Corpcor: Shrinkage Estimators for Covariance and Partial Correlation

Implements a James-Stein-type shrinkage estimator for covariance matrices, with separate shrinkage for variances and correlations. The method is described in Schafer and Strimmer (2005) and Opgen-Rhein and Strimmer (2007). The package provides functions for computing partial correlations, matrix inverses, powers, singular value decomposition, and checking matrix properties.

Use Cases

• Estimate stable covariance matrices based on the described shrinkage method for 'small n, large p' data.
• Compute partial correlations and partial variances based on the provided shrinkage estimators.
• Calculate matrix inverses and powers based on the efficient computation functions for the shrinkage correlation matrix.
• Perform singular value decomposition and check matrix rank based on the available fast functions.

Strengths

• Method is described as computationally and statistically efficient.
• Approach is applicable to 'small n, large p' data and always returns a positive definite, well-conditioned matrix.
• Package provides multiple related estimators and matrix operations, including for partial correlations and matrix powers.

Limitations

• Row count, column details, and data scale are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Authors: Juliane Schafer, Rainer Opgen-Rhein, Verena Zuber, Miika Ahdesmaki, A. Pedro Duarte Silva, and Korbinian Strimmer.

Collection Method

Software package implementing statistical methods from cited academic papers.