Predictive Subset VAR Modeling Using the Genetic Algorithm and Information Complexity


  • Andrew Howe Tennessee Valley Authority
  • Hamparsum Bozdogan University of Tennessee


Model Selection, Multivariate Time Series, Forecast Evaluation, Robustness, Information Criteria, Stochastic Search


Can we use lagged values of major stock market indices to provide useful predictions as a standard vector autoregressive model? Underlying this application, of course, is the question of finding a vector autoregressive model which makes accurate and efficient forecasts.

In this paper, we use the Genetic Algorithm with information complexity criteria as the fitness function to drive subset selection and parameter estimation. In the testing period when the target index lost more than 15%, the identified subset VAR model gained over 17%.

The prediction error bands built around the forecasts are half as wide as those obtained by the saturated model. Using both simulation and application studies, we present evidence that even when the typical regression assumptions seem to be met, the VAR model is misspecified.

Author Biographies

  • Andrew Howe, Tennessee Valley Authority
    Senior Specialist, Energy Market Strategist
  • Hamparsum Bozdogan, University of Tennessee
    Toby & Brenda McKenzie Professor in Business, in Information Complexity, and Model Selection Department of Statistics, Operations and Management Science, 336 SMC The University of Tennessee Knoxville, TN 37996-0532 USA






Special Issue on Granger Econometrics and Statistical Modeling

How to Cite

Predictive Subset VAR Modeling Using the Genetic Algorithm and Information Complexity. (2010). European Journal of Pure and Applied Mathematics, 3(3), 382-405.