Helmut Luetkepohl

• German Institute for Economic Research

We propose a new bootstrap algorithm for inference for impulse responses in structural vector autoregressive models identified with an external proxy variable. Simulations show that the new bootstrap algorithm provides confidence intervals for impulse responses which often have more precise coverage than and similar length to the competing moving-b...

Different local projection (LP) estimators for structural impulse responses of proxy vector autoregressions are reviewed and compared algebraically and with respect to their small sample suitability for inference. Conditions for numerical equivalence and similarities of some estimators are provided. Two generalized least squares (GLS) projection es...

In proxy vector autoregressive models, the structural shocks of interest are identified by an instrument. Although heteroscedasticity is occasionally allowed for in inference, it is typically taken for granted that the impact effects of the structural shocks are time-invariant despite the change in their variances. We develop a test for this implic...

In testing for the cointegrating rank of a vector autoregressive process it is important to take into account level shifts that have occurred in the sample period. Therefore the properties of estimators of the time period where a shift has taken place are investigated. The possible structural break is modeled as a simple shift in the level of the p...

Identification through heteroskedasticity in heteroskedastic simultaneous equations models (HSEMs) is considered. The possibility that heteroskedasticity identifies structural parameters only partially is explicitly allowed for. The asymptotic properties of the identified parameters are derived. Moreover, tests for identification through heterosked...

Tests for identification through heteroskedasticity in structural vector autoregressive analysis are developed for models with two volatility states where the time point of volatility change is known. The tests are Wald type tests for which only the unrestricted model including the covariance matrices of the two volatility states have to be estimat...

In this study, Bayesian inference is developed for structural vector autoregressive models in which the structural parameters are identified via Markov-switching heteroskedasticity. In such a model, restrictions that are just-identifying in the homoskedastic case, become over-identifying and can be tested. A set of parametric restrictions is derive...

Different bootstrap methods and estimation techniques for inference for structural vector autoregressive (SVAR) models identified by generalized autoregressive conditional heteroskedasticity (GARCH) are reviewed and compared in a Monte Carlo study. The bootstrap methods considered are a wild bootstrap, a moving blocks bootstrap and a GARCH residual...

This paper proposes a new nonparametric method of constructing joint confidence bands for impulse response functions of vector autoregressive models. The estimation uncertainty is captured by means of bootstrapping, and the highest density region (HDR) approach is used to construct the bands. A Monte Carlo comparison of the HDR bands with existing...

In this study, Bayesian inference is developed for structural vector autoregressive models in which the structural parameters are identified via Markov-switching heteroskedasticity. In such a model, restrictions that are just-identifying in the homoskedastic case, become over-identifying and can be tested. A set of parametric restrictions is derive...

Methods for constructing joint confidence bands for impulse response functions which are commonly used in vector autoregressive analysis are reviewed. While considering separate intervals for each horizon individually still seems to be the most common approach, a substantial number of methods have been proposed for making joint inferences about the...

We use a cointegrated structural vector autoregressive model to investigate the relation between monetary policy in the euro area and the stock market. Since there may be an instantaneous causal relation, we consider long-run identifying restrictions for the structural shocks and also used (conditional) heteroscedasticity in the residuals for ident...

The performance of information criteria and tests for residual heteroscedasticity for choosing between different models for time‐varying volatility in the context of structural vector autoregressive analysis is investigated. Although it can be difficult to find the true volatility model with the selection criteria, using them is recommended because...

In this survey, estimation methods for structural vector autoregressive models are presented in a systematic way. Both frequentist and Bayesian methods are considered. Depending on the model setup and type of restrictions, least squares estimation, instrumental variables estimation, method-of-moments estimation and generalized method-of-moments are...

In structural vector autoregressive analysis identifying the shocks of interest via heteroskedasticity has become a standard tool. Unfortunately, the approaches currently used for modeling heteroskedasticity all have drawbacks. For instance, assuming known dates for variance changes is often unrealistic while more flexible models based on GARCH or...

There is evidence that estimates of long-run impulse responses of structural vector autoregressive (VAR) models based on long-run identifying restrictions may not be very accurate. This finding suggests that using short-run identifying restrictions may be preferable. We compare structural VAR impulse response estimates based on long-run and short-r...

Identification through heteroskedasticity in heteroskedastic simultaneous equations models (HSEMs) is considered. The possibility that heteroskedasticity identifies structural parameters only partially is explicitly allowed for. The asymptotic properties of the identified parameters are derived. Moreover, tests for identification through heterosked...

Changes in residual volatility in vector autoregressive (VAR) models can be used for identifying structural shocks in a structural VAR analysis. Testable conditions are given for full identification for the case where the volatility changes can be modelled by a multivariate GARCH process. Formal statistical tests are presented for identification an...

Changes in residual volatility are often used for identifying structural shocks in vector autoregressive (VAR) analysis. A number of different models for heteroskedasticity or conditional heteroskedasticity are proposed and used in applications in this context. The different volatility models are reviewed and their advantages and drawbacks are indi...

This paper proposes a new non-parametric method of constructing joint con- fidence bands for impulse response functions of vector autoregressive models. The estimation uncertainty is captured by means of bootstrapping and the highest density region (HDR) approach is used to construct the bands. A Monte Carlo comparison of the HDR bands with existin...

Identification through heteroskedasticity in heteroskedastic simultaneous equations models (HSEMs) is considered. The possibility that heteroskedasticity identifies the structural parameters only partially is explicitly allowed for. The asymptoticproperties of the identified parameters are derived. Moreover, tests for identification through heteros...

Stock market indexes are difficult to predict at longer horizons in efficient markets. Possibilities to improve forecasts of such “unpredictable” variables are considered. In particular, forecasts based on data transformations and multivariate forecasts are compared, using monthly data. Although standard statistical methods indicate that forecast i...

In impulse response analysis estimation uncertainty is typically displayed by constructing bands around estimated impulse response functions. If they are based on the joint asymptotic distribution possibly constructed with bootstrap methods in a frequentist framework, often individual confidence intervals are simply connected to obtain the bands. S...

Changes in residual volatility in vector autoregressive (VAR) models can be used for identifying structural shocks in a structural VAR analysis. Testable conditions are given for full identification for the case where the volatility changes can be modelled by a multivariate GARCH process. Formal statistical tests are presented for identification an...

A growing literature uses changes in residual volatility for identifying structural shocks in vector autoregressive (VAR) analysis. A number of different models for heteroskedasticity or conditional heteroskedasticity are proposed and used in applications in this context. This study reviews the different volatility models and points out their advan...

Changes in residual volatility in vector autoregressive (VAR) models can be used for identifying structural shocks in a structural VAR analysis. Testable conditions are given for full identification for the case where the volatility changes can be modelled by a multivariate GARCH process. Formal statistical tests are presented for identification an...

Changes in residual volatility are often used for identifying structural shocks in vector autoregressive (VAR) analysis. A number of different models for heteroskedasticity or conditional heteroskedasticity are proposed and used in applications in this context. The different volatility models are reviewed and their advantages and drawbacks are indi...

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 be...

In structural vector autoregressive analysis identifying the shocks of interest via heteroskedasticity has become a standard tool. Unfortunately, the approaches currently used for modelling heteroskedasticity all have drawbacks. For instance, assuming known dates for variance changes is often unrealistic while more exible models based on GARCH or M...

In structural vector autoregressive (SVAR) analysis a Markov regime switching (MS) property can be exploited to identify shocks if the reduced form error covariance matrix varies across regimes. Unfortunately, these shocks may not have a meaningful structural economic interpretation. It is discussed how statistical and conventional identifying info...

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 be...

In impulse response analysis estimation uncertainty is typically displayed by constructing bands around estimated impulse response functions. These bands may be based on frequentist or Bayesian methods. If they are based on the joint distribution in the Bayesian framework or the joint asymptotic distribution possibly constructed with bootstrap meth...

In structural vector autoregressive analysis identifying the shocks of interest via heteroskedasticity has become a standard tool. Unfortunately, the approaches currently used for modelling heteroskedasticity all have drawbacks. For instance, assuming known dates for variance changes is often unrealistic while more exible models based on GARCH or M...

In impulse response analysis estimation uncertainty is typically displayed by constructing bands around estimated impulse response functions. These bands may be based on frequentist or Bayesian methods. If they are based on the joint distribution in the Bayesian framework or the joint asymptotic distribution possibly constructed with bootstrap meth...

In vector autoregressive analysis confidence intervals for individual impulse responses are typically reported to indicate the sampling uncertainty in the estimation results. A range of methods are reviewed and a new proposal is made for constructing joint confidence bands, given a prespecifed coverage level, for the impulse responses at all horizo...

In vector autoregressive analyses, confidence intervals for individual impulse responses are typically reported in order to indicate the sampling uncertainty in the estimation results. Various methods are reviewed, and a new method for the construction of joint confidence bands, given a prespecified coverage level, for the impulse responses at all...

Many contemporaneously aggregated variables have stochasticaggregation weights. We compare different forecasts for such variables including univariate forecasts of the aggregate, a multivariate forecast of the aggregate that uses information from the disaggregate components, a forecast which aggregates a multivariate forecast of the disaggregate co...

The paper investigates whether transforming a time series leads to an improvement in forecasting accuracy. The class of transformations that is considered is the Box-Cox power transformation, which applies to series measured on a ratio scale. We propose a nonparametric approach for estimating the optimal transformation parameter based on the freque...

Identification of shocks of interest is a central problem in structural vector autoregressive (SVAR) modelling. Identification is often achieved by imposing restrictions on the impact or long-run effects of shocks or by considering sign restrictions for the impulse responses. In a number of articles changes in the volatility of the shocks have also...

It is emphasized that the shocks in structural vector autoregressions are only identified up to sign and it is pointed out that this feature can result in very misleading confidence intervals for impulse responses if simulation methods such as Bayesian or bootstrap methods are used. The confidence intervals heavily depend on which variable is used...

Economic agents using information that is not incorporated in the econometric model is seen as a possible reason for why nonfundamental shocks are important in econometric models. Allowing for nonfundamental shocks in structural vector autoregressive (SVAR) analysis by considering moving average (MA) representations with roots in the complex unit c...

Given the growing dissatisfaction with exclusion and long-run restrictions in structural vector autoregressive analysis, sign restrictions are becoming increasingly popular. So far there are no techniques for validating the shocks identified via such restrictions. Although in an ideal setting the sign restrictions specify shocks of interest, sign r...

Sometimes forecasts of the original variable are of interest, even though a variable appears in logarithms (logs) in a system of time series. In that case, converting the forecast for the log of the variable to a naïve forecast of the original variable by simply applying the exponential transformation is not theoretically optimal. A simple expressi...

In the presence of generalized conditional heteroscedasticity (GARCH) in the residuals of a vector error correction model (VECM), maximum likelihood (ML) estimation of the cointegration parameters has been shown to be efficient. On the other hand, full ML estimation of VECMs with GARCH residuals is computationally difficult and may not be feasible...

In structural vector autoregressive (SVAR) modeling, sometimes the identifying restrictions are insufficient for a unique specification of all shocks. In this paper it is pointed out that specific distributional assumptions can help in identifying the structural shocks. In particular, a mixture of normal distributions is considered as a possible mo...

Despite the fact that many aggregates are nonlinear functions and the aggregation weights of many macroeconomic aggregates are timevarying, much of the literature on forecasting aggregates considers the case of linear aggregates with fixed, time-invariant aggregation weights. In this study a framework for nonlinear contemporaneous aggregation with...

This paper investigates whether using natural logarithms (logs) of price indices for forecasting inflation rates is preferable to employing the original series. Univariate forecasts for annual inflation rates for a number of European countries and the USA based on monthly seasonal consumer price indices are considered. Stochastic seasonality and de...

For forecasting and economic analysis many variables are used in logarithms (logs). In time series analysis this transformation is often considered to stabilize the variance of a series. We investigate under which conditions taking logs is beneficial for forecasting. Forecasts based on the original series are compared to forecasts based on logs. It...

It is argued that in structural vector autoregressive (SVAR) analysis a Markov regime switching (MS) property can be exploited to identify shocks if the reduced form error covariance matrix varies across states. The model setup is formulated and discussed and it is shown how it can be used to test restrictions which are just-identifying in a standa...

Aggregated times series variables can be forecasted in different ways. For example, they may be forecasted on the basis of the aggregate series or forecasts of disaggregated variables may be obtained first and then these forecasts may be aggregated. A number of forecasts are presented and compared. Classical theoretical results on the relative effi...

It is investigated whether euro area variables can be forecast better based on synthetic time series for the pre-euro period or by using just data from Germany for the pre-euro period. Our forecast comparison is based on quarterly data for the period 1970Q1–2003Q4 for 10 macroeconomic variables. The years 2000–2003 are used as forecasting period. A...

Various criteria for estimating the order of a vector autoregressive process are compared in a simulation study. For the considered processes Schwarz's BIC criterion chooses the correct autoregressive order most often and leads to the smallest mean squared forecasting error in samples of the size usually available in practice.

In multiple time series analysis it is sometimes suggested to remove non-stationarities of the univariate subseries by differencing prior to the multivariate analysis. It is pointed out that, in general, this is not adequate if AR models are built even if stationarity of the univariate subseries can be induced by differencing. Canadian money and in...

A test for the cointegrating rank of a vector autoregressive (VAR) process with a possible shift and broken linear trend is proposed. The break point is assumed to be known. Our test is not a likelihood ratio test but the deterministic terms including the broken trends are removed first by a generalized least squares procedure. Then, a likelihood r...

When applying Johansen's procedure for determining the cointegrating rank to systems of variables with linear deterministic trends, there are two possible tests to choose from. One test allows for a trend in the cointegration relations and the other one restricts the trend to be orthogonal to the cointegration relations. The first test is known to...

A central issue of monetary policy analysis is the specification of monetary policy shocks. In a structural vector autoregressive setting there has been some controversy about which restrictions to use for identifying the shocks because standard theories do not provide enough information to fully identify monetary policy shocks. In fact, to compare...

This paper critically reviews the use of vector autoregressions (VARs) for four tasks: data description, forecasting, structural inference, and policy analysis. The paper begins with a review of VAR analysis, highlighting the differences between reduced-form VARs, recursive VARs and structural VARs. A three variable VAR that includes the unemployme...

The primary aim of the paper is to place current methodological discussions in macroeconometric modeling contrasting the ‘theory first’ versus the ‘data first’ perspectives in the context of a broader methodological framework with a view to constructively appraise them. In particular, the paper focuses on Colander’s argument in his paper “Economist...

Vector autoregressive (VAR) models for stationary and integrated variables are reviewed. Model specification and parameter estimation are discussed and various uses of these models for forecasting and economic analysis are considered. For integrated and cointegrated variables it is argued that vector error correction models offer a particularly con...

This paper deals with the determinants of agents' acquisition of information. Our econometric evidence shows that the general index of Italian share-prices and the series of Italy's financial newspaper sales are cointegrated, and the former series Granger-causes the latter, thereby giving support to the cognitive dissonance hypothesis: (non-profess...

In applied time series analysis, checking for autocorrelation in a fitted model is a routine diagnostic tool. Therefore it is useful to know the asymptotic and small sample properties of the standard tests for the case when some of the variables are cointegrated. The properties of residual autocorrelations of vector error correction models (VECMs)...

A test for the cointegrating rank of a vector autoregressive (VAR) process with a possible shift and broken linear trend is proposed. The break point is assumed to be known. The setup is a VAR process for cointegrated variables. The tests are not likelihood ratio tests but the deterministic terms including the broken trends are removed first by a G...

Aggregated times series variables can be forecasted in different ways. For example, they may be forecasted on the basis of the aggregate series or forecasts of disaggregated variables may be obtained first and then these forecasts may be aggregated. A number of forecasts are presented and compared. Classical theoretical results on the relative effi...

Aggregated times series variables can be forecasted in different ways. For example, they may be forecasted on the basis of the aggregate series or forecasts of disaggregated variables may be obtained first and then these forecasts may be aggregated. A number of forecasts are presented and compared. Classical theoretical results on the relative effi...

Summary Vector autoregressive (VAR) models are capable of capturing the dynamic structure of many time series variables. Impulse response functions are typically used to investigate the relationships between the variables included in such models. In this context the relevant impulses or innovations or shocks to be traced out in an impulse response...

Multivariate simultaneous equations models were used extensively for macroeconometric analysis when Sims (1980) advocated vector autoregressive (VAR) models as alternatives. At that time longer and more frequently observed macroeconomic time series called for models which described the dynamic structure of the variables. VAR models lend themselves...

Vector autoregressive (VAR) models are capable of capturing the dynamic structure of many time series variables. Impulse response functions are typically used to investigate the relationships between the variables included in such models. In this context the relevant impulses or innovations or shocks to be traced out in an impulse response analysis...

A system of U.S. and euro area short- and long-term interest rates is analyzed. According to the expectations hypothesis of the term structure the interest rate spreads should be stationary and according to the uncovered interest rate parity the difference between the U.S. and euro area longterm interest rates should also be stationary. If all four...

Johansen's reduced-rank maximum likelihood (ML) estimator for cointegration parameters in vector error correction models is known to produce occasional extreme outliers. Using a small monetary system and German data we illustrate the practical importance of this problem. We also consider an alternative generalized least squares (GLS) system estimat...

Structural vector autoregressive (VAR) models are in frequent use for impulse response analysis. If cointegrated variables are involved, the corresponding vector error correction models offer a convenient framework for imposing structural long-run and short-run restrictions. Occasionally it is desirable to impose over-identifying restrictions in th...

In Chapter 3, we have discussed estimation of the parameters of a K-dimensional stationary, stable VAR(p) process of the form $$ y_t = \nu + A_1 y_{t - 1} + \ldots + A_p y_{t - p} + u_t , $$ (5.1.1) where all the symbols have their usual meanings. In the investment/income/consumption example considered throughout Chapter 3, we found that many of th...

In the previous chapter, we have assumed that we have given a K-dimensional multiple time series \(y_1 , \ldots ,y_T ,\;with\;y_t = \left( {y_{1t} , \ldots ,y_{Kt} } \right)^\prime , \) which is known to be generated by a VAR(p) process, $$ y_t = v + A_{1yt - 1} + \ldots + A_p y_{t - p} + u_t , $$ (4.1.1) and we have discussed estimation of the par...

This is the new and totally revised edition of Ltkepohl's classic 1991 work. It provides a detailed introduction to the main steps of analyzing multiple time series, model specification, estimation, model checking, and for using the models for economic analysis and forecasting. The book now includes new chapters on cointegration analysis, structura...

Aggregated times series variables can be forecasted in different ways. For example, they may be forecasted on the basis of the aggregate series or forecasts of disaggregated variables may be obtained first and then these forecasts may be aggregated. A number of forecasts are presented and compared. Classical theoretical results on the relative effi...

Time series econometrics is a rapidly evolving field. Particularly, the cointegration revolution has had a substantial impact on applied analysis. Hence, no textbook has managed to cover the full range of methods in current use and explain how to proceed in applied domains. This gap in the literature motivates the present volume. The methods are sk...

Introduction. In the previous chapter we have seen how a model for the DGP of a set of economic time series variables can be constructed. When such a model is available, it can be used for analyzing the dynamic interactions between the variables. This kind of analysis is usually done by tracing the effect of an impulse in one of the variables throu...

Vector autoregressive moving-average (VARMA) processes are suitable models for producing linear forecasts of sets of time series variables. They provide parsimonious representations of linear data generation processes. The setup for these processes in the presence of stationary and cointegrated variables is considered. Moreover, unique or identifie...