Bessel and Beta Regressions via Expectation-Maximization Algorithm for Continuous Bounded Data
score_residual_bet
startvalues
summary.bbreg
vcov.bbreg
simdata_bes
simdata_bet
bbreg
coef.bbreg
d2mudeta2
d2phideta2
D2Q_Obs_Fisher_bes
D2Q_Obs_Fisher_bet
dbbtest
dbessel
DQ2_Obs_Fisher_bes
DQ2_Obs_Fisher_bet
EMrun_bes
EMrun_bes_dbb
EMrun_bet
EMrun_bet_dbb
envelope_bes
envelope_bet
Ew1z
Ew2z
fitted.bbreg
gradlam_bes_dbb
gradlam_bet
gradtheta_bes
gradtheta_bet
infmat_bes
infmat_bet
plot.bbreg
pred_accuracy_bes
pred_accuracy_bet
predict.bbreg
print.bbreg
Qf_bes
Qf_bes_dbb
Qf_bet
Qf_bet_dbb
quantile_residual_bes
quantile_residual_bet
score_residual_bes
Functions to fit, via Expectation-Maximization (EM) algorithm, the Bessel and Beta regressions to a data set with a bounded continuous response variable. The Bessel regression is a new and robust approach proposed in the literature. The EM version for the well known Beta regression is another major contribution of this package. See details in the references Barreto-Souza, Mayrink and Simas (2022) <doi:10.1111/anzs.12354> and Barreto-Souza, Mayrink and Simas (2020) <arXiv:2003.05157>.