Content area
Abstract
Water utility planning efforts are supported by short-term water demand forecasts. This study applies a Linear Transfer Function (LTF) approach in order to model and forecast water demand for single-family residential, multi-family residential, and nonresidential customer categories in Phoenix, Arizona. Out-of-sample simulations of water demand, with a monthly frequency, are generated for periods when actual demand is known. Descriptive measures and two formal tests are utilized to analyze the accuracy of LTF projections against two random walk benchmarks. The price elasticities for the single-family residential, multi-family residential, and nonresidential usage categories are -0.36, -0.31, and -0.75, respectively. The descriptive accuracy results for per customer water usage forecasts in most cases favor the LTF model, but the differences against the benchmarks are statistically insignificant in most cases. The LTF model successfully predicts the direction of movement in water usage around forty percent of the time. Mixed descriptive accuracy results are obtained from an analysis of the LTF customer base forecasts. Both benchmark forecasts are competitive with the LTF customer base forecasts.
