Using Geographically Weighted Regression Models to Estimate Annual Average Daily Traffic

Annual average daily traffic (AADT) is important information for many transportation planning, design, operation, and maintenance activities and for funding allocation. Many studies have attempted AADT estimation by using various methods, such as the factor approach, regression analysis, and artificial neural networks. An application of geographically weighted regression (GWR) methods for estimating AADT is presented. GWR models allow model parameters to be estimated locally instead of globally, as in the case of ordinary linear regression (OLR) analysis. The spatial variation of the parameter estimates and the local R² from the GWR models were investigated, and the AADT estimation errors were analyzed. Compared with OLR models, the GWR models were more accurate and were useful for studying the effects of the regressors at different locations.