Structural Vector Autoregressions: Checking Identifying Long‐run Restrictions via Heteroskedasticity

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. Abstract. Long-run restrictions have been used extensively for identifying structural shocks in vector autoregressive (VAR) analysis. Such restrictions are typically just-identifying but can be checked by utilizing changes in volatility. This paper reviews and contrasts the volatility models that have been used for this purpose. Three main approaches have been used, exogenously generated changes in the unconditional residual covariance matrix, changing volatility modelled by a Markov switching mechanism and multivariate generalized autoregressive conditional heteroskedasticity (GARCH) models. Using changes in volatility for checking long-run identifying restrictions in structural VAR analysis is illustrated by reconsidering models for identifying fundamental components of stock prices. Terms of use: Documents in

Are There Bubbles in Stock Prices? Testing for Fundamental Shocks

“…Note that for Italy however, the long-run effect of the shock is insignificant at the 90% confidence level. Such a result is also found in Lütkepohl and Velinov (2014) when the identification scheme is rejected. This could mean that the identified shock is not necessarily a fundamental one to stock prices.…”

“…In particular, we find as in Lütkepohl and Velinov (2014) that the long-run impulse response is less significant when the identification restriction is rejected. This is the case for Italy.…”

“…Finally, recall that for Germany and the UK the contemporaneous matrix may not be identified through heteroskedasticity. As is argued in Lütkepohl and Velinov (2014), this would mean that the p-values for these countries in Table 3 are overstated. However, since these values are rather high (well above the 10% level) this may not be a serious problem.…”

Choosing between Different Time-Varying Volatility Models for Structural Vector Autoregressive Analysis

“…The model was first proposed for SVAR analysis by Lanne et al (2010). It has been used in a range of applied SVAR studies including Velinov and Chen (2015), Lütkepohl and Netšunajev (2014a), and Lütkepohl and Velinov (2016).…”

Fiscal multipliers in a structural VEC model with mixed normal errors

“…The nonuniqueness of B may imply that the actual number of degrees of freedom of the 2 -distribution in the LR-test is less than 6 (see e.g. Lütkepohl and Velinov 2014). Given the rejection of the …rst restricted model at 6 degrees of freedom, the same test statistic leads to rejection with a lower number of degrees of freedom as well.…”