Relation between treatment benefit and underlying risk in meta-analysis: Standard of “label invariance” should not be abandoned

Abstract

Under normal circumstances we would leave it to Purves to decide when and how to publish the results of the evaluation.In the light of the intense interest in the project among doctors and industry, however, we took the rather unusual step of inviting Purves to prepare an interim report that we could put in the public domain.2The interim report is just that: an appreciation of work in progress, not a definitive statement of results.The conclusions in the report ("our very tentative assessment ...") are guarded, and the strongest claims are made not for the Prodigy system itself but for only the general concept of patient specific decision support.Those who wish to see formal tests of statisti- cal significance will have to wait patiently, as we are doing, for the final report.In the meantime, we continue to have every confidence in the integrity, statistical or otherwise, of Purves and his team.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 11 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.