1 Department of Pediatrics, William Beaumont Hospital, Royal Oak, MI 48072
2 Department of Statistics, Pennsylvania State University, University Park, PA 16802
In Reply.
We appreciate the comments of Drs Malloy and Reed, and we agree (with some embarrassment) that our use of the term "risk-ratio" is inappropriate; we should have used "odds" and this term should be substituted for risk ratio throughout the paper.1
We also agree that one should be cautious in the interpretation of observational data subjected to multivariate logistic analysis. We were certainly aware of the variables considered biologically important in the modeling of risk factors for neonatal jaundice.