The Effect of Data Aggregation on Estimations of Nurse Staffing and Patient Outcomes.

Abstract

OBJECTIVE\nTo examine how estimates of the association between nurse staffing and patient length of stay (LOS) change with data aggregation over varying time periods and settings, and statistical controls for unobserved heterogeneity.\n\n\nDATA SOURCES/STUDY SETTING\nLongitudinal secondary data from October, 2002 through September, 2006 for 215 ICUs and 438 general acute care units at 143 facilities in the Veterans Affairs health care system.\n\n\nRESEARCH DESIGN\nThis retrospective observational study used unit-level panel data to analyze the association between nurse staffing and LOS. This association was measured over both a month-long and a year-long period, with and without fixed effects.\n\n\nDATA COLLECTION\nWe used VA administrative data to obtain patient data on severity of illness and LOS, as well as labor hours and wages for each unit by month.\n\n\nPRINCIPAL FINDINGS\nOverall, shorter length of stay was associated with higher nurse staffing hours and lower proportions of hours provided by LPNs, unlicensed personnel, and contract staff. Estimates of the association between nurse staffing and LOS changed in magnitude when aggregating data over years instead of months, in different settings, and when controlling for unobserved heterogeneity.\n\n\nCONCLUSIONS\nEstimating the association between nurse staffing and LOS is contingent on time period of analysis and specific methodology. In future studies, researchers should be aware of these differences when exploring nurse staffing and patient outcomes.