In this paper we examine the relationship between inpatient length of stay and the patient's type of health insurance. The data consist of discharges in seven diagnosis-related groups (DRGs) from community hospitals in Minneapolis and St. Paul during 1982. After controlling for the effects of the patient's age, sex, medical condition, and severity of illness, as well as the hospital's size, teaching and ownership status, and average annual occupancy rate, we must reject the null hypothesis that the patient's type of health plan is unrelated to inpatient length of stay in Twin Cities community hospitals. We find that, in most cases, patients in prepaid group practices and independent practice associations exhibit significantly shorter lengths of stay than similar patients in Blue Cross and commercial health insurance plans, while Medicare and Medicaid patients exhibit significantly longer lengths of stay than those of similar commercially insured patients