Residual Sum of Squares for partitions (training and test sets) of the data set. Residuals are calculated here based on the bessel regression.

Usage

pred_accuracy_bes(
  residual,
  kap,
  lam,
  z,
  x,
  v,
  ntest,
  predict,
  epsilon,
  link.mean,
  link.precision
)

Arguments

residual

Character indicating the type of residual ("pearson", "score" or "quantile").

kap

coefficients in kappa related to the mean parameter.

lam

coefficients in lambda related to the precision parameter.

z

response vector with 0 < z_i < 1.

x

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

v

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

ntest

number of observations in the test set for prediction.

predict

number of partitions (training and test sets) to be evaluated.

epsilon

tolerance parameter used in the Expectation-Maximization algorithm for the training data set.

link.mean

a string containing the link function for the mean. The possible link functions for the mean are "logit","probit", "cauchit", "cloglog".

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

Vector containing the RSS for each partition of the full data set.