Identifying significant model inputs with neural networks - Tax court determination of reasonable compensation

Neural networks have much to offer academic researchers and business practi tioners. For example, recent research has shown that neural networks can cl assify and predict as well as traditional statistical methods, such as ordi nary least squares (OLS). Neural networks, however, are limited in that the y do not provide measures of significance of individual inputs as OLS (and other methods) provides. When neural networks overcome this limitation thei r variety and numbers of applications will increase dramatically and they w ill become more valuable to academe and practitioners. This study compares the abilities of OLS and neural networks, when used in conjunction with the Wilcoxen signed-ranks test to identify significant model inputs. (C) 1999 Elsevier Science Ltd. All rights reserved.