Predictive Statistical Cost Estimation Model for Existing Single Family Home Elevation Projects

One of the most preferred flood mitigation techniques for existing homes is raising the elevation of the lowest floor above the base flood elevation (BFE). Determination of project effectiveness through benefit-cost analysis (BCA) relies on the expected avoided flood loss and the project cost. Conventional construction cost estimates are highly detailed, considering specific details of the project; however, mitigation project decisions must often be made while considering only highly generalized building details. To provide a robust, generalized project cost estimation method, this paper implements data modeling and mining methods such as multiple regression, random forest, generalized additive model (GAM), and model evaluation and selection with cross-validation methods to hindcast elevation costs for existing single-family homes based on average floor area, increase in floor elevation, number of stories, and foundation type. Project cost data for homes elevated in Louisiana, United States, between 2005 and 2015 are used in cost prediction analysis. The statistical modeling results are compared with detailed estimations for several types of home foundations over a range of elevations. The results show substantial agreement between regression predictions and detailed estimates using RSMeans cost data.

Dieses Werk wurde unter der Creative-Commons-Lizenz Namensnennung 4.0 International (CC-BY 4.0) veröffentlicht und darf unter den Lizenzbedinungen vervielfältigt, verbreitet, öffentlich zugänglich gemacht, sowie abgewandelt und bearbeitet werden. Dabei muss der Urheber bzw. Rechteinhaber genannt und die Lizenzbedingungen eingehalten werden.