ABSTRACT
This chapter aims to understand the concepts of correlation and linearity, and build and interpret nonlinear regression models, and build and interpret logistic regression models. It discusses several regression techniques as background information and keys to finding adequate models. The forms are simple linear regression, multiple regression, exponential and sine nonlinear regression, binary logistic regression, and Poisson regression. The chapter concerns examples that illustrate some of the misconceptions surrounding correlation and shows possible corrections that the people use in our mathematical modeling courses. It considers sine regression, one-predictor logistics regression, and one-predictor Poisson regression. The logistic function, approximating a unit step function, gave the name logistic regression. The most general form handles dependent variables with a finite number of states. Along with investigating regression, the chapter explains some of the common misconceptions decision makers have concerning correlation and regression.
