A Bootstrap Method for Identifying and Evaluating a Structural Vector Autoregression

To purchase or authenticate to the full-text of this article, please visit this link: http://dx.doi.org/10.1111/j.1468-0084.2007.00496.x Byline: Selva Demiralp ([dagger]), Kevin D. Hoover ([double dagger]), Stephen J. Perez (s.) Keywords: C30; C32; C51 Abstract: Abstract Graph-theoretic methods of causal search based on the ideas of Pearl (2000), Spirtes et al. (2000), and others have been applied by a number of researchers to economic data, particularly by Swanson and Granger (1997) to the problem of finding a data-based contemporaneous causal order for the structural vector autoregression, rather than, as is typically done, assuming a weakly justified Choleski order. Demiralp and Hoover (2003) provided Monte Carlo evidence that such methods were effective, provided that signal strengths were sufficiently high. Unfortunately, in applications to actual data, such Monte Carlo simulations are of limited value, as the causal structure of the true data-generating process is necessarily unknown. In this paper, we present a bootstrap procedure that can be applied to actual data (i.e. without knowledge of the true causal structure). We show with an applied example and a simulation study that the procedure is an effective tool for assessing our confidence in causal orders identified by graph-theoretic search algorithms. Author Affiliation: ([dagger])Department of Economics, Koc University, Sariyer, Istanbul 34450, Turkey (e-mail:sdemiralp@ku.edu.tr) ([double dagger])Department of Economics, Duke University, 213 Social Science Building, Box 90097, Durham, NC 27708-0097, USA (e-mail:kd.hoover@duke.edu) (s.)Department of Economics, California State University, Sacramento, 6000 J Street, Sacramento, CA 95819-6082, USA (e-mail:sjperez@csus.edu) Article History: Final Manuscript Received: October 2007