Dataset
Workers
Employer-employee matched data with anonymized firm and worker identifiers plus job-title and year fields.
Graph Summary
A large, realistic two-way firm-worker benchmark.
The primary benchmark graph is built from unique (id1, id2) pairs. The figure shows a binned sparsity pattern of the bipartite incidence block, with both partitions relabeled to contiguous integer identifiers. This block is the off-diagonal part of the corresponding graph Laplacian.
Variables
Columns in the clean CSV:
The v1 graph uses id1 and id2. Additional identifier-like columns available for richer specifications: id3, id4.
Source Notes
Anonymized employer-employee matched panel collected by the author.
Regressors and outcome are synthetic benchmark variables.
Historical Benchmark
2017 SEC benchmark timings for this dataset, in seconds:
| Method | Citation | Seconds |
|---|---|---|
| MAP-Aitken | (Guimaraes 2012) | 484.1 |
| MAP-SD | (Gaure 2013) | 146.0 |
| MAP-CG-Sym | (Correia 2016) | 169.6 |
| MAP+Prune | (Correia 2016) | 646.1 |
| LSMR | (Gomez 2016) | 356.3 |