This workflow demonstrates how to do carry out a multidimensional scaling analysis. In multidimensional scaling, a set of distance measures between all pairs of items is used as input data, and the output is a set of dimensions that best captures those distances. In this sample, the data consist of the air distances between 28 US cities. Ideally, the analysis should reveal two underlying dimensions that describe the distance measures between cities (one roughly corresponding to North-South and another roughly corresponding to East-West).