I sent out a question a few days ago asking help with cv.glm and I didn't get any responses. Is it my question? I'd appreciate any response just to see my post makes it out there. What I'm looking to do is to get a column of predicted responses from cv.glm (leave-one-out). This produces a single predicted value for each case, correct? How can I get those values? I don't want predicted values using a full model but just the values that come from the cross validation. Thanks, Jeff Here's the code I used for the model and to get delta: q_uk.nb <- glm.nb(nat_est ~ UK + I(UK^2), SRCOUNT, link=log) cv.err1 <- cv.glm(SRCOUNT,q_uk.nb) **************************************** Jeffrey A. Stratford, Ph.D. Postdoctoral Associate 331 Funchess Hall Department of Biological Sciences Auburn University Auburn, AL 36849 334-329-9198 FAX 334-844-9234 http://www.auburn.edu/~stratja