This manuscript presents a framework to develop vector error correction (VEC) models applicable to forecasting the short- and long-run movements of the average hourly earnings of construction labor, which is an essential predictor of the construction labor costs. These models characterize the relationship between average hourly earnings and a set of explanatory variables. The framework is applied to develop VEC forecasting models for the average hourly earnings of construction labor in the USA based on the identified variables that govern its movements, such as Global Energy Price Index, Gross Domestic Product, and Personal Consumption Expenditures. More than 150 candidate VEC models were created, of which 25 passed the diagnostics. The most appropriate model was then identified by comparing the prediction performance of these models when applied to the forecasting average hourly earnings over 36-months. The proposed framework and the ensuing models address the need for appropriate models that can forecast the short- and long-run movements of the labor costs. Practitioners can use the proposed framework to develop much-needed forecast models and estimate construction labor costs of the various projects. The insights derived from the development and applications of these models can enhance the chances of project success.

该手稿提供了一个框架，可用于开发矢量误差校正（VEC）模型，该模型可用于预测建筑工人平均每小时收入的短期和长期变动，这是建筑工人成本的重要预测指标。这些模型描述了平均小时收入与一组解释变量之间的关系。该框架可根据确定的控制其变动的变量（例如全球能源价格指数，国内生产总值和个人消费支出）来开发VEC预测模型，以用于美国建筑工人的平均每小时收入。创建了150多个候选VEC模型，其中25个通过了诊断。然后，通过将这些模型应用于36个月的预测平均每小时收入，将这些模型的预测性能进行比较，从而确定最合适的模型。拟议的框架和随后的模型满足了对可以预测劳动力成本的短期和长期变动的适当模型的需求。从业人员可以使用提出的框架来开发急需的预测模型，并估算各个项目的建筑人工成本。从这些模型的开发和应用中得出的见解可以增加项目成功的机会。从业人员可以使用提出的框架来开发急需的预测模型，并估算各个项目的建筑人工成本。从这些模型的开发和应用中得出的见解可以增加项目成功的机会。从业人员可以使用提出的框架来开发急需的预测模型，并估算各个项目的建筑人工成本。从这些模型的开发和应用中得出的见解可以增加项目成功的机会。