glm.predict

Functions to calculate predicted values and the difference between the two cases with confidence interval for lm() [linear model], glm() [generalised linear model], glm.nb() [negative binomial model], polr() [ordinal logistic model], multinom() [multinomial model] and tobit() [tobit model], svyglm() [survey-weighted generalised linear models], lmer() [linear multilevel models] using Monte Carlo simulations or bootstrap. Reference: Bennet A. Zelner (2009) doi:10.1002/smj.783.