Measuring Inflation and Growth Using Spanning Trees.

It is shown how most methods of measuring inflation and growth have an underlying spanning tree. The spanning tree whose resulting inflation (growth) estimates are least sensitive to the choice of index number formula can be computed using Kruskal's minimum spanning tree algorithm. Applying this algorithm to American, British, and Australian data sets, chaining is shown to be the best possible way of linking annual data. For quarterly data, the optimal method of linking depends on the amount of seasonality in the data.