Refinement of Storey Enclosure Forecasting Method

Previous researches have suggested that there is only little improvement in the accuracy of building forecasts as design develops. It has been criticized that established conventional forecasting methods also lack measures of their own performance. An early stage price forecasting model, the Storey Enclosure Method developed by James in 1954, uses some physical measurements of buildings to estimate building prices. Although James’ Storey Enclosure Method (JSEM) is not a widely used model in practice, the model has been proved empirically, if rather crudely, to be a better model than other commonly used models. This paper describes some preliminary research to refine JSEM using regression techniques. Advanced features of the proposed model include the use of cross validation for reliability analysis that simulates how forecasts are produced in practice and a dual stepwise selection strategy that enhances the chance of identifying the best model. To precisely judge the performance of models, this paper suggests using bias and consistency with parametric and non-parametric statistical inferences.