First, springs are the machine of fit for a continuous response model (Farebrother, 1987). Suppose that you have n points and that you want to know the expected value (mean) of the points. Envision what happens when you lay the points out on a scale and connect them to a common junction with springs (see Connect Springs to Data Points). When you let go, the springs wiggle the junction point up and down and then bring it to rest at the mean. This is what must happen according to physics.
Connect Springs to Data Points
Effect of Pressure Cylinders in Partitions shows what the situation looks like for a single category such as the medium size cars (see the mosaic column from Carpoll.jmp labeled medium in A Mosaic Plot for Categorical Data). Suppose there are thirteen responses (cars). The first level (American) has six responses, the next has two, and the last has five responses. The response probabilities become 6/13, 2/13, and 5/13, respectively, as the pressure against the response partitions balances out to minimize the total energy.
Effect of Pressure Cylinders in Partitions
A Mosaic Plot for Categorical Data

Help created on 9/19/2017