A new four-arm within-study comparison: Design, implementation, and data
Bibliographic record
Abstract
Within-study comparisons (WSCs) use real, rather than simulated, data to compare estimates from observational studies against benchmarks from randomized controlled trials (RCTs). A primary goal of WSCs is to assess whether well-designed quasi-experimental designs (QEDs) can produce internally valid causal effect estimates comparable to those from RCTs. In this paper, we describe the design and implementation of a new type of WSC. Motivated by Shadish et al. (2008), we examine the impact of a mathematics training intervention and a vocabulary study session on posttest scores for mathematics and vocabulary, respectively. We extend the original design in three ways. First, before random assignment, we ask participants to express a preference for either the mathematics or vocabulary training session, after which they are randomly assigned regardless of preferences. This allows us to experimentally identify and estimate the overall average treatment effect (ATE) and two conditional ATEs: the average treatment effect on the treated (ATT) and the average treatment effect on the untreated (ATU). Second, participant recruitment and sample size (N = 2200) were determined through power analyses for comparing RCT and QED estimates, ensuring sufficient power for methodological comparisons. Finally, the study's eligibility criteria, recruitment, treatment allocation, and analysis plan were preregistered on the Open Science Foundation platform, and the data are publicly accessible. We believe that this WSC design and the resulting data set will be valuable for researchers seeking to evaluate causal inference methods and test identification assumptions using real-world data.
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 | 0.393 | 0.591 |
| Meta-epidemiology (narrow) | 0.004 | 0.005 |
| Meta-epidemiology (broad) | 0.009 | 0.010 |
| Bibliometrics | 0.007 | 0.009 |
| Science and technology studies | 0.004 | 0.007 |
| Scholarly communication | 0.006 | 0.012 |
| Open science | 0.006 | 0.009 |
| Research integrity | 0.012 | 0.011 |
| Insufficient payload (model declined to judge) | 0.018 | 0.004 |
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; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
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".