Determination of optimal prediction oriented multivariate latent factor models using loss functions

Claus Weihs; Torsten Hothorn

In this paper a projection pursuit method is developed which determines optimal multivariate latent factor models based on a flexible loss function. This way, the unknown model coefficients are estimated with respect to optimal predictive power. The specification of the loss function in practical applications is discussed. The method is illustrated by means of simulation examples.

MoreLess

Year of publication:	2002
Authors:	Weihs, Claus ; Hothorn, Torsten
Publisher:	Dortmund : SFB 475, Universität Dortmund
Subject:	latent factor models \| predictive power \| loss functions \| projection pursuit \| Prognoseverfahren \| Forecasting model \| Theorie \| Theory \| Faktorenanalyse \| Factor analysis \| Schätzung \| Estimation \| Multivariate Analyse \| Multivariate analysis