PAGFL: Joint Estimation and Identification of Latent Groups in Panel Data Models

In panel data analysis, unobservable group structures are a common challenge. Disregarding group-level heterogeneity by assuming an entirely homogeneous panel can introduce bias. Conversely, estimating individual coefficients for each cross-sectional unit is inefficient and may lead to high uncertainty. This package addresses this issue by implementing the pairwise adaptive group fused Lasso (PAGFL) by Mehrabani (2023) <doi:10.1016/j.jeconom.2022.12.002>. PAGFL is an efficient methodology to identify latent group structures and estimate group-specific coefficients simultaneously.

Version: 1.0.1
Imports: Rcpp, pbapply
LinkingTo: Rcpp, RcppArmadillo
Published: 2024-02-17
Author: Paul Haimerl ORCID iD [aut, cre], Ali Mehrabani ORCID iD [ctb]
Maintainer: Paul Haimerl <paul.haimerl at>
License: AGPL (≥ 3)
NeedsCompilation: yes
Materials: README NEWS
CRAN checks: PAGFL results


Reference manual: PAGFL.pdf


Package source: PAGFL_1.0.1.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): PAGFL_1.0.1.tgz, r-oldrel (arm64): PAGFL_1.0.1.tgz, r-release (x86_64): PAGFL_1.0.1.tgz
Old sources: PAGFL archive


Please use the canonical form to link to this page.