Models for forecasting hospital bed requirements in the acute sector.

STUDY OBJECTIVE The aim was to evaluate the current approach to forecasting hospital bed requirements. DESIGN 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. RESULTS 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. CONCLUSION The simple trend fitting approach is inferior to the time series approach in modelling hospital bed requirements.