Highway location problem that considers demands and its application to regression analysis

In this paper, we investigate the problem of locating a highway (as a line segment) in a Euclidean plane so that the total travel time between cities can be minimized; we propose a method for estimating its construction. Furthermore, we apply it to a regression analysis by using a highway location in which the speed of the vehicles is considered to be infinite. The disadvantage of the least squares method – a change in the correlation coefficient with a change in the slope of the regression line – can be improved by using this method.