Title :
Prequential and cross-validated mixture regression estimation
Author :
Modha, Dharmendra S. ; Masry, Elias
Author_Institution :
IBM Almaden Res. Center, San Jose, CA, USA
Abstract :
Prequential model selection and cross-validation are data-driven methodologies for selecting a single “best” model from a collection of competing models. In contrast, we propose prequential and cross-validated mixtures which are suitably weighted combinations of all the rival models under consideration. We empirically study prequential and cross-validated mixtures (both based on neural networks) for regression estimation
Keywords :
estimation theory; neural nets; statistical analysis; cross-validated mixture regression estimation; data-driven methodologies; i.i.d. random variables; neural networks; prequential model selection; Convergence; Data analysis; Neural networks; Postal services; Predictive models; Random variables; USA Councils;
Conference_Titel :
Information Theory, 1998. Proceedings. 1998 IEEE International Symposium on
Conference_Location :
Cambridge, MA
Print_ISBN :
0-7803-5000-6
DOI :
10.1109/ISIT.1998.708964