Variable Reduction and Variable Selection Methods Using Small, Medium and Large Datasets : A Forecast Comparison for the PEEIs

This paper is concerned with the forecasting performance of variable reduction and variable selection methods using medium and large datasets. The variable reduction methods include Principal Components, Partial Least Squares and Bayesian Shrinkage Regression. The variable selection methods choose the appropriate predictors by minimising an information criterion. We use heuristic optimisation algorithms that are computationally feasible and include the Genetic Algorithm, the Simulated Annealing, the Sequential Testing and the MC3. The medium sets are subsets of the original dataset and are created using: (i) the best representative (most correlated) variable in each category and (ii) estimates of the exponent of cross-sectional dependence introduced recently by Bailey, Kapetanios and Pesaran (2012). We assess the forecasting performance of the above methods in forecasting four principal European economic indicators for the Euro Area economy. These are the quarterly GDP growth, the quarterly final consumption expenditure growth, the monthly industrial production growth and the monthly inflation. Our empirical exercise suggests that smaller datasets highly improve the forecasting performance of variable selection models and slightly enhance the variable reduction models