has characteristic
has parameter
uses
hybridity
partial least squares regression method
hierarchical cluster-based partial least squares regression method
1
2012-01-18
http://identifiers.org/doi/10.1186/1752-0509-5-90
AZ
HC-PLSR
Multivariate regression method based on separating the observations into clusters and generating Partial Least Squares Regression (PLSR) [http://identifiers.org/biomodels.kisao/KISAO_0000416] models within each cluster. This local regression analysis is suitable for very non-linear systems. PLSR is a regression method based on estimated latent variables, related to Principal Component Analysis (PCA) and Principal Component Regression (PCR).
Hierarchical cluster-based partial least squares regression method uses fuzzy C-means clustering, PLSR and Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) or Naive Bayes for classification of new observations to be predicted.
Requested by Kristin Tøndel on Thursday, October 13, 2011 11:13:17 AM.
number of partial least squares components
partial least squares regression-like method
mean-centring of variables
standardising of variables
matrix for clusterization