Abstract
A great part of the defense literature is focused on the interaction between military spending and economic activity. To investigate this interrelationship, researchers have applied a wide variety of methodologies with totally different assumptions and statistical properties. Until today, however, no detailed examination of the sensitivity of empirical results to the various statistical methods has been provided in the literature. The present paper attempts to fill this gap by providing, firstly, a review of the majority of the time series methodologies used in the defense–growth literature and, secondly, an econometric application using data of the U.S. economy over the period 1961–2015 in order to establish empirically the association between econometric procedures and empirical results. The empirical findings of the conducted analysis suggest that statistical methods can indeed become a significant source of variation in the investigation of the defense–growth nexus.
Acknowledgements
We are grateful to Christos Kollias and an anonymous referee for their helpful and constructive suggestions that helped improve the paper. The usual disclaimer applies.
Notes
1. In the frame of this test the used auxiliary equation does not include a constant and trend in its mathematical format.
2. The probability value of the corresponding heteroskedasticity test was found equal to 0.0205.