Content, review and definition of the 23 data quality components collected from the reference literature
| DQC | Literature source | Corresponding data quality framework | Definition |
|---|---|---|---|
| Reliability | Sachs et al. (2018), van de Berg et al. (2014) | UN Statistics Quality Assurance Framework (2018), European Statistics Code of Practice (2017), IMF Data Quality Assessment Framework (2003) | Data itself is generated from reliable sources with scientific robustness |
| Relevance | OECD (2008), Salzman (2003), Mazziotta and Pareto (2013), Alipour and Ahmadi (2017), Brackstone (1999), European Commission (2007) | European Statistics Code of Practice (2017), (Uganda Standards for Statistics 942), UN Statistics Quality Assurance Framework (2018), Quality Framework and Guidelines for OECD Statistical Activities (2011) | Data serve to address the purposes for which they are sought by users, or which they are presented as addressing |
| Completeness | Black and van Nederpelt (2020), Strong et al. (1997), Strong et al. (1997), Weidema and Wesnæs (1996), Odeny et al. (2023), Alipour and Ahmadi (2017) | – | Coverage or percentage to which all required data is known from the relevant sources |
| Temporal representativeness | Weidema and Wesnæs (1996) | – | Data reflects the true population of the underlying study regarding the time/age of the dataset |
| Geographical representativeness | Weidema and Wesnæs (1996) | – | Data reflects the true population of the underlying study regarding the location of the dataset |
| Serviceability | Black and van Nederpelt (2020) | IMF Data Quality Assessment Framework (2003) | Data, with adequate periodicity and timeliness, are consistent and follow a predictable revisions policy |
| Accessibility | OECD (2008), Mazziotta and Pareto (2013), Alipour and Ahmadi (2017), Brackstone (1999), European Commission (2007) | (Uganda Standards for Statistics 942), European Statistics Code of Practice (2017), UN Statistics Quality Assurance Framework (2018), IMF Data Quality Assessment Framework (2003), Quality Framework and Guidelines for OECD Statistical Activities (2011) | Data and metadata are easily available and assistance to users is adequate |
| Accuracy | OECD (2008), Sachs et al. (2018), Strong et al. (1997), Alipour and Ahmadi (2017), Brackstone (1999), European Commission (2007) | Uganda Standards for Statistics 942, UN Statistics Quality Assurance Framework (2018), European Statistics Code of Practice (2017), IMF Data Quality Assessment Framework (2003), Quality Framework and Guidelines for OECD Statistical Activities (2011) | Source data and statistical techniques are sound and statistical outputs sufficiently portray reality |
| Methodological soundness | UBOS, (2013-unpublished) | UN Statistics Quality Assurance Framework (2018), European Statistics Code of Practice (2017), IMF Data Quality Assessment Framework (2003) | The methodological basis for the statistics follows internationally accepted standards, guidelines, or good practices |
| Assurances of integrity | Black and van Nederpelt (2020), Federal Committee on Statistical Methodology (2020) | IMF Data Quality Assessment Framework (2003) | The principle of objectivity in the collection, processing, and dissemination of statistics is firmly adhered to |
| Global relevance | Sachs et al. (2018) | – | Data are relevant for monitoring achievement of the phenomena and applicable to the entire country. They are nationally comparable and allow for direct comparison of performance across areas |
| Statistical adequacy | Sachs et al. (2018) | – | Data selected represent valid and reliable measures |
| Timeliness | OECD (2008), Mazziotta and Pareto (2013), Sachs et al. (2018), WHO (2022), Alipour and Ahmadi (2017), Brackstone (1999), European Commission (2007) | UN Statistics Quality Assurance Framework (2018), Quality Framework and Guidelines for OECD Statistical Activities (2011) | The indicators selected are up to date and published on a reasonably prompt schedule |
| Content | Booysen (2002) | – | Data measures all or some facets of the construct under study |
| Technique and method | Booysen (2002) | – | Data measures the construct under study in a quantitative (qualitative), objective (subjective), cardinal (ordinal) or unidimensional (multidimensional) manner |
| Comparative application | Booysen (2002), WHO (2022), European Commission (2007) | (Uganda Standards for Statistics 942), (European Statistics Code of Practice, 2017) | Data compares the level of the construct under study (1) across space (“cross-section”) or time (“time-series”), and (2) in an absolute or relative manner |
| Focus | Booysen (2002) | – | Data measures the construct under study in terms of input (“means”) or output (“ends”) |
| Clarity and simplicity | Booysen (2002), European Commission (2007) | European Statistics Code of Practice (2017) | Data are clear and simple in their content, purpose, method, comparative application and focus |
| Availability | Booysen (2002) | (Uganda Standards for Statistics 942) | Data are readily available on a particular indicator across time and space |
| Flexibility | Booysen (2002) | Data are relatively flexible in allowing for changes in content, purpose, method, comparative application and focus | |
| Interpretability | Black and van Nederpelt (2020), Strong et al. (1997), Brackstone (1999) | UN Statistics Quality Assurance Framework (2018), Quality Framework and Guidelines for OECD Statistical Activities (2011) | Data are easily understood and properly used by users |
| Professional independence | Eurostat (2019), (UBOS, 2013-unpublished) | European Statistics Code of Practice (2017) | Systems, procedures and practices for data production are free from undue political interference |
| Gender responsiveness | (UBOS, 2013-unpublished) | – | Data easily portray the differences between men and women, girls and boys |
| DQC | Literature source | Corresponding data quality framework | Definition |
|---|---|---|---|
| Reliability | UN Statistics Quality Assurance Framework (2018), | Data itself is generated from reliable sources with scientific robustness | |
| Relevance | Data serve to address the purposes for which they are sought by users, or which they are presented as addressing | ||
| Completeness | – | Coverage or percentage to which all required data is known from the relevant sources | |
| Temporal representativeness | – | Data reflects the true population of the underlying study regarding the time/age of the dataset | |
| Geographical representativeness | – | Data reflects the true population of the underlying study regarding the location of the dataset | |
| Serviceability | IMF Data Quality Assessment Framework (2003) | Data, with adequate periodicity and timeliness, are consistent and follow a predictable revisions policy | |
| Accessibility | (Uganda Standards for Statistics 942), | Data and metadata are easily available and assistance to users is adequate | |
| Accuracy | Uganda Standards for Statistics 942, UN Statistics Quality Assurance Framework (2018), | Source data and statistical techniques are sound and statistical outputs sufficiently portray reality | |
| Methodological soundness | UBOS, (2013-unpublished) | UN Statistics Quality Assurance Framework (2018), | The methodological basis for the statistics follows internationally accepted standards, guidelines, or good practices |
| Assurances of integrity | IMF Data Quality Assessment Framework (2003) | The principle of objectivity in the collection, processing, and dissemination of statistics is firmly adhered to | |
| Global relevance | – | Data are relevant for monitoring achievement of the phenomena and applicable to the entire country. They are nationally comparable and allow for direct comparison of performance across areas | |
| Statistical adequacy | – | Data selected represent valid and reliable measures | |
| Timeliness | UN Statistics Quality Assurance Framework (2018), Quality Framework and Guidelines for OECD Statistical Activities (2011) | The indicators selected are up to date and published on a reasonably prompt schedule | |
| Content | – | Data measures all or some facets of the construct under study | |
| Technique and method | – | Data measures the construct under study in a quantitative (qualitative), objective (subjective), cardinal (ordinal) or unidimensional (multidimensional) manner | |
| Comparative application | (Uganda Standards for Statistics 942), ( | Data compares the level of the construct under study (1) across space (“cross-section”) or time (“time-series”), and (2) in an absolute or relative manner | |
| Focus | – | Data measures the construct under study in terms of input (“means”) or output (“ends”) | |
| Clarity and simplicity | Data are clear and simple in their content, purpose, method, comparative application and focus | ||
| Availability | (Uganda Standards for Statistics 942) | Data are readily available on a particular indicator across time and space | |
| Flexibility | Data are relatively flexible in allowing for changes in content, purpose, method, comparative application and focus | ||
| Interpretability | UN Statistics Quality Assurance Framework (2018), Quality Framework and Guidelines for OECD Statistical Activities (2011) | Data are easily understood and properly used by users | |
| Professional independence | Systems, procedures and practices for data production are free from undue political interference | ||
| Gender responsiveness | (UBOS, 2013-unpublished) | – | Data easily portray the differences between men and women, girls and boys |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.