The Stock Market Crash - VECM's & Structural Breaks

A few weeks ago, Roger Farmer kindly drew my attention to a recent paper of his - "The Stock Market Crash Really Did Cause the Great Recession" (here). To whet your appetites, here's the abstract:

"This note shows that a big stock market crash, in the absence of central bank intervention, will be followed by a major recession one to four quarters later. I establish this fact by studying the forecasting ability of three models of the unemployment rate. I show that the connection between changes in the stock market and changes in the unemployment rate has remained structurally stable for seventy years. My findings demonstrate that the stock market contains significant information about future unemployment."

The three model's that Roger is referring to are a univariate model for the unemployment rate, a VECM, and a bivariate VAR model - all estimated using EViews. Models of the latter two types have featured heavily in past post on this blogs.

Apart from the "big message" of the paper, as expressed very clearly in the abstract, there's an important secondary message that also accords well with some of my previous posts - e.g., here and here. Namely, if there are structural breaks in the cointegrating vector, this can have a seriously adverse effect on the predictive performance of a VECM.

I fully agree with Roger when he concludes that:

"The failure of (his) VECM as a forecasting tool does not imply that we should ignore the cointegrating relationship between unemployment and the stock market when formulating economic policy. When there are occasional breaks in cointegrating equations, models specified in first differences are known to generate mode accurate forecasts, even if the data generating process is a VECM." (p.11)

Read this paper - you'll learn a lot.

© 2013, David E. Giles