Premium
Polluter Discriminant Analysis
Author(s) -
Tock Donald G.,
Wright Gordon P.
Publication year - 1976
Publication title -
water resources research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.863
H-Index - 217
eISSN - 1944-7973
pISSN - 0043-1397
DOI - 10.1029/wr012i004p00613
Subject(s) - linear discriminant analysis , discriminant , pollution , environmental science , statistics , computer science , mathematics , artificial intelligence , ecology , biology
A unique water pollution data base for the U.S. coastal waterways and Great Lakes that has been evolving since 1965 is discussed in this paper. The pollution statistics in this data base are used to develop a model, using multiple discriminant techniques, to determine which pollution incident report variables will discriminate the polluter who reports his spill from the polluter who does not report his spill. The results of the analysis as given in this paper indicate that as few as nine variables, out of a possible 60 variables, provide reasonable discriminatory power.