This paper continues the work of this series with two results. The first is an exponential equivalence theorem which states that every generalized least-squares regression line can be generated by an equivalent exponential regression. It follows that every generalized least-squares line has an effective normalized exponential parameter between 0 and 1 which classifies the line on the spectrum between ordinary least-squares and the extremal line for a given set of data. The second result is the presentation of fundamental formulas for the generalized least-squares slope and y-intercept.
N. Greene. "Generalized Least-Squares Regressions III: Further Theory and Classification," in Proceedings of the 5th International Conference on Applied Mathematics and Informatics (AMATHI '14), 2014, pp. 34-38.