BACKGROUND AND PURPOSE: Conceptual research utilization (CRU) is one indicator of an optimum practice environment that leads to improved patient and organizational outcomes. Yet, its measurement has not been adequately addressed. In this study, we investigated precision of scores obtained with a new CRU scale using item response theory (IRT) methods. METHODS: We analyzed the responses from 1,349 health care aides from 30 Canadian nursing homes using Samejima's (1969, 1996) graded response model (GRM). RESULTS: Findings suggest that the CRU scale is most precise at low to average trait levels with significantly less precision at higher trait levels. CONCLUSIONS: The scale showed acceptable precision at low to average trait levels. New items and/or different response options that capture higher trait levels are needed. Future development of the scale is discussed.
BACKGROUND AND PURPOSE: Conceptual research utilization (CRU) is one indicator of an optimum practice environment that leads to improved patient and organizational outcomes. Yet, its measurement has not been adequately addressed. In this study, we investigated precision of scores obtained with a new CRU scale using item response theory (IRT) methods. METHODS: We analyzed the responses from 1,349 health care aides from 30 Canadian nursing homes using Samejima's (1969, 1996) graded response model (GRM). RESULTS: Findings suggest that the CRU scale is most precise at low to average trait levels with significantly less precision at higher trait levels. CONCLUSIONS: The scale showed acceptable precision at low to average trait levels. New items and/or different response options that capture higher trait levels are needed. Future development of the scale is discussed.