Learn R Programming

mpath (version 0.4-2.26)

be.zeroinfl: conduct backward stepwise variable elimination for zero inflated count regression

Description

conduct backward stepwise variable elimination for zero inflated count regression from zeroinfl function

Usage

be.zeroinfl(object, data, dist=c("poisson", "negbin", "geometric"), alpha=0.05, 
            trace=FALSE)

Value

an object of zeroinfl with all variables having p-values less than the significance level alpha

Arguments

object

an object from function zeroinfl

data

argument controlling formula processing via model.frame.

dist

one of the distributions in zeroinfl function

alpha

significance level of variable elimination

trace

logical value, if TRUE, print detailed calculation results

Author

Zhu Wang <zwang145@uthsc.edu>

Details

conduct backward stepwise variable elimination for zero inflated count regression from zeroinfl function

References

Zhu Wang, Shuangge Ma, Ching-Yun Wang, Michael Zappitelli, Prasad Devarajan and Chirag R. Parikh (2014) EM for Regularized Zero Inflated Regression Models with Applications to Postoperative Morbidity after Cardiac Surgery in Children, Statistics in Medicine. 33(29):5192-208.

Zhu Wang, Shuangge Ma and Ching-Yun Wang (2015) Variable selection for zero-inflated and overdispersed data with application to health care demand in Germany, Biometrical Journal. 57(5):867-84.