Municipal water consumption forecast accuracy

Thomas M. Fullerton, Angel Molina

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

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
Volume46
Issue number6
DOIs
StatePublished - Jun 1 2010
Externally publishedYes

Fingerprint

econometrics
water economics
accuracy assessment
competitiveness
labor market
water
forecast
water consumption
fill
labor
infrastructure
water quality
market
cost
planning

ASJC Scopus subject areas

  • Water Science and Technology

Cite this

Municipal water consumption forecast accuracy. / Fullerton, Thomas M.; Molina, Angel.

In: Water Resources Research, Vol. 46, No. 6, W06515, 01.06.2010.

Research output: Contribution to journalArticle

@article{73fb4b2c29c64e0bbcf2e6a33821e752,
title = "Municipal water consumption forecast accuracy",
abstract = "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.",
author = "Fullerton, {Thomas M.} and Angel Molina",
year = "2010",
month = "6",
day = "1",
doi = "10.1029/2009WR008450",
language = "English (US)",
volume = "46",
journal = "Water Resources Research",
issn = "0043-1397",
publisher = "American Geophysical Union",
number = "6",

}

TY - JOUR

T1 - Municipal water consumption forecast accuracy

AU - Fullerton, Thomas M.

AU - Molina, Angel

PY - 2010/6/1

Y1 - 2010/6/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=77954408732&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954408732&partnerID=8YFLogxK

U2 - 10.1029/2009WR008450

DO - 10.1029/2009WR008450

M3 - Article

AN - SCOPUS:77954408732

VL - 46

JO - Water Resources Research

JF - Water Resources Research

SN - 0043-1397

IS - 6

M1 - W06515

ER -