The paper contains some misprints and to avoid misunderstandings we choose to present here the main results again.
Theorem 1 Let y t
, T be i.i.d., where ε t has symmetric continuous density f (.) with mean zero, variance one, and E[ε 8t ] < ∞. Let T = T 1 +T 2 , and assume that T 1 /T → λ 1 and T 2 /T → λ 2 where 0 < λ 1 , λ 2 < 1, with λ 1 + λ 2 = 1, The online version of the original article can be found under
We develop a new automatically-computable test for super exogeneity, using a variant of generalto-specific modeling. Based on the recent developments of impulse saturation applied to marginal models under the null that no impulses matter, we select the significant impulses for testing in the conditional. Since zero-mean changes are relatively undetectable in both VARs and conditional equations, we focus on location shifts, although we also discuss variance changes. The approximate analytical non-centrality of the test is derived for a failure of weak exogeneity when there is a shift in the marginal process. Monte Carlo simulations confirm the empirical accuracy of the nominal significance levels under the null, and show rejections for this failure of super exogeneity. An empirical application to UK M1 delivers new results for this much-studied data set.
OLS estimation of an impulse-indicator coefficient is inconsistent, but its variance can be consistently estimated. Although the ratio of the inconsistent estimator to its standard error has a tdistribution, that test is inconsistent: one solution is to form an index of indicators. We provide Monte Carlo evidence that including a plethora of indicators need not distort model selection, permitting the use of many dummies in a general-to-specific framework. Although White's (1980) heteroskedasticity test is incorrectly sized in that context, we suggest an improvement. Finally, a possible modification to impulse 'intercept corrections' is considered.JEL classifications: C51, C22.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.