Farmer R D, Emami J
Department of Community Medicine, Charing Cross and Westminster Medical School, London.
J Epidemiol Community Health. 1990 Dec;44(4):307-12. doi: 10.1136/jech.44.4.307.
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.
旨在评估当前预测医院床位需求的方法。
该研究为时间序列和回归分析。使用1969年至1982年15至44岁年龄组普通外科平均住院时间的时间序列来评估预测平均住院时间未来值的不同方法，以及其随后在确定医院床位需求中的应用。
有人提出，简单趋势拟合方法存在模型设定误差，并对数据施加了不合理的限制。时间序列方法（博克斯-詹金斯方法）被证明是对数据进行建模的更合适方法。
在对医院床位需求进行建模时，简单趋势拟合方法不如时间序列方法。
