AWWA JAW56927

Any utility facing rapid growth and expensive capital improvementsneeds accurate water demand forecasts for planning.For a smaller suburban utility, the planning effort is constrainedby limited staff and financial resources. Although smallerutilities may understand the benefits of using multiple regressionfor water demand forecasting, they may instead decide to useconventional trend analysis or unit water demand analysis. Thisdecision is often based on the belief that multiple regression isdifficult to implement, requires staff experts on statistics, and istoo time-consuming.This study was undertaken to eliminate these misperceptions.It shows that: regression-based water demand modelsare easy to develop using features available in most spreadsheetand statistical software packages; and, the time to develop amodel can be reduced from days to minutes if a systematicmodel construction procedure such as stepwise regressionis used.Although good information is available on using multipleregression analysis to investigate historic water demand, littleinformation is available on the merits of stepwise regressionand/or other systematic model construction techniques. Thisarticle can help make regression-based water demand analysismore accessible to water suppliers with limited resources andstaff expertise. Includes 10 references, tables, figures.

Product Details

Edition:

Vol. 94 - No. 10

Published:

10/01/2002

Number of Pages:

11

File Size:

1 file , 500 KB