Principal Component Pursuit for Environmental Epidemiology
Retrieve default PCP parameter settings for given matrix
Cross-validated grid search for PCP models
Hard-thresholding operator
Impute missing values in given matrix
Estimate rank of a given matrix
pcpr: Principal Component Pursuit for Environmental Epidemiology
Project matrix to rank r
Square root principal component pursuit (convex PCP)
Rank-based robust matrix completion (non-convex PCP)
Simulate simple mixtures data
Simulate limit of detection data
Simulate random missingness in a given matrix
Compute singular values of given matrix
Estimate sparsity of given matrix
Implementation of the pattern recognition technique Principal Component Pursuit tailored to environmental health data, as described in Gibson et al (2022) <doi:10.1289/EHP10479>.
Useful links