Objectives: This study investigates the relationship between nurse staffing levels and differences in patient outcomes in terms of average length of stay, in-hospital mortality rate and 30-day death rate in order to evaluate the effectiveness of a policy that differentiates fees for inpatients on the basis of nurse-to-bed ratios. Methods: We obtained information on inpatients from health insurance claims data published by the Health Insurance Review and Assessment Service(HIRA) in 2008, organizational factors(type of hospital, ownership) from the records of the hospital report system in 2008, and nurse staffing levels, which were graded on a scale of 1 to 7, from data compiled between December 15, 2007, and September 20, 2008. The data were segregated according to type of hospital and quarter and finally 3,517 records of 1,182 hospitals were analyzed using multi-level analysis. Results: The average length of stay in grade 1~6 hospitals was lower than that in grade 7 ones, but the difference was much below one day. No significant difference was found among different grades in tertiary hospitals. Further, variations in staffing levels did not result in any significant difference in the in-hospital mortality rate and 30-day death rate. Conclusions: High nurse staffing levels did not result in better patient outcomes compared with low staffing levels. We therefore recommend modifying the above nurse staffing policy so as to make it more effective in improving patient outcomes.