I am doing a logistic regression. One of the categorical varibales alcohol use is coming off as being very significant. I did a frequency this variable I found 795 did not use alcohol and 4 did. Is it wise to include this varibale as a predictor of birth weight given its distribution? -- Thanks, Jim. You may leave the list at any time by sending the command SIGNOFF allstat to [log in to unmask], leaving the subject line blank.