1 Introduction
In linear regression analysis, sometimes the relationship between X and Y may
not be linear, instead it may suggest nonlinear relationship. In this situation, the
nonlinear regression model or polynomial and/or other nonlinear terms is more
appropriate instead of linear regression model. However, in practice, it is very
difficult to find the exact nonlinear relationship even though there is monotonic
relationship. An alternative approach is to use rank regression for formulating a
nonlinear model [4 – 6]. As noted by Iman and Conover [6], “The mere presence
of so many important input variables makes it difficult to think in terms of finding
an appropriate nonlinear model. This is a case where regressions on ranks become