R D Farmer1, J Emami. 1. Department of Community Medicine, Charing Cross and Westminster Medical School, London.
Abstract
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.
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.