Models for forecasting hospital bed requirements in the acute sector.

• DOI: 10.1136/jech.44.4.307
• Publication Date: 2008-11-12T20:10:54Z
• Authors: R D Farmer; J Emami
• Keywords: Adult; Health Services Needs and Demand; Models, Statistical; Adolescent; Length of Stay; 3. Good health; 03 medical and health sciences; Patient Admission; 0302 clinical medicine; Hospital Bed Capacity; Hospital Planning; Humans; Regression Analysis; Emergencies; Bed Occupancy; Forecasting

The aim was to evaluate the current approach to forecasting hospital bed requirements.The study was a time series and regression analysis. The time series for mean duration of stay for general surgery in the age group 15-44 years (1969-1982) was used in the evaluation of different methods of forecasting future values of mean duration of stay and its subsequent use in the formation of hospital bed requirements.It has been suggested that the simple trend fitting approach suffers from model specification error and imposes unjustified restrictions on the data. Time series approach (Box-Jenkins method) was shown to be a more appropriate way of modelling the data.The simple trend fitting approach is inferior to the time series approach in modelling hospital bed requirements.