Monday, October 10, 2016

Spurious correlation in Robert Lucas's "Prize lecture"

By chance the other day I came across Spurious correlation at the FRED Blog. They write:

Relationships between macroeconomic time series are not usually straightforward enough to establish with a simple graph. The problem is that almost all time series tend to grow in the long term as an economy grows... Because time series can exhibit a common trend, it becomes difficult to interpret whether there is a relationship between them beyond that common trend. We call this spurious correlation.

By chance just now I came across an old one of mine containing an excerpt from Robert Lucas's Nobel Prize lecture. This excerpt:

Figure 1, taken from McCandless and Weber (1995), plots 30 year (1960-1990) average annual inflation rates against average annual growth rates of M2 over the same 30 year period, for a total of 110 countries. One can see that the points lie roughly on the 45-degree line, as predicted by the quantity theory. The simple correlation between inflation and money growth is .95.

For Robert Lucas, 110 spurious correlations on one graph is good evidence.

No comments: