Understanding the differential pattern of length of stay (LOS) in long-term care (LTC) due to residents? attributes has important practical implications in the management of long-term care. In this paper, we extend a previously developed modelling approach to incorporate residents? attributes. Two applications using data collected by a local authority in England are presented to demonstrate the potential use of this extension. In the study of possible difference in LOS pattern due to gender, our model provides quantitative support to the observations that male residents admitted to NC take more time to settle down and have poorer short-term survival prospect than female residents.