No Economic Crystal Ball Necessary

You don’t need a crystal ball to tell you what is going to happen next in the economy. You need a statistical model. A new method from North Carolina State University can help researchers determine which economic variables they should focus on by identifying whether a variable can be predicted.

The new method could be a breakthrough for economists and statisticians, says Dr. Mehmet Caner, an associate professor of economics at NC State and co-author of the paper unveiling the new research. “This could lead to much great insight into the national and global economy by providing the impetus to develop new forecasting models for those variables that can be predicted,” he says.

Currently, economists and statisticians use tools called “unit root tests” to determine whether an economic variable – such as unemployment – can be predicted. “The issue,” Caner says, “is that unit root tests often say variables are unpredictable when they actually can be predicted.

“I think our method will show that many variables believed to be unpredictable are actually predictable,” Caner says, “including currency exchange rates and gross domestic product.”

Caner worked with Dr. Keith Knight, of the University of Toronto, to develop an entirely new method using new models to better differentiate between predictable and unpredictable economic variables.

The idea stemmed in part from the use of Bridge estimator models in medical research to identify sections of genetic code that may be related to disease. Caner and Knight saw that similar techniques could be used to determine which economic variables within an economic system might be predictable.

Caner will present the new research, “No Country for Old Unit Root Tests: Bridge Estimators Differentiate between Nonstationary versus Stationary Models and Select Optimal Lag,” at the European Economic Association and Econometric Society European meeting being held in Barcelona, Spain, from Aug. 23-27.

-shipman-

Note to editors: The presentation abstract follows.

“No Country for Old Unit Root Tests: Bridge Estimators Differentiate between Nonstationary versus Stationary Models and Select Optimal Lag”

Authors: Mehmet Caner, North Carolina State University; Keith Knight, University of Toronto.

Presented: Aug. 23-27, 2009, at the European Economic Association and Econometric Society European meeting in Barcelona, Spain.

Abstract: This paper introduces a novel way of differentiating a unit root from a stationary alternative. We write up the model consisting of “zero” and “nonzero” parameters. If the lagged dependent variable has a coefficient of zero, we know that the variable has a unit root. We exploit this property and treat this as a model selection problem. We show that Bridge estimators can select the correct model. They estimate “zero” parameter on the lagged dependent variable as zero (nonstationarity), if this is nonzero (stationary), estimate the coefficient with standard normal limit. In this sense, we extend the statistics literature as well, since that literature only deals with model selection among only stationary variables. The reason that our methodology can outperform the existing unit root tests with lag selection methods stems from the two-step nature of existing unit root tests. In our method, we select the optimal lag length and unit root simultaneously. We show that in simulations, this makes big difference in terms of size and power.