PSRM · 2025

Linking datasets on organizations

Libgober & Jerzak

How do you reliably connect organization records across sources when names are messy, identifiers are incomplete, and scale is enormous? This project focuses on linkage methods, open collaboration, and validation strategies that work in the real world.

Record linkage Validation Organizations Open collaboration
Why it matters

Linkage at scale

When datasets don’t talk to each other, we lose power, coverage, and the ability to test theory. Linking organizational records — carefully, transparently, and at scale — can turn fragmented sources into reusable research infrastructure.

Scale

Linkage strategies designed for very large, messy corpora.

Transparency

Clear error modes and auditing where mistakes matter.

Reusability

Linked outputs that other researchers can build on.