Discussion of "Simple Defensible Sample Sizes Based on Cost Efficiency" by Peter Bacchetti, Charles E. McCulloch, and Mark R. Segal
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
When introducing the notion of sample size estimation we like to share the story of the statistician who responded to the question: “How many subjects do I need for my study?” with a Socratic-like: “How many bricks does it take to build a wall?” The answer of course depends on what kind of wall one seeks to build. Bacchetti, McCulloch, and Segal (BMS) put forward a new architecture for wall building. Their paper is a welcome call to others to more explicitly consider cost perspectives when planning the size of trials. The blueprints are impressive and the wall is touted as being designed in a cost-effective manner. However, at the end of the day one is left with a nagging concern about its functionality. Different types of studies have different purposes. For example, a clinical trial might be considered either exploratory or confirmatory depending upon whether it is an early phase study to generate data that will support further investigation or a late phase study designed to corroborate promising preliminary results. The requirement for the latter is typically demanding in that its intent is to affect medical practice and a strong wall is needed to support that enterprise. As Peto, Collins, and Gray (1995) note, “The medical importance of treatment effects that are only moderate in size implies the need for large-scale randomized evidence (…). Reliable detection or refutation of moderate differences requires negligible biases and small random errors.”
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it