The effects of regional anesthesia and of the obstetrician on the risk of cesarean delivery remain controversial. The purpose of this study was to determine whether epidural analgesia or the obstetrician group is associated with an increase in the risk for cesarean delivery in nulliparous women. Data were collected for a two-year period from the medical records of all nulliparous women who had a private obstetrician who delivered >20 babies per year, and who presented with a singleton gestation in the vertex presentation for a trial of labor. Data were collected for 3699 women of whom 1832 were nulliparous. Of the 1832 nulliparous women, data were analyzed for the 1278 women who met our study criteria, representing 14 separate obstetrician groups. Excluding the 50 women whose babies were delivered for fetal distress (leaving 1228 women for analysis), the epidural rate was 93%, range 81-98%, and the cesarean delivery rate was 14%, range 8-34%. Logistic regression analyses revealed that (odds ratio, 95% confidence interval) patient age (1.7, 1.2-2.4), birth weight (1.001, 1.001-1.002), induction of labor (1.9, 1.3-2.7), non-Caucasian (1.9, 1.2-2.9) and the obstetrician group, (P=0.002), were independently associated with the risk of cesarean delivery, but epidural analgesia was not (1.6, 0.7-3.6). The obstetrician group is independently associated with the risk of cesarean delivery in nulliparous women, but we could not demonstrate this association with epidural analgesia. We suggest that in future studies regarding epidural analgesia and cesarean delivery, the obstetrician group should be included as a variable.