Lovelace's Square - PCA for missing data (O-ALS)

Orthogonalized Alternating Least Squares (OALS) is a decomposition method that iteratively calculates scores and loadings from data, even in the presence of missing values. By alternately optimizing scores and loadings while ensuring orthogonality, OALS provides robust, interpretable solutions for incomplete datasets.

Reference: Gomez-Sanchez, A.; Vitale, R.; Ruckebusch, C.; de Juan, A. (2024). Solving the missing value problem in PCA by Orthogonalized-Alternating Least Squares (O-ALS). Chemometrics and Intelligent Laboratory Systems, 250, 105153. https://doi.org/10.1016/j.chemolab.2024.105153

Our supporters

PCA for missing data (O-ALS)

Comments (0)

PCA for missing data (O-ALS)

Comments (0)