Geographically weighted regression (GWR) is a popular tool for modeling
spatial heterogeneity in a regression model. However, the current weighting
function used in GWR only considers the geographical distance, while the
attribute similarity is totally ignored. In this study, we proposed a covariate
weighting function that combines the geographical distance and attribute
distance. The covariate-distance weighted regression (CWR) is the extension of
GWR including geographical distance and attribute distance. House prices are
affected by numerous factors, such as house age, floor area, and land use.
Prediction model is used to help understand the characteristics of regional
house prices. The CWR was used to understand the relationship between the house
price and controlling factors. The CWR can consider the geological and
attribute distances, and produce accurate estimates of house price that
preserve the weight matrix for geological and attribute distance functions.
Results show that the house attributes/conditions and the characteristics of
the house, such as floor area and house age, might affect the house price.
After factor selection, in which only house age and floor area of a building
are considered, the RMSE of the CWR model can be improved by 2.9%-26.3% for
skyscrapers when compared to the GWR. CWR can effectively reduce estimation
errors from traditional spatial regression models and provide novel and
feasible models for spatial estimation.

本研究提出了一种基于地理和属性距离的加权回归模型，称之为 CWR，用于预测房屋价格，并分析了房龄、建筑面积等因素对房价的影响。结果表明，该模型可以通过降低传统空间回归模型的估计误差来提高房屋价格的准确性。