Data validation and data quality assessment

Francois Clemens; Mathieu Lepot; Frank Blumensaat; Dominik Leutnant; Guenter GRUBER

Data validation and data quality assessment

Francois Clemens^*, Mathieu Lepot, Frank Blumensaat, Dominik Leutnant, Guenter GRUBER

^*Corresponding author for this work

Institute of Urban Water Management and Landscape Water Engineering (2150)

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Once data have been recorded, data validation procedures have to be conducted to assess the quality of the data, i.e. give a confidence grade. Furthermore, gaps may occur in time series and, depending on the purposes, these can be given values by application of e.g. interpolation. Since both aspects are strongly
correlated, this chapter gives an overview on the main data validation and data curation/imputation methods. Instead of offering exhaustive details on existing methods, this chapter aims at providing concepts for most popular techniques, a discussion of their advantages and disadvantages in the light of different cases of application, and some thoughts on potential impacts of the choices that must be made. Despite involving mathematical methods, data validation remains a largely subjective process: every data user must be aware of those subjectivities.

Original language	English
Title of host publication	Metrology in Urban Drainage and Stormwater Management: Plug and Pray
Publisher	IWA Publishing
Chapter	Chapter 9
Pages	327 - 390
Number of pages	64
ISBN (Electronic)	9781789060119
Publication status	Published - Aug 2021

Keywords

metrology, urban drainage, stormwater management, data validation, data quality assessment

Fields of Expertise

Sustainable Systems

Access to Document

https://doi.org/10.2166/9781789060119_0327

Cite this

@inbook{7e4b00494ecd4790bd5218a1a748a35d,

title = "Data validation and data quality assessment",

abstract = "Once data have been recorded, data validation procedures have to be conducted to assess the quality of the data, i.e. give a confidence grade. Furthermore, gaps may occur in time series and, depending on the purposes, these can be given values by application of e.g. interpolation. Since both aspects are stronglycorrelated, this chapter gives an overview on the main data validation and data curation/imputation methods. Instead of offering exhaustive details on existing methods, this chapter aims at providing concepts for most popular techniques, a discussion of their advantages and disadvantages in the light of different cases of application, and some thoughts on potential impacts of the choices that must be made. Despite involving mathematical methods, data validation remains a largely subjective process: every data user must be aware of those subjectivities.",

keywords = "metrology, urban drainage, stormwater management, data validation, data quality assessment",

author = "Francois Clemens and Mathieu Lepot and Frank Blumensaat and Dominik Leutnant and Guenter GRUBER",

year = "2021",

month = aug,

language = "English",

pages = "327 -- 390",

booktitle = "Metrology in Urban Drainage and Stormwater Management: Plug and Pray",

publisher = "IWA Publishing",

address = "United Kingdom",

}

TY - CHAP

T1 - Data validation and data quality assessment

AU - Clemens, Francois

AU - Lepot, Mathieu

AU - Blumensaat, Frank

AU - Leutnant, Dominik

AU - GRUBER, Guenter

PY - 2021/8

Y1 - 2021/8

N2 - Once data have been recorded, data validation procedures have to be conducted to assess the quality of the data, i.e. give a confidence grade. Furthermore, gaps may occur in time series and, depending on the purposes, these can be given values by application of e.g. interpolation. Since both aspects are stronglycorrelated, this chapter gives an overview on the main data validation and data curation/imputation methods. Instead of offering exhaustive details on existing methods, this chapter aims at providing concepts for most popular techniques, a discussion of their advantages and disadvantages in the light of different cases of application, and some thoughts on potential impacts of the choices that must be made. Despite involving mathematical methods, data validation remains a largely subjective process: every data user must be aware of those subjectivities.

AB - Once data have been recorded, data validation procedures have to be conducted to assess the quality of the data, i.e. give a confidence grade. Furthermore, gaps may occur in time series and, depending on the purposes, these can be given values by application of e.g. interpolation. Since both aspects are stronglycorrelated, this chapter gives an overview on the main data validation and data curation/imputation methods. Instead of offering exhaustive details on existing methods, this chapter aims at providing concepts for most popular techniques, a discussion of their advantages and disadvantages in the light of different cases of application, and some thoughts on potential impacts of the choices that must be made. Despite involving mathematical methods, data validation remains a largely subjective process: every data user must be aware of those subjectivities.

KW - metrology, urban drainage, stormwater management, data validation, data quality assessment

M3 - Chapter

SP - 327

EP - 390

BT - Metrology in Urban Drainage and Stormwater Management: Plug and Pray

PB - IWA Publishing

ER -