% Generated by roxygen2: do not edit by hand % Please edit documentation in R/PLSDA_class.R \name{PLSDA} \alias{PLSDA} \title{Partial least squares discriminant analysis} \usage{ PLSDA(number_components = 2, factor_name, pred_method = "max_prob", ...) } \arguments{ \item{number_components}{(numeric, integer) The number of PLS components. The default is \code{2}.\cr} \item{factor_name}{(character) The name of a sample-meta column to use.} \item{pred_method}{(character) Prediction method. Allowed values are limited to the following: \itemize{ \item{\code{"max_yhat"}: The predicted group is selected based on the largest value of y_hat.}\item{\code{"max_prob"}: The predicted group is selected based on the largest probability of group membership.}} The default is \code{"max_prob"}.} \item{...}{Additional slots and values passed to \code{struct_class}.} } \value{ A \code{PLSDA} object with the following \code{output} slots: \tabular{ll}{ \code{scores} \tab (DatasetExperiment) \cr \code{loadings} \tab (data.frame) \cr \code{yhat} \tab (data.frame) \cr \code{design_matrix} \tab (data.frame) \cr \code{y} \tab (data.frame) \cr \code{reg_coeff} \tab (data.frame) \cr \code{probability} \tab (data.frame) \cr \code{vip} \tab (data.frame) \cr \code{pls_model} \tab (list) \cr \code{pred} \tab (data.frame) \cr \code{threshold} \tab (numeric) \cr \code{sr} \tab (data.frame) Selectivity ratio for a variable represents a measure of a variable's importance in the PLS model. The output data.frame contains a column of selectivity ratios, a column of p-values based on an F-distribution and a column indicating significance at p < 0.05. \cr \code{sr_pvalue} \tab (data.frame) A p-value computed from the Selectivity Ratio based on an F-distribution. \cr } } \description{ PLS is a multivariate regression technique that extracts latent variables maximising covariance between the input data and the response. The Discriminant Analysis variant uses group labels in the response variable. For >2 groups a 1-vs-all approach is used. Group membership can be predicted for test samples based on a probability estimate of group membership, or the estimated y-value. } \details{ This object makes use of functionality from the following packages:\itemize{ \item{\code{pls}}} } \section{Inheritance}{ A \code{PLSDA} object inherits the following \code{struct} classes: \cr\cr \verb{[PLSDA]} >> \verb{[PLSR]} >> \verb{[model]} >> \verb{[struct_class]} } \examples{ M = PLSDA( number_components = 2, factor_name = "V1", pred_method = "max_prob") M = PLSDA('number_components'=2,factor_name='Species') } \references{ Liland K, Mevik B, Wehrens R (2023). \emph{pls: Partial Least Squares and Principal Component Regression}. R package version 2.8-3, \url{https://CRAN.R-project.org/package=pls}. Perez NF, Ferre J, Boque R (2009). "Calculation of the reliability of classification in discriminant partial least-squares binary classification." \emph{Chemometrics and Intelligent Laboratory Systems}, \emph{95}(2), 122-128. Barker M, Rayens W (2003). "Partial least squares for discrimination." \emph{Journal of Chemometrics}, \emph{17}(3), 166-173. }