OBJECTIVE To examine the relationship between nurse staffing and patient length of stay in an acute-care hospital over a 1-year period. BACKGROUND Although there has been prior research on the relationship between nurse staffing and length of stay in acute-care hospitals, there is a need for more information on how nurse staffing is related to length of stay longitudinally. METHODS Retrospective time-series registry data from 20 acute-care inpatient units of a Finnish university hospital as a monthly time series in 2008 were analysed by linear mixed models. RESULTS The ratio of registered nurses to all nurses was 72.4%. Nurses worked mainly (96%) full time, and 63% had permanent employment contracts. Statistically significant variation was found in time series of five variables. Statistically significant relationships were found between length of stay and patient acuity, diagnosis-related group-volume, census and nursing hours per patient day at the unit level. Nursing hours per patient day had the strongest correlation with length of stay. CONCLUSIONS A rational response to the variations in patient care needs and intensity in the complex care environment is flexible nurse staffing. Increasing nursing hours per patient day to achieve shorter length of stays is not the only solution, well-functioning care processes are also essential.