siriustar <qinlangjinan <at> live.cn> writes: > > Hi, Dear R-help > I know there are some R package to deal with zero-inflated count data. But I > am now looking for R package to deal with zero-inflated continuous data. > > The response variable (Y) in my dataset contains a larger mount of zero and > the Non-zero response are quite right skewed. Now what i am doing is first > to use a logistic regression on covariates (X) to estimate the probability > of Y being 0. Then focus on the dataset where Y is not zero, and run a > linear regression or gamma glm to estimate the association between Y and X > when Y is not zero. > However, the linear regression and gamma glm model fit my data poorly. > > So, I am thinking maybe a zero inflated gamma or zero inflated lognormal > regression are helpful, where I can estimate the probability of Y being zero > and the association between non zero Y and X at the same time. > However, I dont know which R package can do that.
I think your 'conditional' strategy is quite useful in general, and may in general give you the same answers as the zero-inflated approach you're suggesting. Perhaps there are some other issues with the conditional (gamma GLM) parts of your analysis? Have you tried simple log-linear regression (i.e. assuming that the non-zero values are lognormally distributed)? I would recommend reading this thread in the r-sig-ecology mailing list: http://thread.gmane.org/gmane.comp.lang.r.ecology/2124 ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
