Procrustes cross-validation

Version 1.1.0 (436 KB) by Sergey Kucheryavskiy
Set of methods for generating Procrustes validation sets for PCA/SIMCA, PCR and PLS models.
5.0
(1)
27 Downloads
Updated 13 Aug 2023

View License

Procrustes cross-validation is a new approach for validation of chemometric models. It makes possible to generate a new dataset, named "PV-set" and use it for validation of models in the same way as with an independent validation set. The current implementation supports Principal Component Analysis (method "pcvpca()", Principal Component Regression (method "pcvpcr()") and Partial Least Squares (method "pcvpls()") models.
Check Getting started documentation and see more details here: https://github.com/svkucheryavski/pcv.

Cite As

Kucheryavskiy S., Rodionova, O., & Pomerantsev, A. *Procrustes Cross-Validation of multivariate regression model*. Analytica Chimica Acta, 1255, 2023 [10.1016/j.aca.2023.341096](https://doi.org/10.1016/j.aca.2023.341096)

MATLAB Release Compatibility
Created with R2018b
Compatible with R2018a and later releases
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

doc

Version Published Release Notes
1.1.0

The last version contains small improvements, better test coverage, as well as a new experimental feature — CV scope. See more details in the Project GitHub repository.
1.0.4

Fixed a small bug related to ordering of response values for cross-validation.
1.0.3

Fixed a small bug introduced in 1.0.2.
1.0.2

Amall changes to make the toolbox compatible with MATLAB 2017a or newer.
1.0