Supervised Heterogeneous Gaussian Graphical Models with Spectrometric Analysis

A research dataset accompanies a proposed supervised heterogeneous Gaussian graphical model for analyzing data with continuous or discrete response variables. The dataset includes spectrometric data used to illustrate the model's performance, as published by author Xin Zeng in 2026. The total package is 2.2 MB, containing text files, a PDF, and compressed archives.

Use Cases

• Validate the proposed high-dimensional ECM algorithm's performance on the included spectrometric data.
• Benchmark new heterogeneous network analysis methods against the model's outputs for continuous response variables.
• Analyze subgroup structures identified by the supervised model within the spectrometric dataset.
• Reproduce the numerical studies demonstrating the model's statistical analysis and prediction performance.

Strengths

• Dataset is directly linked to a peer-reviewed publication with supplementary materials available online.
• The model accommodates both continuous and discrete response variables, increasing applicability.
• Full research context is provided, including a non-asymptotic statistical analysis of the algorithm outputs.

Limitations

• The dataset is small at 2.2 MB, limiting the scale of analysis possible.
• Specific row count, column names, and data structure are not provided in the description.
• The primary focus is methodological demonstration, which may limit generalizability to other domains.

Provenance

Source

figshare, published by author Xin Zeng.

Collection Method

Created for numerical studies to demonstrate a proposed statistical model, includes spectrometric data.

Freshness

Last updated in April 2026, indicating recent research.