Nm. Faber, Comparison of two recently proposed expressions for partial least squares regression prediction error, CHEM INTELL, 52(2), 2000, pp. 123-134
Two recently proposed expressions for partial least squares (PLS) predictio
n error are compared. Using extensive Monte Carlo simulations, it is found.
that the expression based on the so-called errors-in-variables approach yi
elds prediction intervals with coverage probabilities close to their nomina
l value, whereas the expression, which is implemented in the latest version
of Unscrambler (7.0), is found to behave unsatisfactorily. The difference
between the two approaches is illustrated on a real near-infrared data set
taken from the literature. (C) 2000 Elsevier Science B.V. All rights reserv
ed.