This study evaluated hospital demographics, staffing, pharmacy variables, health care outcomes measures (severity of illness-adjusted mortality rates, drug costs, total cost of care, and length of stay) and medication errors. A database was constructed from the 1992 American Hospital Association's Abridged Guide to the Health Care Field, the 1992 National Clinical Pharmacy Services database, and 1992 mortality data from the Health Care Financing Administration. Simple statistical tests and a severity of illness-adjusted multiple regression analysis were employed. The study population consisted of 1116 hospitals that reported information on medication errors and 913 hospitals that reported information on medication errors that adversely affected patient care outcomes. We evaluated factors associated with the 430,586 medication errors and 17,338 medication errors that adversely affected patient care outcomes. Medication errors occurred in 5.07% of the patients admitted each year to these hospitals. Each hospital experienced a medication error every 22.7 hours (every 19.73 admissions). Medication errors that adversely affected patient care outcomes occurred in 0.25% of all patients admitted to these hospitals/year. Each hospital experienced a medication error that adversely affected patient care outcomes every 19.23 days (or every 401 admissions). The following factors were associated with increased medication errors/occupied bed/year: lack of pharmacy teaching affiliation (slope = 0.8875, p=0.0416), centralized pharmacists (slope = 1.0942, p=0.0001), number of registered nurses/occupied bed (slope = 1.624, p=0.032), number of registered pharmacists/occupied bed (slope = 25.0573, p=0.0001), hospital mortality rate (slope = 2.8017, p=0.0192), and total cost of care/occupied bed/year (slope = 0.01432, p=0.0091). Factors associated with decreased medication errors were location in the Mid-Atlantic census region (slope = -1.5182, p=0.03), affiliation with a pharmacy teaching program (slope = -1.0252, p=0.0349), decentralized pharmacists (slope = -0.9843, p=0.0037), and number of medical residents/occupied bed (slope = -1.478, p=0.0014). There was a 45% decrease in medication errors (1.81-fold decrease) in hospitals that had decentralized pharmacists, compared with hospitals that had centralized pharmacists. In addition, there was a 94% decrease in medication errors that adversely affected patient care outcomes (16.88-fold decrease) in hospitals that had decentralized pharmacists compared with hospitals that had only centralized pharmacists. Based on previous field studies and our findings in 1116 hospitals, it appears that one of the most effective ways to prevent or reduce medication errors is to decentralize pharmacists to patient care areas. The results of this study should help hospitals reduce the number of medication errors that occur each year.