Building access to linked data for program evaluation: lessons and opportunities from the evaluation of a pan-Canadian skills training initiative
Bibliographic record
Abstract
In recent years, Canada’s statistical agency (Statistics Canada) has developed sophisticated linkage infrastructure through their Social Data Linkage Environment (SDLE), linking internal data sets held by Statistics Canada and external data held by researchers. While the SDLE presents an opportunity for better measurement of the effectiveness of policies and programs, to date it has not been used for this purpose outside of government, instead largely supporting academic research projects. This session presents a novel approach to program evaluation in the Canadian context, using the SDLE Statistics Canada administrative data alongside independently collected program data from multiple service providers to evaluate the outcomes and effectiveness of a portfolio of skills training programs. Our approach aims to both rigorously evaluate the long-term outcomes of participants in this portfolio of public skills training programs, and develop a replicable proof-of-concept for using linked data infrastructure in Canada to support program evaluations. Through this initiative, we identify the key design features needed to support this use case for linked data, including study design parameters, necessary datasets and linkage processes, and privacy and data governance policies. Finally, we identify opportunities for future replication of this approach in Canada, including strategies for expedited linkage and analysis of evaluation results that maintain privacy requirements. We find that using the SDLE infrastructure for program evaluation is both feasible and desirable, however barriers exist to replicating this approach, including sectoral capacity for collecting linkable data, and transposing linkage and confidentiality rules from an academic research to a program evaluation context.
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 | 0.577 | 0.538 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.009 | 0.017 |
| Science and technology studies | 0.017 | 0.016 |
| Scholarly communication | 0.031 | 0.018 |
| Open science | 0.010 | 0.027 |
| Research integrity | 0.004 | 0.009 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".