Multi-Study Poisson Factor Model for High-Dimensional Count Data

A methodological paper and associated data for a factor model designed to analyze high-dimensional count responses with covariates across multiple studies. The work was authored by Wei Liu and last updated in May 2026. The 1.6 MB resource includes files in PDF, ZIP, GZ, and TXT formats.

Use Cases

• Developing factor analysis methods for high-dimensional count data based on the described model.
• Extracting study-shared and study-specific latent factors from multi-study data.
• Analyzing overdispersed count responses with heterogeneous noise, as mentioned in the description.
• Applying the proposed variational estimation procedure to single-cell sequencing datasets.

Strengths

• Model accounts for heterogeneous noises and overdispersion among counts with augmented covariates.
• Includes a proposed criterion for selecting the optimal number of factors and rank of regression coefficients.
• The associated files total 1.6 MB and are available under a permissive CC-BY-4.0 license.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The primary content appears to be a research paper; the nature and scale of the accompanying data files are unspecified.

Provenance

Source

figshare

Collection Method

Likely generated from simulations and an analysis of a single-cell sequencing dataset, as described in the paper.

Freshness

Last updated 2026-05-26 18:19:02