Premium
Comments on the article ‘Bilinear estimation of pollution source profiles and amounts by using multivariate receptor models’
Author(s) -
ElShaarawi A. H.
Publication year - 2002
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/env.559
Subject(s) - multivariate statistics , bilinear interpolation , estimation , identification (biology) , econometrics , field (mathematics) , computer science , statistics , mathematics , economics , machine learning , botany , management , pure mathematics , biology
I welcome this article as it sheds new light on the important but difficult problem of the identification of pollution sources and the estimation of their contributions from field monitoring data. The article raises a number of technical issues, which are pertinent to the use of its methods in applications. In particular, a number of assumptions are used but without indicating how they can be tested from the data. I will confine my comments to: (a) the model specification and how it might be used in practice; (b) the estimation of the model's parameters. Copyright © 2002 John Wiley & Sons, Ltd.