Joint Inference and Counterfactual Experimentation for Impulse Response Functions By Local Projections

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. This paper provides three measures of the uncertainty associated to an impulse response path: (1) conditional confidence bands which isolate the uncertainty of individual response coefficients given the temporal path experienced up to that point; (2) response percentile bounds} which provide bounds on the universe of permissible paths at a given probability level; and (3) Wald tests of joint significance and joint cumulative significance. These results rely on general assumptions for the joint distribution of the system's impulse responses. Given this distribution, the paper then shows how to construct counterfactual experiments formally; provides a test on the likelihood of observing the counterfactual; and derives the distribution of the system's responses conditional on the counterfactual. The paper then derives the asymptotic joint distribution of structural impulse responses identified by either short-or long-run recursive assumptions and estimated by local projections (Jorda, 2005). An application to a two country system implements all of these new methods. This paper provides three measures of the uncertainty associated to an impulse response path: Terms of use: Documents in(1) conditional confidence bands which isolate the uncertainty of individual response coefficients given the temporal path experienced up to that point; (2) response percentile bounds which provide bounds on the universe of permissible paths at a given probability level; and (3) Wald tests of joint significance and joint cumulative significance. These results rely on general assumptions for the joint distribution of the system's impulse responses. Given this distribution, the paper then shows how to construct counterfactual experiments formally; provides a test on the likelihood of observing the counterfactual; and derives the distribution of the system's responses conditional on the counterfactual. The paper then derives the asymptotic joint distribution of structural impulse responses identified by either short-or long-run recursive assumptions and estimated by local projections (Jordà, 2005). An application to a two country system implements all of these new methods.

Oil Price Shocks and Inflation Dynamics in Nigeria: Sensitivity of Unit Root to Structural Breaks

“…LPIRF uses a new set of estimates for each horizon and thus avoids escalation of the misspecification error through the non-linearity of the standard VIRFs technique as h increase and h > 1. The advantages of LPIRF over VAR are: (i) it is more robust to misspecification, (ii) it does not involve the same nonlinearity as VAR and hence are more likely to be well approximated by Gaussian distribution, in contrast to VAR and SVAR, assumptions on the structure are not needed (iv) it can be estimated by simple regression and (v) it does not require identification [10,11,12,27].…”

“…These models rely on impulse responses and variance decomposition for interpretation as the coefficients of VAR and SVAR are always impossible to interpret. Impulse responses generated from VAR and SVAR models are biased and inconsistent [10][11][12]. Furthermore, almost all the previous empirical studies on oil price shocks in Nigeria failed to account for structural break in the unit root test.…”