tcv: Determining the Number of Factors in Poisson Factor Models via Thinning Cross-Validation

Implements methods for selecting the number of factors in Poisson factor models, with a primary focus on Thinning Cross-Validation (TCV). The TCV method is based on the 'data thinning' technique, which probabilistically partitions each count observation into training and test sets while preserving the underlying factor structure. The Poisson factor model is then fit on the training set, and model selection is performed by comparing predictive performance on the test set. This toolkit is designed for researchers working with high-dimensional count data in fields such as genomics, text mining, and social sciences. The data thinning methodology is detailed in Dharamshi et al. (2025) <doi:10.1080/01621459.2024.2353948> and Wang et al. (2025) <doi:10.1080/01621459.2025.2546577>.

Version:	0.1.0
Imports:	stats, GFM, countsplit, irlba
LinkingTo:	Rcpp, RcppArmadillo
Suggests:	knitr, rmarkdown, testthat (≥ 3.0.0)
Published:	2025-09-23
Author:	Zhijing Wang [aut, cre], Heng Peng [aut], Peirong Xu [aut]
Maintainer:	Zhijing Wang <wangzhijing at sjtu.edu.cn>
BugReports:	https://github.com/Wangzhijingwzj/tcv/issues
License:	GPL (≥ 3)
URL:	https://github.com/Wangzhijingwzj/tcv
NeedsCompilation:	yes
SystemRequirements:	C++17
CRAN checks:	tcv results

Documentation:

Reference manual:

tcv.html , tcv.pdf

Downloads:

Package source:	tcv_0.1.0.tar.gz
Windows binaries:	r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries:	r-release (arm64): not available, r-oldrel (arm64): not available, r-release (x86_64): not available, r-oldrel (x86_64): not available

Linking:

Please use the canonical form https://CRAN.R-project.org/package=tcv to link to this page.