Municipal water consumption forecast accuracy

Thomas M. Fullerton, Angel L. Molina

Research output: Contribution to journalArticlepeer-review

17 Scopus citations


Municipal water consumption planning is an active area of research because of infrastructure construction and maintenance costs, supply constraints, and water quality assurance. In spite of that, relatively few water forecast accuracy assessments have been completed to date, although some internal documentation may exist as part of the proprietary "grey literature." This study utilizes a data set of previously published municipal consumption forecasts to partially fill that gap in the empirical water economics literature. Previously published municipal water econometric forecasts for three public utilities are examined for predictive accuracy against two random walk benchmarks commonly used in regional analyses. Descriptive metrics used to quantify forecast accuracy include root-mean-square error and Theil inequality statistics. Formal statistical assessments are completed using four-pronged error differential regression F tests. Similar to studies for other metropolitan econometric forecasts in areas with similar demographic and labor market characteristics, model predictive performances for the municipal water aggregates in this effort are mixed for each of the municipalities included in the sample. Given the competitiveness of the benchmarks, analysts should employ care when utilizing econometric forecasts of municipal water consumption for planning purposes, comparing them to recent historical observations and trends to insure reliability. Comparative results using data from other markets, including regions facing differing labor and demographic conditions, would also be helpful.

Original languageEnglish (US)
Article numberW06515
JournalWater Resources Research
Issue number6
StatePublished - Jun 2010
Externally publishedYes

ASJC Scopus subject areas

  • Water Science and Technology


Dive into the research topics of 'Municipal water consumption forecast accuracy'. Together they form a unique fingerprint.

Cite this