One Size Doesn’t Fit All: Administrative Data Quality Frameworks for Production of Official Statistics
Bibliographic record
Abstract
Background with rationaleThe use of administrative data is key to achieving the UK Statistics Authority’s strategy of Better Statistics, Better Decisions. Integrating administrative data into official statistics can benefit policy decisions by allowing the possibility of greater granularity and improved timeliness in outputs, while delivering efficiency gains and reducing respondent burden. Quality assessment and communicating uncertainty of administrative data sources is critical to their effective integration into official statistical outputs. Main AimThis presentation will discuss the main challenges of quality assuring statistical outputs containing administrative data. The differences in existing quality frameworks and identified quality metrics will be discussed. In addition, the presentation will cover the need to tailor quality assessment to answer a specific research question that an identified source is being used for and the considerations required. Methods/ApproachA comprehensive literature review was carried out, bringing together existing quality frameworks and metrics from National Statistical Institutes (NSIs) and academia for production of statistics using administrative data sources. ResultsThe main challenges and considerations faced when quality assuring outputs produced using administrative sources have been identified. The quality requirements for different outputs across social, business and census statistics were summarised and a general quality framework for admin data developed. This framework draws on international best practices for use in the UK statistical system. ConclusionIntegrating administrative data presents challenges can’t be solved by a one-size fits all framework. Through unifying available guidance, an adaptable quality assurance methodology has been created, enabling the use of public data for the public good.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.400 | 0.452 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| Bibliometrics | 0.021 | 0.022 |
| Science and technology studies | 0.008 | 0.028 |
| Scholarly communication | 0.044 | 0.034 |
| Open science | 0.011 | 0.019 |
| Research integrity | 0.010 | 0.017 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".