Add federated non-inferiority meta-analysis task and the AcT analysis - #71
Open
legend5teve wants to merge 1 commit into
Open
legend5teve wants to merge 1 commit into
legend5teve wants to merge 1 commit into
Conversation
Adds the r_noninferiority_meta task, which implements federated site-stratified non-inferiority meta-analysis in R. Each site returns a proportion difference and its standard error and the coordinating centre pools them by inverse-variance weighting using metafor. The module follows the layout of the existing r_* tasks, so tasks_validator picks it up by convention with no registration step. A task referencing it uses "model": "RNoninferiorityMeta". Adds analysis/act-noninferiority, holding the single entry-point script behind Table 1, Table 2 and Table 3 of the accompanying manuscript together with the archived artifacts of the run that produced them. The task scripts are resolved from the location of run_analysis.R rather than from the working directory, so the run behaves the same way wherever it is started, and a misplaced task directory fails at startup with a clear error. The archived run reproduced the per-arm counts published by the parent trial for all four outcomes, which is the provenance check the script enforces before it writes a table. The crude primary estimate is 2.1365 with a 95% interval of -2.6114 to 6.8844 and the site-stratified estimate is 2.1168 with -2.5325 to 6.7661. Across the ten specifications of the sensitivity grid the lower bound stays between -2.9544 and -2.0917. The trial data are restricted and are not included. The script takes the extract as an argument and records neither its path nor its file name, and the per-site partitions are removed when the run ends, so the archived output holds only the tables and the log. Adds .zenodo.json so the archived release carries the manuscript author list and description rather than metadata derived from commit history.
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds the
r_noninferiority_metatask, which implements federated site-stratified non-inferiority meta-analysis in R. Each site returns a proportion difference and its standard error and the coordinating centre pools them by inverse-variance weighting using metafor. The module follows the layout of the existingr_*tasks, sotasks_validatorpicks it up by convention with no registration step. A task referencing it uses"model": "RNoninferiorityMeta".Adds
analysis/act-noninferiority, holding the single entry-point script behind Table 1, Table 2 and Table 3 of the accompanying manuscript together with the archived artifacts of the run that produced them. The task scripts are resolved from the location ofrun_analysis.Rrather than from the working directory, so the run behaves the same way wherever it is started.The archived run reproduced the per-arm counts published by the parent trial for all four outcomes, which is the provenance check the script enforces before it writes a table. The crude primary estimate is 2.1365 with a 95% interval of -2.6114 to 6.8844 and the site-stratified estimate is 2.1168 with -2.5325 to 6.7661. Across the ten specifications of the sensitivity grid the lower bound stays between -2.9544 and -2.0917.
The trial data are restricted and are not included. The script takes the extract as an argument and records neither its path nor its file name, and the per-site partitions are removed when the run ends, so the archived output holds only the tables and the log.
Adds
.zenodo.jsonso the archived release carries the manuscript author list and description rather than metadata derived from commit history.This lands ahead of a
v0.2.0release, which the Zenodo webhook will archive as a new version under concept DOI 10.5281/zenodo.20388959 for the manuscript's Code Availability section.🤖 Generated with Claude Code
https://claude.ai/code/session_01QyV1P2jh8bSwD5W5mkCGzu