Scoping review of 30 papers finds that vertical methods for linear and logistic regression on partitioned health data rarely achieve equivalence to pooled analyses while also being communication-efficient and verifiably private.
Examples of papers that would not meet the criteria: the method is 5 presented on horizontally partitioned data only; or the method requires pooling all line- level data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multi-Site Health Research Integrating Complementary Data Sources: A Scoping Review of Statistical Inference Methods for Vertically Partitioned Data
Scoping review of 30 papers finds that vertical methods for linear and logistic regression on partitioned health data rarely achieve equivalence to pooled analyses while also being communication-efficient and verifiably private.