Jörg Breitung's research while affiliated with University of Cologne and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (29)
This paper studies the asymptotic properties of endogeneity corrections based on nonlinear transformations without external instruments, which were originally proposed by Park and Gupta (2012) and have become popular in applied research. In contrast to the original copula-based estimator, our approach is based on a nonparametric control function an...
In this paper we provide a general two‐step framework for linear projection estimators of impulse responses in structural vector autoregressions (SVARs). This framework is particularly useful for situations when structural shocks are identified from information outside the VAR (e.g. narrative shocks). We provide asymptotic results for statistical i...
This paper considers a linear regression model with an endogenous regressor which is not normally distributed. It is shown that the corresponding coefficient can be consistently estimated without external instruments by adding a rank-based transformation of the regressor to the model and performing standard OLS estimation. In contrast to other appr...
It is well known that the conventional cumulative sum (CUSUM) test suffers from low power and large detection delay. In order to improve the power of the test, we propose two alternative statistics. The backward CUSUM detector considers the recursive residuals in reverse chronological order, whereas the stacked backward CUSUM detector sequentially...
A correction to this paper has been published: https://doi.org/10.1007/s00181-021-02074-8
A computationally simple bias correction for linear dynamic panel data models is proposed and its asymptotic properties are studied when the number of time periods is fixed or tends to infinity with the number of panel units. The approach can accommodate both fixed-effects and random-effects assumptions, heteroskedastic errors, as well as higher-or...
We develop tests for the null hypothesis that forecasts become uninformative beyond some maximum forecast horizon h*. The forecast may result from a survey of forecasters or from an estimated parametric model. The first class of tests compares the mean‐squared prediction error of the forecast to the variance of the evaluation sample, whereas the se...
In this paper, we compare alternative estimation approaches for factor augmented panel data models. Our focus lies on panel data sets where the number of panel groups (N) is large relative to the number of time periods (T). The principal component (PC) and common correlated effects (CCE) estimators were originally developed for panel data with larg...
We analyse estimation procedures for the panel data models with heterogeneous slopes. Specifically we take into account a possible dependence between regressors and heterogeneous slope coefficients, which is referred to as systematic variation. It is shown that under relevant forms of systematic slope variations (i) the pooled OLS estimator is seve...
It is well known that the conventional CUSUM test suffers from low power and large detection delay. We therefore propose two alternative detector statistics. The backward CUSUM detector sequentially cumulates the recursive residuals in reverse chronological order, whereas the stacked backward CUSUM detector considers a triangular array of backward...
In this article, we propose instrumental variables (IV) and generalized method of moments (GMM) estimators for panel data models with weakly exogenous variables. The model is allowed to include heterogeneous time trends besides the standard fixed effects (FE). The proposed IV and GMM estimators are obtained by applying a forward filter to the model...
The frequency-specific Granger causality test is extended to a more general null hypothesis that allows causality testing at unknown frequencies within a pre-specified range of frequencies. This setup corresponds better to empirical situations encountered in applied research and it is easily implemented in vector autoregressive models. Furthermore...
This paper employs the Lagrange Multiplier (LM) principle to test parameter homogeneity across cross-section units in panel data models. The test can be seen as a generalization of the Breusch-Pagan test against random individual effects to all regression coeffcients. While the original test procedure assumes a likelihood framework under normality,...
The popular volatility models focus on the conditional variance given past observations, whereas the (arguably most important) information in the current observation is ignored. This paper proposes a simple model for now-casting volatilities based on a specific ARMA representation of the log-transformed squared returns that allows us to estimate th...
In this paper a nonparametric approach for estimating mixed-frequency forecast equations is proposed. In contrast to the popular MIDAS approach that employs an (exponential) Almon or Beta lag distribution, we adopt a penalized least-squares estimator that imposes some degree of smoothness to the lag distribution. This estimator is related to nonpar...
We propose several tests for rational bubbles and investigate their power properties. The focus lies on the case where bubble
detection is reduced to testing for a unknown change from a random walk to an explosive process. In simulations, a Chow-type
break test exhibits the highest power and performs well relative to the power envelope. The Chow-ty...
Replacing rational expectations by adaptive learning algorithms complicates the dynamics of economic models. Identification of the structural parameters may improve relative to rational expectations, but it deteriorates when learning converges. Learning also induces persistent dynamics, and this makes the distribution of estimators and test statist...
It has become common in economics and in epidemiology to make studies in which subjects are followed over time (longitudinal data) or the observations are structured into groups sharing common unmeasured characteristics (hierarchical data). These studies may be more informative than simple crosssectional data, but they need an appropriate statistic...
Stock and Watson (2002a, 2002b) have suggested a principal component approach to forecasting macroeconomic variables using dynamic factors extracted from a large number of predictors. As has been demonstrated, the relative performance of this new forecasting technique may be dramat-ically better than forecasts based on traditional forecasting techn...
This chapter introduces the tools available in XploRe for analyzing microdata, i.e. data sets consisting of observations on N individual units, such as persons, households or firms.
A test procedure based on ranks is suggested to test for nonlinear cointegration. For two (or more) time series it is assumed that there exist monotonic transformations such that the normalized series can asymptotically be represented by independent Brownian motions. Rank test procedures based on the difference between the sequences of ranks are su...
In this paper two questions are addressed: (i) Do monetary shocks have an effect on bank loan supply in the euro area? (ii) Does bank loan supply affect output? To identify loan supply effects the strategy of Driscoll (2004) is employed. The empirical analysis applies a panel econometric approach. The analysis comprises of quarterly data since the...
This paper investigates whether interest rate changes impact on firms' marginal costs and whether this has a direct effect on their price setting be-havior, translating into aggregate inflation dynamics. Empirical tests on the existence of the cost channel are employed, using a structural econometric approach. Estimation and inference is conducted...
Correct inference on the coefficients of dynamic regression models depends in a crucial manner on the degree of persistence of the explanatory variables. While standard asymptotic inference applies in OLS regressions with stationary regressors, the limiting distributions are nonstandard in the presence of integrated regressors. The paper studies te...
How big are cross-country and cross-sector differences in import and export behaviour? A panel of manufacturing industries in several developed countries reveals that there is substantial variation across sectors, in the response of trade to changes in prices and incomes. Ignoring this heterogeneity can render conventional results biased and incons...
Citations
... Recently, Breitung et al. (2023) argued that it remains uncertain a priori whether the standard properties of maximum likelihood (ML) estimation hold for IV-free copula-based endogeneity corrections and under which assumptions they may be applicable. The challenge of formulating precise statements about limiting properties in the presence of a nonparametrically generated regressor is a highly intricate task. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/11431281087707013-1664808327369_Q64/Dominik-Wied.jpg)
... The paper is also part of a broad literature that studies the advantages of IRF estimation using LP estimators, relative to constructing IRFs on vector autoregressive models. Several contributions document the performance of LP estimators, including Gonçalves et al. (2022), Kilian and Kim (2011), Alloza et al. (2019, Breitung et al. (2019) Herbst and Johannsen (2021), and Bruns and Lütkepohl (2022). While LP estimators are usually proposed in a frequentist setting, we follow Miranda-Agrippino and Ricco (2021) and take a Bayesian approach to LP, yet in a non-linear framework. ...
... This is used to estimate the baseline level, which is produced by the over-performing predictive model identified in the testing set and corresponds to the "expected" web query activity under normal conditions or in the absence of the disruptive pandemic. The choice of the length of h is based on two important criteria: (i) it should be smaller than the testing window [45] and (ii) it should be short enough so as to minimize the risk of losing the forecasting accuracy that is bared by longer forecasts [46]. Of note, the best performing model specifications uncovered in the out-of-sample setting are first reestimated and their parameters optimized over the entire pre-pandemic window of length 131 before issuing point forecasts for the following 27 weeks. ...
... In this way, a specific approach that accounts for heteroscedasticity and cross-sectional dependence was applied to understand the channel through which electricity fluctuations affect the tax base in SSA. To correct the bias embedded in the traditional panel estimators, (Breitung et al., 2022;Everaert & Pozzi, 2007) suggest the use of linear dynamic panel models that overcome the challenges related to traditional panel estimators. Similarly, Kweka (2023) applied the same approach in analysing the effect of terms of trade on tax revenue in SSA. ...
... Failing to reject the null hypothesis suggests projections are efficient. We determine the maximum informative projection horizon by comparing the projections' mean-squared prediction errors to the variance of the evaluation sample as proposed by Breitung and Knüppel (2021). The Breitung and Knüppel test states that the ideal projection equals the conditional expectation μ h, t = E(P t, t − h |I t − h ) under quadratic loss, where P t, t − h is the projection for year t at horizon h and I t − h is defined as the information set available at time th. ...
... 12. See Ahn et al. (2013), Breitung and Hansen (2021), and Brown (2022) Combined with Theorem 2.1, Lemma 2.3 implies that the τ g,t s are identified under ...
... Starting from the individual model's significance in GMM, we also used the Hansen test to validate the instruments deployed in the model, and the Hausman test to confirm the choice between GLS and GMM (and the evaluation between fixed and random effects) (Breitung and Salish 2021). Following these tests, we assumed that the results were consistent with our baseline findings using the GLS model. ...
... We revisit the GMM estimator for linear dynamic panel data models for the robustness and validity check of the model, estimator specified with linear moment conditions, and fixed effects (Arellano and Bover 1995;Blundell and Bond 1998;Hayakawa et al. 2019;Kripfganz and Schwarz 2019;Manuel Arellano and Stephen Bond, 1991). GMM handles endogeneity, controls for unobserved heterogeneity, and accounts for serial correlation in the error term. ...
... The sum of all significant values of unconditional GC is equal to ∑ f ∈( f 1 , f 2 ;d) BGCS 1,2→3 ( f ) = 0.552 (Fig. 6G). The spectral interval of interest of the unconditional GC spectrum ( f ∈ [18,20]) is determined by bifrequencies ( f 1 = 8.5, f 2 = 10.5). The sum of all significant values of unconditional GC in this spectral interval is equal to ∑ f ∈( f 1 , f 2 ;d) BGCS 1,2→3 ( f ) = 0.128 (Fig. 6H). ...
... Ignoring this argument for individual characteristic features of these countries may result in biased estimation and inference (Breitung et al., 2016). Therefore, besides the CSD, homogeneity in slope coefficients is a critical issue to explore before executing panel data analysis. ...
