Purpose A data quality assessment framework (DQAF) is crucial in the foundational stages of composite indicators (CIs) construction by guaranteeing the selection of appropriate elementary indicators. While data quality components are rooted in UN Fundamental Principles of Official Statistics, different CI builders frequently utilize diverse criteria, with scant information regarding the cultivation of these components. This not only leads to diverse output but also prompts problems of justification. Design/methodology/approach This study, which focuses on a CI for public service delivery, utilized literature to identify 23 potential data quality components. Through the assessment of 19 experts, priority five components over the original 23 were: relevance, interpretability, methodological soundness, accuracy and statistical adequacy. An elaboration of these quality components, the quality criteria and associated scores ranging from 1 to 5 formed the DQAF. In application to service delivery data, an aggregated quality score below 2.0 served as a cut-off point for accepting elementary indicators into the initial list for CI construction. Findings The study's findings underscore the significance of a thoroughly documented DQAF, not only for CI construction, but also for its adaptability to different case studies, hence augmenting its application. The designed DQAF includes a dual orientation comprising two user-oriented (interpretability and relevance) and three producer-oriented (methodological soundness, accuracy and statistical adequacy) data quality components. This orientation connects data producers and users, offering a justification for indicators' selection and highlighting opportunities for enhancing data quality. The application of the DQAF to public service delivery led to the selection of 51 from 103 potential elementary indicators for the development of the relevant CI, with an overall acceptability rate of 48.6%. Originality/value The significance of expert participation in the formulation and implementation of the DQAF for a specific case study is emphasized to reduce subjectivity in scoring and guarantee thorough evaluations. The DQAF seeks to refine the selection process by addressing potential overlaps and redundancies in the chosen components, hence improving the overall quality and dependability of CIs. The approach to evaluate data quality proposed in this article is new and it is suggested for CI constructions in all subject fields.
Muhanguzi et al. (Mon,) studied this question.