Partial Least Squares Regression - Underlying Model

Underlying Model

The general underlying model of multivariate PLS is

\begin{align}
X &= T P^{\top} + E\\
Y &= U Q^{\top} + F,
\end{align}

where is an matrix of predictors, is an matrix of responses; and are matrices that are, respectively, projections of X (the X score, component or factor matrix) and projections of Y (the Y scores); and are, respectively, and orthogonal loading matrices; and matrices and are the error terms, assumed to be i.i.d. normal. The decompositions of X and Y are made so as to maximise the covariance of T and U.

Read more about this topic:  Partial Least Squares Regression

Famous quotes containing the words underlying and/or model:

    Sport in the sense of a mass-spectacle, with death to add to the underlying excitement, comes into existence when a population has been drilled and regimented and depressed to such an extent that it needs at least a vicarious participation in difficult feats of strength or skill or heroism in order to sustain its waning life-sense.
    Lewis Mumford (1895–1990)

    ...that absolutely everything beloved and cherished of the bourgeoisie, the conservative, the cowardly, and the impotent—the State, family life, secular art and science—was consciously or unconsciously hostile to the religious idea, to the Church, whose innate tendency and permanent aim was the dissolution of all existing worldly orders, and the reconstitution of society after the model of the ideal, the communistic City of God.
    Thomas Mann (1875–1955)